[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-browserbase-company-research":3,"mdc-2qgrow-key":37,"related-repo-browserbase-company-research":1820,"related-org-browserbase-company-research":1932},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":35,"mdContent":36},"company-research","conduct deep company and product research","Company discovery and deep research skill. Researches a company's product and ICP,\ndiscovers target companies to sell to using Browserbase Search API, deeply researches\neach using a Plan→Research→Synthesize pattern, and scores ICP fit — compiled into\na scored research report and CSV. Supports depth modes (quick\u002Fdeep\u002Fdeeper) for\nbalancing scale vs intelligence.\nUse when the user wants to: (1) find companies to sell to, (2) research potential\ncustomers, (3) discover companies matching an ICP, (4) build a target company list,\n(5) do market research on prospects. Triggers: \"find companies to sell to\",\n\"company research\", \"find prospects\", \"ICP research\", \"target companies\",\n\"who should we sell to\", \"market research\", \"lead research\", \"prospect list\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"browserbase","Browserbase","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fbrowserbase.png",[12,16,19,22,23],{"name":13,"slug":14,"type":15},"Research","research","tag",{"name":17,"slug":18,"type":15},"Competitive Intelligence","competitive-intelligence",{"name":20,"slug":21,"type":15},"Marketing","marketing",{"name":9,"slug":8,"type":15},{"name":24,"slug":25,"type":15},"Sales","sales",3649,"https:\u002F\u002Fgithub.com\u002Fbrowserbase\u002Fskills","2026-04-27T05:34:56.172569","MIT",232,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"Browserbase's official collection of agent skills to access the web.","https:\u002F\u002Fgithub.com\u002Fbrowserbase\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fcompany-research","---\nname: company-research\ndescription: |\n  Company discovery and deep research skill. Researches a company's product and ICP,\n  discovers target companies to sell to using Browserbase Search API, deeply researches\n  each using a Plan→Research→Synthesize pattern, and scores ICP fit — compiled into\n  a scored research report and CSV. Supports depth modes (quick\u002Fdeep\u002Fdeeper) for\n  balancing scale vs intelligence.\n  Use when the user wants to: (1) find companies to sell to, (2) research potential\n  customers, (3) discover companies matching an ICP, (4) build a target company list,\n  (5) do market research on prospects. Triggers: \"find companies to sell to\",\n  \"company research\", \"find prospects\", \"ICP research\", \"target companies\",\n  \"who should we sell to\", \"market research\", \"lead research\", \"prospect list\".\nlicense: MIT\ncompatibility: Requires browse CLI (`npm install -g browse`) and BROWSERBASE_API_KEY env var\nallowed-tools: Bash Agent\nmetadata:\n  author: browserbase\n  version: \"1.1.0\"\n---\n\n# Company Research\n\nDiscover and deeply research companies to sell to. Uses Browserbase Search API for discovery and a Plan→Research→Synthesize pattern for deep enrichment — outputting a scored research report and CSV.\n\n**Required**: `BROWSERBASE_API_KEY` env var and `browse` CLI installed.\n\n**First-run setup**: On the first run you'll be prompted to approve `browse cloud fetch`, `browse cloud search`, `cat`, `mkdir`, `sed`, etc. Select **\"Yes, and don't ask again for: browse cloud fetch:\\*\"** (or equivalent) for each to auto-approve for the session. To permanently approve, add these to your `~\u002F.claude\u002Fsettings.json` under `permissions.allow`:\n```json\n\"Bash(browse:*)\", \"Bash(bunx:*)\", \"Bash(bun:*)\", \"Bash(node:*)\",\n\"Bash(cat:*)\", \"Bash(mkdir:*)\", \"Bash(sed:*)\", \"Bash(head:*)\", \"Bash(tr:*)\", \"Bash(rm:*)\"\n```\n\n**Path rules**: Always use the full literal path in all Bash commands — NOT `~` or `$HOME` (both trigger \"shell expansion syntax\" approval prompts). Resolve the home directory once and use it everywhere. When constructing subagent prompts, replace `{SKILL_DIR}` with the full literal path.\n\n**Output directory**: All research output goes to `~\u002FDesktop\u002F{company_slug}_research_{YYYY-MM-DD}\u002F`. This directory contains one `.md` file per researched company plus a final `.csv`. The user gets both the scored spreadsheet and the full research files on their Desktop.\n\n**CRITICAL — Tool restrictions (applies to main agent AND all subagents)**:\n- All web searches: use `browse cloud search`. NEVER use WebSearch.\n- All page content extraction: use `node {SKILL_DIR}\u002Fscripts\u002Fextract_page.mjs \"\u003Curl>\"`. This script fetches via `browse cloud fetch --output`, parses title + meta tags + visible body text, and automatically falls back to `browse get markdown` when fetch fails or returns thin JS-rendered content. NEVER hand-roll a `browse cloud fetch | sed` pipeline — it strips meta tags and doesn't parse the stdout JSON envelope. NEVER use WebFetch.\n- All research output: subagents write **one markdown file per company** to `{OUTPUT_DIR}\u002F{company-slug}.md` using bash heredoc. NEVER use the Write tool or `python3 -c`. See `references\u002Fexample-research.md` for the file format.\n- Report + CSV compilation: use `node {SKILL_DIR}\u002Fscripts\u002Fcompile_report.mjs {OUTPUT_DIR} --open` — generates HTML report and CSV in one step, opens overview in browser.\n- URL deduplication: use `node {SKILL_DIR}\u002Fscripts\u002Flist_urls.mjs \u002Ftmp` after discovery.\n- **Subagents must use ONLY the Bash tool. No other tools allowed.**\n- **Main agent NEVER reads raw discovery JSON batch files.** Use `list_urls.mjs` for dedup.\n\n**CRITICAL — Anti-hallucination rules (applies to main agent AND all subagents)**:\n- NEVER infer `product_description`, `industry`, or `target_audience` from a site's fonts, framework (Framer\u002FNext.js\u002FReact), design system, or typography. These are cosmetic and say nothing about what the company sells.\n- NEVER let the user's own ICP leak into a target's description. If you don't know what the target does, write `Unknown` — do not pattern-match them onto the ICP.\n- `product_description` MUST quote or paraphrase a specific phrase from `extract_page.mjs` output (TITLE, META_DESCRIPTION, OG_DESCRIPTION, HEADINGS, or BODY). If none of those fields yield a recognizable product statement, write `Unknown — homepage content not accessible`.\n- If `product_description` is `Unknown`, cap `icp_fit_score` at 3 and set `icp_fit_reasoning` to `Insufficient evidence — homepage returned no readable content`.\n\n**CRITICAL — Minimize permission prompts**:\n- Subagents MUST batch ALL file writes into a SINGLE Bash call using chained heredocs. One Bash call = one permission prompt.\n- Batch ALL searches and ALL fetches into single Bash calls using `&&` chaining.\n\n## Pipeline Overview\n\nFollow these 5 steps in order. Do not skip steps or reorder.\n\n1. **Company Research** — Deeply understand the user's company, product, and who they sell to\n2. **Depth Mode Selection** — Choose research depth based on how many targets they want\n3. **Discovery** — Find target companies using diverse search queries\n4. **Deep Research & Scoring** — Research each company, score ICP fit\n5. **Report & CSV** — Present findings, compile scored CSV\n\n---\n\n## Step 0: Setup Output Directory\n\nBefore starting, create the output directory on the user's Desktop:\n\n```bash\nOUTPUT_DIR=~\u002FDesktop\u002F{company_slug}_research_{YYYY-MM-DD}\nmkdir -p \"$OUTPUT_DIR\"\n```\n\nReplace `{company_slug}` with the user's company name (lowercase, hyphenated) and `{YYYY-MM-DD}` with today's date. Pass `{OUTPUT_DIR}` (as a full literal path, not with `~`) to all subagent prompts so they write research files there.\n\nAlso clean up discovery batch files from prior runs:\n```bash\nrm -f \u002Ftmp\u002Fcompany_discovery_batch_*.json\n```\n\n## Step 1: Deep Company Research\n\nThis is the most important step. The quality of everything downstream depends on deeply understanding the user's company.\n\n1. Ask the user for their company name or URL\n\n2. **Check for an existing profile**:\n   - List files in `{SKILL_DIR}\u002Fprofiles\u002F` (ignore `example.json`)\n   - If a matching profile exists → load it, present to user: \"I have your profile from {researched_at}. Still accurate?\" If yes → skip to Step 2.\n   - If no profile exists → proceed with deep research below.\n\n3. **Run a full deep research on the user's company** using the Plan→Research→Synthesize pattern.\n   See `references\u002Fresearch-patterns.md` for sub-question templates and research methodology.\n\n   **Key research steps:**\n   - Search: `browse cloud search \"{company name}\" --num-results 10`\n   - Fetch homepage: `node {SKILL_DIR}\u002Fscripts\u002Fextract_page.mjs \"{company website}\"`\n   - **Discover site pages via sitemap** (do NOT hardcode paths like `\u002Fabout` or `\u002Fcustomers`):\n     1. `browse cloud fetch --allow-redirects \"{company website}\u002Fsitemap.xml\"` — sitemap is small, raw `browse cloud fetch` is fine\n     2. Scan for URLs with keywords: `customer`, `case-stud`, `pricing`, `about`, `use-case`, `industry`, `solution`\n     3. Optionally also fetch `\u002Fllms.txt` for page descriptions\n     4. Pick 3-5 most relevant URLs and extract with `extract_page.mjs` (NOT raw `browse cloud fetch`)\n   - Search for external context and competitors\n   - Accumulate findings with confidence levels\n\n   **Synthesize into a profile**:\n   Company, Product, Existing Customers, Competitors, Use Cases.\n   Do NOT include ICP or sub-verticals — those are per-run decisions.\n\n4. Present the profile to the user for confirmation. Do not proceed until confirmed.\n\n5. **Save the confirmed profile** to `{SKILL_DIR}\u002Fprofiles\u002F{company-slug}.json`\n\n6. **Ask clarifying questions** using `AskUserQuestion` with checkboxes:\n   - \"Which segments are you targeting?\" with options derived from the company research\n   - \"Company stage?\" — Startups, Mid-market, Enterprise, All\n   - \"How many companies \u002F depth?\" — Quick (~100), Deep (~50), Deeper (~25)\n   - This is the ONLY user interaction. After this, execute silently until results are ready.\n\n## Step 2: Depth Mode Selection\n\n| Mode | Research per company | Best for |\n|------|---------------------|----------|\n| `quick` | Homepage + 1-2 searches | ~100 companies, broad scan |\n| `deep` | 2-3 sub-questions, 5-8 tool calls | ~50 companies, solid research |\n| `deeper` | 4-5 sub-questions, 10-15 tool calls | ~25 companies, full intelligence |\n\n## Step 3: Discovery\n\n**Formula**: `ceil(requested_companies \u002F 35)` search queries needed. Over-discover by ~2-3x because filtering typically drops 50-70%.\n\nGenerate search queries with these patterns:\n- Industry + company stage + geography (\"fintech startups series A Bay Area\")\n- Technology stack + use case (\"companies using Selenium for web scraping\")\n- Competitor adjacency (\"alternatives to {known company in ICP}\")\n- Buyer persona + pain point (\"engineering teams struggling with browser automation\")\n\n**Process**:\n1. Launch ALL discovery subagents at once (up to ~6 per message). Each runs its queries in a SINGLE Bash call:\n   ```bash\n   browse cloud search \"{query}\" --num-results 25 --output \u002Ftmp\u002Fcompany_discovery_batch_{N}.json\n   ```\n2. After all waves complete, deduplicate: `node {SKILL_DIR}\u002Fscripts\u002Flist_urls.mjs \u002Ftmp`\n3. **Filter the URL list** — remove:\n   - Blog posts, news articles (globenewswire.com, techcrunch.com, etc.)\n   - Directories\u002Faggregators (tracxn.com, crunchbase.com, g2.com)\n   - The user's own competitors and existing customers (from profile)\n   Keep only company homepages.\n\nSee `references\u002Fworkflow.md` for subagent prompt templates and wave management.\n\n## Step 4: Deep Research & Scoring\n\nLaunch subagents to research companies in parallel. See `references\u002Fworkflow.md` for the enrichment subagent prompt template. See `references\u002Fresearch-patterns.md` for the full research methodology.\n\n**Process**:\n1. Split filtered URLs into groups per subagent (quick: ~10, deep: ~5, deeper: ~2-3)\n2. Launch ALL enrichment subagents at once (up to ~6 per message)\n3. Each subagent uses ONLY Bash — for each company:\n\n   **Phase A — Plan** (skip in quick mode):\n   Decompose into 2-5 sub-questions based on ICP and enrichment fields.\n\n   **Phase B — Research Loop**:\n   Search and fetch pages, extract findings. Respect step budget (quick: 2-3, deep: 5-8, deeper: 10-15).\n\n   **Phase C — Synthesize**:\n   Score ICP fit 1-10 with evidence. Fill enrichment fields from findings.\n\n4. Subagents write ALL markdown files in a SINGLE Bash call using chained heredocs to `{OUTPUT_DIR}\u002F`\n5. After ALL subagents complete, proceed to Step 5\n\n**Critical**: Include the confirmed ICP description verbatim in every subagent prompt. Pass the full literal `{OUTPUT_DIR}` path to every subagent.\n\n## Step 5: Report & CSV\n\n1. **Generate HTML report + CSV** (opens overview in browser automatically):\n   ```bash\n   node {SKILL_DIR}\u002Fscripts\u002Fcompile_report.mjs {OUTPUT_DIR} --open\n   ```\n   This generates:\n   - `{OUTPUT_DIR}\u002Findex.html` — overview page with scored table (opens in browser)\n   - `{OUTPUT_DIR}\u002Fcompanies\u002F*.html` — individual company pages (linked from overview)\n   - `{OUTPUT_DIR}\u002Fresults.csv` — scored spreadsheet for import into sheets\u002FCRM\n\n2. **Present a summary in chat** too:\n\n```\n## Company Research Complete\n\n- **Total companies researched**: {count}\n- **Depth mode**: {mode}\n- **Score distribution**:\n  - Strong fit (8-10): {count}\n  - Partial fit (5-7): {count}\n  - Weak fit (1-4): {count}\n- **Report opened in browser**: ~\u002FDesktop\u002F{company_slug}_research_{date}\u002Findex.html\n```\n\n3. Show the **top companies** sorted by ICP score in a table:\n\n```\n| Company | Score | Product | Industry | Fit Reasoning |\n|---------|-------|---------|----------|---------------|\n| Acme | 9 | AI inventory management | E-commerce SaaS | Series A, uses Selenium, expanding to EU |\n```\n\n4. For the top 3-5 companies, show a brief research summary — key findings, why they're a good fit, and what specific angle to approach them with.\n\nOffer to dig deeper into specific companies, adjust scoring criteria, or re-run discovery with different queries.\n",{"data":38,"body":43},{"name":4,"description":6,"license":29,"compatibility":39,"allowed-tools":40,"metadata":41},"Requires browse CLI (`npm install -g browse`) and BROWSERBASE_API_KEY env var","Bash Agent",{"author":8,"version":42},"1.1.0",{"type":44,"children":45},"root",[46,54,60,88,158,351,385,419,428,570,579,690,699,720,727,732,785,789,795,800,869,905,910,945,951,956,1269,1275,1374,1380,1397,1402,1425,1434,1538,1551,1557,1576,1584,1648,1665,1671,1765,1775,1791,1800,1809,1814],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","Company Research",{"type":47,"tag":55,"props":56,"children":57},"p",{},[58],{"type":52,"value":59},"Discover and deeply research companies to sell to. Uses Browserbase Search API for discovery and a Plan→Research→Synthesize pattern for deep enrichment — outputting a scored research report and CSV.",{"type":47,"tag":55,"props":61,"children":62},{},[63,69,71,78,80,86],{"type":47,"tag":64,"props":65,"children":66},"strong",{},[67],{"type":52,"value":68},"Required",{"type":52,"value":70},": ",{"type":47,"tag":72,"props":73,"children":75},"code",{"className":74},[],[76],{"type":52,"value":77},"BROWSERBASE_API_KEY",{"type":52,"value":79}," env var and ",{"type":47,"tag":72,"props":81,"children":83},{"className":82},[],[84],{"type":52,"value":85},"browse",{"type":52,"value":87}," CLI installed.",{"type":47,"tag":55,"props":89,"children":90},{},[91,96,98,104,106,112,113,119,120,126,127,133,135,140,142,148,150,156],{"type":47,"tag":64,"props":92,"children":93},{},[94],{"type":52,"value":95},"First-run setup",{"type":52,"value":97},": On the first run you'll be prompted to approve ",{"type":47,"tag":72,"props":99,"children":101},{"className":100},[],[102],{"type":52,"value":103},"browse cloud fetch",{"type":52,"value":105},", ",{"type":47,"tag":72,"props":107,"children":109},{"className":108},[],[110],{"type":52,"value":111},"browse cloud search",{"type":52,"value":105},{"type":47,"tag":72,"props":114,"children":116},{"className":115},[],[117],{"type":52,"value":118},"cat",{"type":52,"value":105},{"type":47,"tag":72,"props":121,"children":123},{"className":122},[],[124],{"type":52,"value":125},"mkdir",{"type":52,"value":105},{"type":47,"tag":72,"props":128,"children":130},{"className":129},[],[131],{"type":52,"value":132},"sed",{"type":52,"value":134},", etc. Select ",{"type":47,"tag":64,"props":136,"children":137},{},[138],{"type":52,"value":139},"\"Yes, and don't ask again for: browse cloud fetch:*\"",{"type":52,"value":141}," (or equivalent) for each to auto-approve for the session. To permanently approve, add these to your ",{"type":47,"tag":72,"props":143,"children":145},{"className":144},[],[146],{"type":52,"value":147},"~\u002F.claude\u002Fsettings.json",{"type":52,"value":149}," under ",{"type":47,"tag":72,"props":151,"children":153},{"className":152},[],[154],{"type":52,"value":155},"permissions.allow",{"type":52,"value":157},":",{"type":47,"tag":159,"props":160,"children":165},"pre",{"className":161,"code":162,"language":163,"meta":164,"style":164},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","\"Bash(browse:*)\", \"Bash(bunx:*)\", \"Bash(bun:*)\", \"Bash(node:*)\",\n\"Bash(cat:*)\", \"Bash(mkdir:*)\", \"Bash(sed:*)\", \"Bash(head:*)\", \"Bash(tr:*)\", \"Bash(rm:*)\"\n","json","",[166],{"type":47,"tag":72,"props":167,"children":168},{"__ignoreMap":164},[169,248],{"type":47,"tag":170,"props":171,"children":174},"span",{"class":172,"line":173},"line",1,[175,181,187,191,196,200,205,209,213,217,222,226,230,234,239,243],{"type":47,"tag":170,"props":176,"children":178},{"style":177},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[179],{"type":52,"value":180},"\"",{"type":47,"tag":170,"props":182,"children":184},{"style":183},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[185],{"type":52,"value":186},"Bash(browse:*)",{"type":47,"tag":170,"props":188,"children":189},{"style":177},[190],{"type":52,"value":180},{"type":47,"tag":170,"props":192,"children":194},{"style":193},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[195],{"type":52,"value":105},{"type":47,"tag":170,"props":197,"children":198},{"style":177},[199],{"type":52,"value":180},{"type":47,"tag":170,"props":201,"children":202},{"style":183},[203],{"type":52,"value":204},"Bash(bunx:*)",{"type":47,"tag":170,"props":206,"children":207},{"style":177},[208],{"type":52,"value":180},{"type":47,"tag":170,"props":210,"children":211},{"style":193},[212],{"type":52,"value":105},{"type":47,"tag":170,"props":214,"children":215},{"style":177},[216],{"type":52,"value":180},{"type":47,"tag":170,"props":218,"children":219},{"style":183},[220],{"type":52,"value":221},"Bash(bun:*)",{"type":47,"tag":170,"props":223,"children":224},{"style":177},[225],{"type":52,"value":180},{"type":47,"tag":170,"props":227,"children":228},{"style":193},[229],{"type":52,"value":105},{"type":47,"tag":170,"props":231,"children":232},{"style":177},[233],{"type":52,"value":180},{"type":47,"tag":170,"props":235,"children":236},{"style":183},[237],{"type":52,"value":238},"Bash(node:*)",{"type":47,"tag":170,"props":240,"children":241},{"style":177},[242],{"type":52,"value":180},{"type":47,"tag":170,"props":244,"children":245},{"style":193},[246],{"type":52,"value":247},",\n",{"type":47,"tag":170,"props":249,"children":251},{"class":172,"line":250},2,[252,256,261,265,269,273,278,282,286,290,295,299,303,307,312,316,320,324,329,333,337,341,346],{"type":47,"tag":170,"props":253,"children":254},{"style":177},[255],{"type":52,"value":180},{"type":47,"tag":170,"props":257,"children":258},{"style":183},[259],{"type":52,"value":260},"Bash(cat:*)",{"type":47,"tag":170,"props":262,"children":263},{"style":177},[264],{"type":52,"value":180},{"type":47,"tag":170,"props":266,"children":267},{"style":193},[268],{"type":52,"value":105},{"type":47,"tag":170,"props":270,"children":271},{"style":177},[272],{"type":52,"value":180},{"type":47,"tag":170,"props":274,"children":275},{"style":183},[276],{"type":52,"value":277},"Bash(mkdir:*)",{"type":47,"tag":170,"props":279,"children":280},{"style":177},[281],{"type":52,"value":180},{"type":47,"tag":170,"props":283,"children":284},{"style":193},[285],{"type":52,"value":105},{"type":47,"tag":170,"props":287,"children":288},{"style":177},[289],{"type":52,"value":180},{"type":47,"tag":170,"props":291,"children":292},{"style":183},[293],{"type":52,"value":294},"Bash(sed:*)",{"type":47,"tag":170,"props":296,"children":297},{"style":177},[298],{"type":52,"value":180},{"type":47,"tag":170,"props":300,"children":301},{"style":193},[302],{"type":52,"value":105},{"type":47,"tag":170,"props":304,"children":305},{"style":177},[306],{"type":52,"value":180},{"type":47,"tag":170,"props":308,"children":309},{"style":183},[310],{"type":52,"value":311},"Bash(head:*)",{"type":47,"tag":170,"props":313,"children":314},{"style":177},[315],{"type":52,"value":180},{"type":47,"tag":170,"props":317,"children":318},{"style":193},[319],{"type":52,"value":105},{"type":47,"tag":170,"props":321,"children":322},{"style":177},[323],{"type":52,"value":180},{"type":47,"tag":170,"props":325,"children":326},{"style":183},[327],{"type":52,"value":328},"Bash(tr:*)",{"type":47,"tag":170,"props":330,"children":331},{"style":177},[332],{"type":52,"value":180},{"type":47,"tag":170,"props":334,"children":335},{"style":193},[336],{"type":52,"value":105},{"type":47,"tag":170,"props":338,"children":339},{"style":177},[340],{"type":52,"value":180},{"type":47,"tag":170,"props":342,"children":343},{"style":183},[344],{"type":52,"value":345},"Bash(rm:*)",{"type":47,"tag":170,"props":347,"children":348},{"style":177},[349],{"type":52,"value":350},"\"\n",{"type":47,"tag":55,"props":352,"children":353},{},[354,359,361,367,369,375,377,383],{"type":47,"tag":64,"props":355,"children":356},{},[357],{"type":52,"value":358},"Path rules",{"type":52,"value":360},": Always use the full literal path in all Bash commands — NOT ",{"type":47,"tag":72,"props":362,"children":364},{"className":363},[],[365],{"type":52,"value":366},"~",{"type":52,"value":368}," or ",{"type":47,"tag":72,"props":370,"children":372},{"className":371},[],[373],{"type":52,"value":374},"$HOME",{"type":52,"value":376}," (both trigger \"shell expansion syntax\" approval prompts). Resolve the home directory once and use it everywhere. When constructing subagent prompts, replace ",{"type":47,"tag":72,"props":378,"children":380},{"className":379},[],[381],{"type":52,"value":382},"{SKILL_DIR}",{"type":52,"value":384}," with the full literal path.",{"type":47,"tag":55,"props":386,"children":387},{},[388,393,395,401,403,409,411,417],{"type":47,"tag":64,"props":389,"children":390},{},[391],{"type":52,"value":392},"Output directory",{"type":52,"value":394},": All research output goes to ",{"type":47,"tag":72,"props":396,"children":398},{"className":397},[],[399],{"type":52,"value":400},"~\u002FDesktop\u002F{company_slug}_research_{YYYY-MM-DD}\u002F",{"type":52,"value":402},". This directory contains one ",{"type":47,"tag":72,"props":404,"children":406},{"className":405},[],[407],{"type":52,"value":408},".md",{"type":52,"value":410}," file per researched company plus a final ",{"type":47,"tag":72,"props":412,"children":414},{"className":413},[],[415],{"type":52,"value":416},".csv",{"type":52,"value":418},". The user gets both the scored spreadsheet and the full research files on their Desktop.",{"type":47,"tag":55,"props":420,"children":421},{},[422,427],{"type":47,"tag":64,"props":423,"children":424},{},[425],{"type":52,"value":426},"CRITICAL — Tool restrictions (applies to main agent AND all subagents)",{"type":52,"value":157},{"type":47,"tag":429,"props":430,"children":431},"ul",{},[432,445,482,518,531,544,552],{"type":47,"tag":433,"props":434,"children":435},"li",{},[436,438,443],{"type":52,"value":437},"All web searches: use ",{"type":47,"tag":72,"props":439,"children":441},{"className":440},[],[442],{"type":52,"value":111},{"type":52,"value":444},". NEVER use WebSearch.",{"type":47,"tag":433,"props":446,"children":447},{},[448,450,456,458,464,466,472,474,480],{"type":52,"value":449},"All page content extraction: use ",{"type":47,"tag":72,"props":451,"children":453},{"className":452},[],[454],{"type":52,"value":455},"node {SKILL_DIR}\u002Fscripts\u002Fextract_page.mjs \"\u003Curl>\"",{"type":52,"value":457},". This script fetches via ",{"type":47,"tag":72,"props":459,"children":461},{"className":460},[],[462],{"type":52,"value":463},"browse cloud fetch --output",{"type":52,"value":465},", parses title + meta tags + visible body text, and automatically falls back to ",{"type":47,"tag":72,"props":467,"children":469},{"className":468},[],[470],{"type":52,"value":471},"browse get markdown",{"type":52,"value":473}," when fetch fails or returns thin JS-rendered content. NEVER hand-roll a ",{"type":47,"tag":72,"props":475,"children":477},{"className":476},[],[478],{"type":52,"value":479},"browse cloud fetch | sed",{"type":52,"value":481}," pipeline — it strips meta tags and doesn't parse the stdout JSON envelope. NEVER use WebFetch.",{"type":47,"tag":433,"props":483,"children":484},{},[485,487,492,494,500,502,508,510,516],{"type":52,"value":486},"All research output: subagents write ",{"type":47,"tag":64,"props":488,"children":489},{},[490],{"type":52,"value":491},"one markdown file per company",{"type":52,"value":493}," to ",{"type":47,"tag":72,"props":495,"children":497},{"className":496},[],[498],{"type":52,"value":499},"{OUTPUT_DIR}\u002F{company-slug}.md",{"type":52,"value":501}," using bash heredoc. NEVER use the Write tool or ",{"type":47,"tag":72,"props":503,"children":505},{"className":504},[],[506],{"type":52,"value":507},"python3 -c",{"type":52,"value":509},". See ",{"type":47,"tag":72,"props":511,"children":513},{"className":512},[],[514],{"type":52,"value":515},"references\u002Fexample-research.md",{"type":52,"value":517}," for the file format.",{"type":47,"tag":433,"props":519,"children":520},{},[521,523,529],{"type":52,"value":522},"Report + CSV compilation: use ",{"type":47,"tag":72,"props":524,"children":526},{"className":525},[],[527],{"type":52,"value":528},"node {SKILL_DIR}\u002Fscripts\u002Fcompile_report.mjs {OUTPUT_DIR} --open",{"type":52,"value":530}," — generates HTML report and CSV in one step, opens overview in browser.",{"type":47,"tag":433,"props":532,"children":533},{},[534,536,542],{"type":52,"value":535},"URL deduplication: use ",{"type":47,"tag":72,"props":537,"children":539},{"className":538},[],[540],{"type":52,"value":541},"node {SKILL_DIR}\u002Fscripts\u002Flist_urls.mjs \u002Ftmp",{"type":52,"value":543}," after discovery.",{"type":47,"tag":433,"props":545,"children":546},{},[547],{"type":47,"tag":64,"props":548,"children":549},{},[550],{"type":52,"value":551},"Subagents must use ONLY the Bash tool. No other tools allowed.",{"type":47,"tag":433,"props":553,"children":554},{},[555,560,562,568],{"type":47,"tag":64,"props":556,"children":557},{},[558],{"type":52,"value":559},"Main agent NEVER reads raw discovery JSON batch files.",{"type":52,"value":561}," Use ",{"type":47,"tag":72,"props":563,"children":565},{"className":564},[],[566],{"type":52,"value":567},"list_urls.mjs",{"type":52,"value":569}," for dedup.",{"type":47,"tag":55,"props":571,"children":572},{},[573,578],{"type":47,"tag":64,"props":574,"children":575},{},[576],{"type":52,"value":577},"CRITICAL — Anti-hallucination rules (applies to main agent AND all subagents)",{"type":52,"value":157},{"type":47,"tag":429,"props":580,"children":581},{},[582,610,623,649],{"type":47,"tag":433,"props":583,"children":584},{},[585,587,593,594,600,602,608],{"type":52,"value":586},"NEVER infer ",{"type":47,"tag":72,"props":588,"children":590},{"className":589},[],[591],{"type":52,"value":592},"product_description",{"type":52,"value":105},{"type":47,"tag":72,"props":595,"children":597},{"className":596},[],[598],{"type":52,"value":599},"industry",{"type":52,"value":601},", or ",{"type":47,"tag":72,"props":603,"children":605},{"className":604},[],[606],{"type":52,"value":607},"target_audience",{"type":52,"value":609}," from a site's fonts, framework (Framer\u002FNext.js\u002FReact), design system, or typography. These are cosmetic and say nothing about what the company sells.",{"type":47,"tag":433,"props":611,"children":612},{},[613,615,621],{"type":52,"value":614},"NEVER let the user's own ICP leak into a target's description. If you don't know what the target does, write ",{"type":47,"tag":72,"props":616,"children":618},{"className":617},[],[619],{"type":52,"value":620},"Unknown",{"type":52,"value":622}," — do not pattern-match them onto the ICP.",{"type":47,"tag":433,"props":624,"children":625},{},[626,631,633,639,641,647],{"type":47,"tag":72,"props":627,"children":629},{"className":628},[],[630],{"type":52,"value":592},{"type":52,"value":632}," MUST quote or paraphrase a specific phrase from ",{"type":47,"tag":72,"props":634,"children":636},{"className":635},[],[637],{"type":52,"value":638},"extract_page.mjs",{"type":52,"value":640}," output (TITLE, META_DESCRIPTION, OG_DESCRIPTION, HEADINGS, or BODY). If none of those fields yield a recognizable product statement, write ",{"type":47,"tag":72,"props":642,"children":644},{"className":643},[],[645],{"type":52,"value":646},"Unknown — homepage content not accessible",{"type":52,"value":648},".",{"type":47,"tag":433,"props":650,"children":651},{},[652,654,659,661,666,668,674,676,682,683,689],{"type":52,"value":653},"If ",{"type":47,"tag":72,"props":655,"children":657},{"className":656},[],[658],{"type":52,"value":592},{"type":52,"value":660}," is ",{"type":47,"tag":72,"props":662,"children":664},{"className":663},[],[665],{"type":52,"value":620},{"type":52,"value":667},", cap ",{"type":47,"tag":72,"props":669,"children":671},{"className":670},[],[672],{"type":52,"value":673},"icp_fit_score",{"type":52,"value":675}," at 3 and set ",{"type":47,"tag":72,"props":677,"children":679},{"className":678},[],[680],{"type":52,"value":681},"icp_fit_reasoning",{"type":52,"value":493},{"type":47,"tag":72,"props":684,"children":686},{"className":685},[],[687],{"type":52,"value":688},"Insufficient evidence — homepage returned no readable content",{"type":52,"value":648},{"type":47,"tag":55,"props":691,"children":692},{},[693,698],{"type":47,"tag":64,"props":694,"children":695},{},[696],{"type":52,"value":697},"CRITICAL — Minimize permission prompts",{"type":52,"value":157},{"type":47,"tag":429,"props":700,"children":701},{},[702,707],{"type":47,"tag":433,"props":703,"children":704},{},[705],{"type":52,"value":706},"Subagents MUST batch ALL file writes into a SINGLE Bash call using chained heredocs. One Bash call = one permission prompt.",{"type":47,"tag":433,"props":708,"children":709},{},[710,712,718],{"type":52,"value":711},"Batch ALL searches and ALL fetches into single Bash calls using ",{"type":47,"tag":72,"props":713,"children":715},{"className":714},[],[716],{"type":52,"value":717},"&&",{"type":52,"value":719}," chaining.",{"type":47,"tag":721,"props":722,"children":724},"h2",{"id":723},"pipeline-overview",[725],{"type":52,"value":726},"Pipeline Overview",{"type":47,"tag":55,"props":728,"children":729},{},[730],{"type":52,"value":731},"Follow these 5 steps in order. Do not skip steps or reorder.",{"type":47,"tag":733,"props":734,"children":735},"ol",{},[736,745,755,765,775],{"type":47,"tag":433,"props":737,"children":738},{},[739,743],{"type":47,"tag":64,"props":740,"children":741},{},[742],{"type":52,"value":53},{"type":52,"value":744}," — Deeply understand the user's company, product, and who they sell to",{"type":47,"tag":433,"props":746,"children":747},{},[748,753],{"type":47,"tag":64,"props":749,"children":750},{},[751],{"type":52,"value":752},"Depth Mode Selection",{"type":52,"value":754}," — Choose research depth based on how many targets they want",{"type":47,"tag":433,"props":756,"children":757},{},[758,763],{"type":47,"tag":64,"props":759,"children":760},{},[761],{"type":52,"value":762},"Discovery",{"type":52,"value":764}," — Find target companies using diverse search queries",{"type":47,"tag":433,"props":766,"children":767},{},[768,773],{"type":47,"tag":64,"props":769,"children":770},{},[771],{"type":52,"value":772},"Deep Research & Scoring",{"type":52,"value":774}," — Research each company, score ICP fit",{"type":47,"tag":433,"props":776,"children":777},{},[778,783],{"type":47,"tag":64,"props":779,"children":780},{},[781],{"type":52,"value":782},"Report & CSV",{"type":52,"value":784}," — Present findings, compile scored CSV",{"type":47,"tag":786,"props":787,"children":788},"hr",{},[],{"type":47,"tag":721,"props":790,"children":792},{"id":791},"step-0-setup-output-directory",[793],{"type":52,"value":794},"Step 0: Setup Output Directory",{"type":47,"tag":55,"props":796,"children":797},{},[798],{"type":52,"value":799},"Before starting, create the output directory on the user's Desktop:",{"type":47,"tag":159,"props":801,"children":805},{"className":802,"code":803,"language":804,"meta":164,"style":164},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","OUTPUT_DIR=~\u002FDesktop\u002F{company_slug}_research_{YYYY-MM-DD}\nmkdir -p \"$OUTPUT_DIR\"\n","bash",[806],{"type":47,"tag":72,"props":807,"children":808},{"__ignoreMap":164},[809,843],{"type":47,"tag":170,"props":810,"children":811},{"class":172,"line":173},[812,817,822,827,832,838],{"type":47,"tag":170,"props":813,"children":814},{"style":193},[815],{"type":52,"value":816},"OUTPUT_DIR",{"type":47,"tag":170,"props":818,"children":819},{"style":177},[820],{"type":52,"value":821},"=",{"type":47,"tag":170,"props":823,"children":824},{"style":183},[825],{"type":52,"value":826},"~\u002FDesktop\u002F",{"type":47,"tag":170,"props":828,"children":829},{"style":193},[830],{"type":52,"value":831},"{",{"type":47,"tag":170,"props":833,"children":835},{"style":834},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[836],{"type":52,"value":837},"company_slug}_research_",{"type":47,"tag":170,"props":839,"children":840},{"style":183},[841],{"type":52,"value":842},"{YYYY-MM-DD}\n",{"type":47,"tag":170,"props":844,"children":845},{"class":172,"line":250},[846,850,855,860,865],{"type":47,"tag":170,"props":847,"children":848},{"style":834},[849],{"type":52,"value":125},{"type":47,"tag":170,"props":851,"children":852},{"style":183},[853],{"type":52,"value":854}," -p",{"type":47,"tag":170,"props":856,"children":857},{"style":177},[858],{"type":52,"value":859}," \"",{"type":47,"tag":170,"props":861,"children":862},{"style":193},[863],{"type":52,"value":864},"$OUTPUT_DIR",{"type":47,"tag":170,"props":866,"children":867},{"style":177},[868],{"type":52,"value":350},{"type":47,"tag":55,"props":870,"children":871},{},[872,874,880,882,888,890,896,898,903],{"type":52,"value":873},"Replace ",{"type":47,"tag":72,"props":875,"children":877},{"className":876},[],[878],{"type":52,"value":879},"{company_slug}",{"type":52,"value":881}," with the user's company name (lowercase, hyphenated) and ",{"type":47,"tag":72,"props":883,"children":885},{"className":884},[],[886],{"type":52,"value":887},"{YYYY-MM-DD}",{"type":52,"value":889}," with today's date. Pass ",{"type":47,"tag":72,"props":891,"children":893},{"className":892},[],[894],{"type":52,"value":895},"{OUTPUT_DIR}",{"type":52,"value":897}," (as a full literal path, not with ",{"type":47,"tag":72,"props":899,"children":901},{"className":900},[],[902],{"type":52,"value":366},{"type":52,"value":904},") to all subagent prompts so they write research files there.",{"type":47,"tag":55,"props":906,"children":907},{},[908],{"type":52,"value":909},"Also clean up discovery batch files from prior runs:",{"type":47,"tag":159,"props":911,"children":913},{"className":802,"code":912,"language":804,"meta":164,"style":164},"rm -f \u002Ftmp\u002Fcompany_discovery_batch_*.json\n",[914],{"type":47,"tag":72,"props":915,"children":916},{"__ignoreMap":164},[917],{"type":47,"tag":170,"props":918,"children":919},{"class":172,"line":173},[920,925,930,935,940],{"type":47,"tag":170,"props":921,"children":922},{"style":834},[923],{"type":52,"value":924},"rm",{"type":47,"tag":170,"props":926,"children":927},{"style":183},[928],{"type":52,"value":929}," -f",{"type":47,"tag":170,"props":931,"children":932},{"style":183},[933],{"type":52,"value":934}," \u002Ftmp\u002Fcompany_discovery_batch_",{"type":47,"tag":170,"props":936,"children":937},{"style":193},[938],{"type":52,"value":939},"*",{"type":47,"tag":170,"props":941,"children":942},{"style":183},[943],{"type":52,"value":944},".json\n",{"type":47,"tag":721,"props":946,"children":948},{"id":947},"step-1-deep-company-research",[949],{"type":52,"value":950},"Step 1: Deep Company Research",{"type":47,"tag":55,"props":952,"children":953},{},[954],{"type":52,"value":955},"This is the most important step. The quality of everything downstream depends on deeply understanding the user's company.",{"type":47,"tag":733,"props":957,"children":958},{},[959,964,1007,1208,1213,1228],{"type":47,"tag":433,"props":960,"children":961},{},[962],{"type":52,"value":963},"Ask the user for their company name or URL",{"type":47,"tag":433,"props":965,"children":966},{},[967,972,973],{"type":47,"tag":64,"props":968,"children":969},{},[970],{"type":52,"value":971},"Check for an existing profile",{"type":52,"value":157},{"type":47,"tag":429,"props":974,"children":975},{},[976,997,1002],{"type":47,"tag":433,"props":977,"children":978},{},[979,981,987,989,995],{"type":52,"value":980},"List files in ",{"type":47,"tag":72,"props":982,"children":984},{"className":983},[],[985],{"type":52,"value":986},"{SKILL_DIR}\u002Fprofiles\u002F",{"type":52,"value":988}," (ignore ",{"type":47,"tag":72,"props":990,"children":992},{"className":991},[],[993],{"type":52,"value":994},"example.json",{"type":52,"value":996},")",{"type":47,"tag":433,"props":998,"children":999},{},[1000],{"type":52,"value":1001},"If a matching profile exists → load it, present to user: \"I have your profile from {researched_at}. Still accurate?\" If yes → skip to Step 2.",{"type":47,"tag":433,"props":1003,"children":1004},{},[1005],{"type":52,"value":1006},"If no profile exists → proceed with deep research below.",{"type":47,"tag":433,"props":1008,"children":1009},{},[1010,1015,1017,1023,1025,1029,1034,1198,1201,1206],{"type":47,"tag":64,"props":1011,"children":1012},{},[1013],{"type":52,"value":1014},"Run a full deep research on the user's company",{"type":52,"value":1016}," using the Plan→Research→Synthesize pattern.\nSee ",{"type":47,"tag":72,"props":1018,"children":1020},{"className":1019},[],[1021],{"type":52,"value":1022},"references\u002Fresearch-patterns.md",{"type":52,"value":1024}," for sub-question templates and research methodology.",{"type":47,"tag":1026,"props":1027,"children":1028},"br",{},[],{"type":47,"tag":64,"props":1030,"children":1031},{},[1032],{"type":52,"value":1033},"Key research steps:",{"type":47,"tag":429,"props":1035,"children":1036},{},[1037,1048,1059,1188,1193],{"type":47,"tag":433,"props":1038,"children":1039},{},[1040,1042],{"type":52,"value":1041},"Search: ",{"type":47,"tag":72,"props":1043,"children":1045},{"className":1044},[],[1046],{"type":52,"value":1047},"browse cloud search \"{company name}\" --num-results 10",{"type":47,"tag":433,"props":1049,"children":1050},{},[1051,1053],{"type":52,"value":1052},"Fetch homepage: ",{"type":47,"tag":72,"props":1054,"children":1056},{"className":1055},[],[1057],{"type":52,"value":1058},"node {SKILL_DIR}\u002Fscripts\u002Fextract_page.mjs \"{company website}\"",{"type":47,"tag":433,"props":1060,"children":1061},{},[1062,1067,1069,1075,1076,1082,1084],{"type":47,"tag":64,"props":1063,"children":1064},{},[1065],{"type":52,"value":1066},"Discover site pages via sitemap",{"type":52,"value":1068}," (do NOT hardcode paths like ",{"type":47,"tag":72,"props":1070,"children":1072},{"className":1071},[],[1073],{"type":52,"value":1074},"\u002Fabout",{"type":52,"value":368},{"type":47,"tag":72,"props":1077,"children":1079},{"className":1078},[],[1080],{"type":52,"value":1081},"\u002Fcustomers",{"type":52,"value":1083},"):\n",{"type":47,"tag":733,"props":1085,"children":1086},{},[1087,1105,1157,1170],{"type":47,"tag":433,"props":1088,"children":1089},{},[1090,1096,1098,1103],{"type":47,"tag":72,"props":1091,"children":1093},{"className":1092},[],[1094],{"type":52,"value":1095},"browse cloud fetch --allow-redirects \"{company website}\u002Fsitemap.xml\"",{"type":52,"value":1097}," — sitemap is small, raw ",{"type":47,"tag":72,"props":1099,"children":1101},{"className":1100},[],[1102],{"type":52,"value":103},{"type":52,"value":1104}," is fine",{"type":47,"tag":433,"props":1106,"children":1107},{},[1108,1110,1116,1117,1123,1124,1130,1131,1137,1138,1144,1145,1150,1151],{"type":52,"value":1109},"Scan for URLs with keywords: ",{"type":47,"tag":72,"props":1111,"children":1113},{"className":1112},[],[1114],{"type":52,"value":1115},"customer",{"type":52,"value":105},{"type":47,"tag":72,"props":1118,"children":1120},{"className":1119},[],[1121],{"type":52,"value":1122},"case-stud",{"type":52,"value":105},{"type":47,"tag":72,"props":1125,"children":1127},{"className":1126},[],[1128],{"type":52,"value":1129},"pricing",{"type":52,"value":105},{"type":47,"tag":72,"props":1132,"children":1134},{"className":1133},[],[1135],{"type":52,"value":1136},"about",{"type":52,"value":105},{"type":47,"tag":72,"props":1139,"children":1141},{"className":1140},[],[1142],{"type":52,"value":1143},"use-case",{"type":52,"value":105},{"type":47,"tag":72,"props":1146,"children":1148},{"className":1147},[],[1149],{"type":52,"value":599},{"type":52,"value":105},{"type":47,"tag":72,"props":1152,"children":1154},{"className":1153},[],[1155],{"type":52,"value":1156},"solution",{"type":47,"tag":433,"props":1158,"children":1159},{},[1160,1162,1168],{"type":52,"value":1161},"Optionally also fetch ",{"type":47,"tag":72,"props":1163,"children":1165},{"className":1164},[],[1166],{"type":52,"value":1167},"\u002Fllms.txt",{"type":52,"value":1169}," for page descriptions",{"type":47,"tag":433,"props":1171,"children":1172},{},[1173,1175,1180,1182,1187],{"type":52,"value":1174},"Pick 3-5 most relevant URLs and extract with ",{"type":47,"tag":72,"props":1176,"children":1178},{"className":1177},[],[1179],{"type":52,"value":638},{"type":52,"value":1181}," (NOT raw ",{"type":47,"tag":72,"props":1183,"children":1185},{"className":1184},[],[1186],{"type":52,"value":103},{"type":52,"value":996},{"type":47,"tag":433,"props":1189,"children":1190},{},[1191],{"type":52,"value":1192},"Search for external context and competitors",{"type":47,"tag":433,"props":1194,"children":1195},{},[1196],{"type":52,"value":1197},"Accumulate findings with confidence levels",{"type":47,"tag":1026,"props":1199,"children":1200},{},[],{"type":47,"tag":64,"props":1202,"children":1203},{},[1204],{"type":52,"value":1205},"Synthesize into a profile",{"type":52,"value":1207},":\nCompany, Product, Existing Customers, Competitors, Use Cases.\nDo NOT include ICP or sub-verticals — those are per-run decisions.",{"type":47,"tag":433,"props":1209,"children":1210},{},[1211],{"type":52,"value":1212},"Present the profile to the user for confirmation. Do not proceed until confirmed.",{"type":47,"tag":433,"props":1214,"children":1215},{},[1216,1221,1222],{"type":47,"tag":64,"props":1217,"children":1218},{},[1219],{"type":52,"value":1220},"Save the confirmed profile",{"type":52,"value":493},{"type":47,"tag":72,"props":1223,"children":1225},{"className":1224},[],[1226],{"type":52,"value":1227},"{SKILL_DIR}\u002Fprofiles\u002F{company-slug}.json",{"type":47,"tag":433,"props":1229,"children":1230},{},[1231,1236,1238,1244,1246],{"type":47,"tag":64,"props":1232,"children":1233},{},[1234],{"type":52,"value":1235},"Ask clarifying questions",{"type":52,"value":1237}," using ",{"type":47,"tag":72,"props":1239,"children":1241},{"className":1240},[],[1242],{"type":52,"value":1243},"AskUserQuestion",{"type":52,"value":1245}," with checkboxes:",{"type":47,"tag":429,"props":1247,"children":1248},{},[1249,1254,1259,1264],{"type":47,"tag":433,"props":1250,"children":1251},{},[1252],{"type":52,"value":1253},"\"Which segments are you targeting?\" with options derived from the company research",{"type":47,"tag":433,"props":1255,"children":1256},{},[1257],{"type":52,"value":1258},"\"Company stage?\" — Startups, Mid-market, Enterprise, All",{"type":47,"tag":433,"props":1260,"children":1261},{},[1262],{"type":52,"value":1263},"\"How many companies \u002F depth?\" — Quick (~100), Deep (~50), Deeper (~25)",{"type":47,"tag":433,"props":1265,"children":1266},{},[1267],{"type":52,"value":1268},"This is the ONLY user interaction. After this, execute silently until results are ready.",{"type":47,"tag":721,"props":1270,"children":1272},{"id":1271},"step-2-depth-mode-selection",[1273],{"type":52,"value":1274},"Step 2: Depth Mode Selection",{"type":47,"tag":1276,"props":1277,"children":1278},"table",{},[1279,1303],{"type":47,"tag":1280,"props":1281,"children":1282},"thead",{},[1283],{"type":47,"tag":1284,"props":1285,"children":1286},"tr",{},[1287,1293,1298],{"type":47,"tag":1288,"props":1289,"children":1290},"th",{},[1291],{"type":52,"value":1292},"Mode",{"type":47,"tag":1288,"props":1294,"children":1295},{},[1296],{"type":52,"value":1297},"Research per company",{"type":47,"tag":1288,"props":1299,"children":1300},{},[1301],{"type":52,"value":1302},"Best for",{"type":47,"tag":1304,"props":1305,"children":1306},"tbody",{},[1307,1330,1352],{"type":47,"tag":1284,"props":1308,"children":1309},{},[1310,1320,1325],{"type":47,"tag":1311,"props":1312,"children":1313},"td",{},[1314],{"type":47,"tag":72,"props":1315,"children":1317},{"className":1316},[],[1318],{"type":52,"value":1319},"quick",{"type":47,"tag":1311,"props":1321,"children":1322},{},[1323],{"type":52,"value":1324},"Homepage + 1-2 searches",{"type":47,"tag":1311,"props":1326,"children":1327},{},[1328],{"type":52,"value":1329},"~100 companies, broad scan",{"type":47,"tag":1284,"props":1331,"children":1332},{},[1333,1342,1347],{"type":47,"tag":1311,"props":1334,"children":1335},{},[1336],{"type":47,"tag":72,"props":1337,"children":1339},{"className":1338},[],[1340],{"type":52,"value":1341},"deep",{"type":47,"tag":1311,"props":1343,"children":1344},{},[1345],{"type":52,"value":1346},"2-3 sub-questions, 5-8 tool calls",{"type":47,"tag":1311,"props":1348,"children":1349},{},[1350],{"type":52,"value":1351},"~50 companies, solid research",{"type":47,"tag":1284,"props":1353,"children":1354},{},[1355,1364,1369],{"type":47,"tag":1311,"props":1356,"children":1357},{},[1358],{"type":47,"tag":72,"props":1359,"children":1361},{"className":1360},[],[1362],{"type":52,"value":1363},"deeper",{"type":47,"tag":1311,"props":1365,"children":1366},{},[1367],{"type":52,"value":1368},"4-5 sub-questions, 10-15 tool calls",{"type":47,"tag":1311,"props":1370,"children":1371},{},[1372],{"type":52,"value":1373},"~25 companies, full intelligence",{"type":47,"tag":721,"props":1375,"children":1377},{"id":1376},"step-3-discovery",[1378],{"type":52,"value":1379},"Step 3: Discovery",{"type":47,"tag":55,"props":1381,"children":1382},{},[1383,1388,1389,1395],{"type":47,"tag":64,"props":1384,"children":1385},{},[1386],{"type":52,"value":1387},"Formula",{"type":52,"value":70},{"type":47,"tag":72,"props":1390,"children":1392},{"className":1391},[],[1393],{"type":52,"value":1394},"ceil(requested_companies \u002F 35)",{"type":52,"value":1396}," search queries needed. Over-discover by ~2-3x because filtering typically drops 50-70%.",{"type":47,"tag":55,"props":1398,"children":1399},{},[1400],{"type":52,"value":1401},"Generate search queries with these patterns:",{"type":47,"tag":429,"props":1403,"children":1404},{},[1405,1410,1415,1420],{"type":47,"tag":433,"props":1406,"children":1407},{},[1408],{"type":52,"value":1409},"Industry + company stage + geography (\"fintech startups series A Bay Area\")",{"type":47,"tag":433,"props":1411,"children":1412},{},[1413],{"type":52,"value":1414},"Technology stack + use case (\"companies using Selenium for web scraping\")",{"type":47,"tag":433,"props":1416,"children":1417},{},[1418],{"type":52,"value":1419},"Competitor adjacency (\"alternatives to {known company in ICP}\")",{"type":47,"tag":433,"props":1421,"children":1422},{},[1423],{"type":52,"value":1424},"Buyer persona + pain point (\"engineering teams struggling with browser automation\")",{"type":47,"tag":55,"props":1426,"children":1427},{},[1428,1433],{"type":47,"tag":64,"props":1429,"children":1430},{},[1431],{"type":52,"value":1432},"Process",{"type":52,"value":157},{"type":47,"tag":733,"props":1435,"children":1436},{},[1437,1500,1510],{"type":47,"tag":433,"props":1438,"children":1439},{},[1440,1442],{"type":52,"value":1441},"Launch ALL discovery subagents at once (up to ~6 per message). Each runs its queries in a SINGLE Bash call:\n",{"type":47,"tag":159,"props":1443,"children":1445},{"className":802,"code":1444,"language":804,"meta":164,"style":164},"browse cloud search \"{query}\" --num-results 25 --output \u002Ftmp\u002Fcompany_discovery_batch_{N}.json\n",[1446],{"type":47,"tag":72,"props":1447,"children":1448},{"__ignoreMap":164},[1449],{"type":47,"tag":170,"props":1450,"children":1451},{"class":172,"line":173},[1452,1456,1461,1466,1470,1475,1479,1484,1490,1495],{"type":47,"tag":170,"props":1453,"children":1454},{"style":834},[1455],{"type":52,"value":85},{"type":47,"tag":170,"props":1457,"children":1458},{"style":183},[1459],{"type":52,"value":1460}," cloud",{"type":47,"tag":170,"props":1462,"children":1463},{"style":183},[1464],{"type":52,"value":1465}," search",{"type":47,"tag":170,"props":1467,"children":1468},{"style":177},[1469],{"type":52,"value":859},{"type":47,"tag":170,"props":1471,"children":1472},{"style":183},[1473],{"type":52,"value":1474},"{query}",{"type":47,"tag":170,"props":1476,"children":1477},{"style":177},[1478],{"type":52,"value":180},{"type":47,"tag":170,"props":1480,"children":1481},{"style":183},[1482],{"type":52,"value":1483}," --num-results",{"type":47,"tag":170,"props":1485,"children":1487},{"style":1486},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[1488],{"type":52,"value":1489}," 25",{"type":47,"tag":170,"props":1491,"children":1492},{"style":183},[1493],{"type":52,"value":1494}," --output",{"type":47,"tag":170,"props":1496,"children":1497},{"style":183},[1498],{"type":52,"value":1499}," \u002Ftmp\u002Fcompany_discovery_batch_{N}.json\n",{"type":47,"tag":433,"props":1501,"children":1502},{},[1503,1505],{"type":52,"value":1504},"After all waves complete, deduplicate: ",{"type":47,"tag":72,"props":1506,"children":1508},{"className":1507},[],[1509],{"type":52,"value":541},{"type":47,"tag":433,"props":1511,"children":1512},{},[1513,1518,1520],{"type":47,"tag":64,"props":1514,"children":1515},{},[1516],{"type":52,"value":1517},"Filter the URL list",{"type":52,"value":1519}," — remove:\n",{"type":47,"tag":429,"props":1521,"children":1522},{},[1523,1528,1533],{"type":47,"tag":433,"props":1524,"children":1525},{},[1526],{"type":52,"value":1527},"Blog posts, news articles (globenewswire.com, techcrunch.com, etc.)",{"type":47,"tag":433,"props":1529,"children":1530},{},[1531],{"type":52,"value":1532},"Directories\u002Faggregators (tracxn.com, crunchbase.com, g2.com)",{"type":47,"tag":433,"props":1534,"children":1535},{},[1536],{"type":52,"value":1537},"The user's own competitors and existing customers (from profile)\nKeep only company homepages.",{"type":47,"tag":55,"props":1539,"children":1540},{},[1541,1543,1549],{"type":52,"value":1542},"See ",{"type":47,"tag":72,"props":1544,"children":1546},{"className":1545},[],[1547],{"type":52,"value":1548},"references\u002Fworkflow.md",{"type":52,"value":1550}," for subagent prompt templates and wave management.",{"type":47,"tag":721,"props":1552,"children":1554},{"id":1553},"step-4-deep-research-scoring",[1555],{"type":52,"value":1556},"Step 4: Deep Research & Scoring",{"type":47,"tag":55,"props":1558,"children":1559},{},[1560,1562,1567,1569,1574],{"type":52,"value":1561},"Launch subagents to research companies in parallel. See ",{"type":47,"tag":72,"props":1563,"children":1565},{"className":1564},[],[1566],{"type":52,"value":1548},{"type":52,"value":1568}," for the enrichment subagent prompt template. See ",{"type":47,"tag":72,"props":1570,"children":1572},{"className":1571},[],[1573],{"type":52,"value":1022},{"type":52,"value":1575}," for the full research methodology.",{"type":47,"tag":55,"props":1577,"children":1578},{},[1579,1583],{"type":47,"tag":64,"props":1580,"children":1581},{},[1582],{"type":52,"value":1432},{"type":52,"value":157},{"type":47,"tag":733,"props":1585,"children":1586},{},[1587,1592,1597,1632,1643],{"type":47,"tag":433,"props":1588,"children":1589},{},[1590],{"type":52,"value":1591},"Split filtered URLs into groups per subagent (quick: ~10, deep: ~5, deeper: ~2-3)",{"type":47,"tag":433,"props":1593,"children":1594},{},[1595],{"type":52,"value":1596},"Launch ALL enrichment subagents at once (up to ~6 per message)",{"type":47,"tag":433,"props":1598,"children":1599},{},[1600,1602,1605,1610,1612,1615,1620,1622,1625,1630],{"type":52,"value":1601},"Each subagent uses ONLY Bash — for each company:",{"type":47,"tag":1026,"props":1603,"children":1604},{},[],{"type":47,"tag":64,"props":1606,"children":1607},{},[1608],{"type":52,"value":1609},"Phase A — Plan",{"type":52,"value":1611}," (skip in quick mode):\nDecompose into 2-5 sub-questions based on ICP and enrichment fields.",{"type":47,"tag":1026,"props":1613,"children":1614},{},[],{"type":47,"tag":64,"props":1616,"children":1617},{},[1618],{"type":52,"value":1619},"Phase B — Research Loop",{"type":52,"value":1621},":\nSearch and fetch pages, extract findings. Respect step budget (quick: 2-3, deep: 5-8, deeper: 10-15).",{"type":47,"tag":1026,"props":1623,"children":1624},{},[],{"type":47,"tag":64,"props":1626,"children":1627},{},[1628],{"type":52,"value":1629},"Phase C — Synthesize",{"type":52,"value":1631},":\nScore ICP fit 1-10 with evidence. Fill enrichment fields from findings.",{"type":47,"tag":433,"props":1633,"children":1634},{},[1635,1637],{"type":52,"value":1636},"Subagents write ALL markdown files in a SINGLE Bash call using chained heredocs to ",{"type":47,"tag":72,"props":1638,"children":1640},{"className":1639},[],[1641],{"type":52,"value":1642},"{OUTPUT_DIR}\u002F",{"type":47,"tag":433,"props":1644,"children":1645},{},[1646],{"type":52,"value":1647},"After ALL subagents complete, proceed to Step 5",{"type":47,"tag":55,"props":1649,"children":1650},{},[1651,1656,1658,1663],{"type":47,"tag":64,"props":1652,"children":1653},{},[1654],{"type":52,"value":1655},"Critical",{"type":52,"value":1657},": Include the confirmed ICP description verbatim in every subagent prompt. Pass the full literal ",{"type":47,"tag":72,"props":1659,"children":1661},{"className":1660},[],[1662],{"type":52,"value":895},{"type":52,"value":1664}," path to every subagent.",{"type":47,"tag":721,"props":1666,"children":1668},{"id":1667},"step-5-report-csv",[1669],{"type":52,"value":1670},"Step 5: Report & CSV",{"type":47,"tag":733,"props":1672,"children":1673},{},[1674,1755],{"type":47,"tag":433,"props":1675,"children":1676},{},[1677,1682,1684,1714,1717,1719],{"type":47,"tag":64,"props":1678,"children":1679},{},[1680],{"type":52,"value":1681},"Generate HTML report + CSV",{"type":52,"value":1683}," (opens overview in browser automatically):",{"type":47,"tag":159,"props":1685,"children":1687},{"className":802,"code":1686,"language":804,"meta":164,"style":164},"node {SKILL_DIR}\u002Fscripts\u002Fcompile_report.mjs {OUTPUT_DIR} --open\n",[1688],{"type":47,"tag":72,"props":1689,"children":1690},{"__ignoreMap":164},[1691],{"type":47,"tag":170,"props":1692,"children":1693},{"class":172,"line":173},[1694,1699,1704,1709],{"type":47,"tag":170,"props":1695,"children":1696},{"style":834},[1697],{"type":52,"value":1698},"node",{"type":47,"tag":170,"props":1700,"children":1701},{"style":183},[1702],{"type":52,"value":1703}," {SKILL_DIR}\u002Fscripts\u002Fcompile_report.mjs",{"type":47,"tag":170,"props":1705,"children":1706},{"style":183},[1707],{"type":52,"value":1708}," {OUTPUT_DIR}",{"type":47,"tag":170,"props":1710,"children":1711},{"style":183},[1712],{"type":52,"value":1713}," --open\n",{"type":47,"tag":1026,"props":1715,"children":1716},{},[],{"type":52,"value":1718},"This generates:",{"type":47,"tag":429,"props":1720,"children":1721},{},[1722,1733,1744],{"type":47,"tag":433,"props":1723,"children":1724},{},[1725,1731],{"type":47,"tag":72,"props":1726,"children":1728},{"className":1727},[],[1729],{"type":52,"value":1730},"{OUTPUT_DIR}\u002Findex.html",{"type":52,"value":1732}," — overview page with scored table (opens in browser)",{"type":47,"tag":433,"props":1734,"children":1735},{},[1736,1742],{"type":47,"tag":72,"props":1737,"children":1739},{"className":1738},[],[1740],{"type":52,"value":1741},"{OUTPUT_DIR}\u002Fcompanies\u002F*.html",{"type":52,"value":1743}," — individual company pages (linked from overview)",{"type":47,"tag":433,"props":1745,"children":1746},{},[1747,1753],{"type":47,"tag":72,"props":1748,"children":1750},{"className":1749},[],[1751],{"type":52,"value":1752},"{OUTPUT_DIR}\u002Fresults.csv",{"type":52,"value":1754}," — scored spreadsheet for import into sheets\u002FCRM",{"type":47,"tag":433,"props":1756,"children":1757},{},[1758,1763],{"type":47,"tag":64,"props":1759,"children":1760},{},[1761],{"type":52,"value":1762},"Present a summary in chat",{"type":52,"value":1764}," too:",{"type":47,"tag":159,"props":1766,"children":1770},{"className":1767,"code":1769,"language":52},[1768],"language-text","## Company Research Complete\n\n- **Total companies researched**: {count}\n- **Depth mode**: {mode}\n- **Score distribution**:\n  - Strong fit (8-10): {count}\n  - Partial fit (5-7): {count}\n  - Weak fit (1-4): {count}\n- **Report opened in browser**: ~\u002FDesktop\u002F{company_slug}_research_{date}\u002Findex.html\n",[1771],{"type":47,"tag":72,"props":1772,"children":1773},{"__ignoreMap":164},[1774],{"type":52,"value":1769},{"type":47,"tag":733,"props":1776,"children":1778},{"start":1777},3,[1779],{"type":47,"tag":433,"props":1780,"children":1781},{},[1782,1784,1789],{"type":52,"value":1783},"Show the ",{"type":47,"tag":64,"props":1785,"children":1786},{},[1787],{"type":52,"value":1788},"top companies",{"type":52,"value":1790}," sorted by ICP score in a table:",{"type":47,"tag":159,"props":1792,"children":1795},{"className":1793,"code":1794,"language":52},[1768],"| Company | Score | Product | Industry | Fit Reasoning |\n|---------|-------|---------|----------|---------------|\n| Acme | 9 | AI inventory management | E-commerce SaaS | Series A, uses Selenium, expanding to EU |\n",[1796],{"type":47,"tag":72,"props":1797,"children":1798},{"__ignoreMap":164},[1799],{"type":52,"value":1794},{"type":47,"tag":733,"props":1801,"children":1803},{"start":1802},4,[1804],{"type":47,"tag":433,"props":1805,"children":1806},{},[1807],{"type":52,"value":1808},"For the top 3-5 companies, show a brief research summary — key findings, why they're a good fit, and what specific angle to approach them with.",{"type":47,"tag":55,"props":1810,"children":1811},{},[1812],{"type":52,"value":1813},"Offer to dig deeper into specific companies, adjust scoring criteria, or re-run discovery with different queries.",{"type":47,"tag":1815,"props":1816,"children":1817},"style",{},[1818],{"type":52,"value":1819},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1821,"total":1931},[1822,1845,1860,1872,1890,1905,1923],{"slug":1823,"name":1823,"fn":1824,"description":1825,"org":1826,"tags":1827,"stars":26,"repoUrl":27,"updatedAt":1844},"agent-experience","audit developer experience with AI agents","Audit the developer experience of a product, SDK, docs site, or SKILL.md by dropping multiple Claude subagents at it with only a tiny task prompt and real tools (WebFetch, Bash, Write). Agents must discover the docs themselves, install deps, ask for credentials if needed, and attempt real execution. The skill captures each agent's trace — tool calls, retries, wall time, errors — and scores on Setup Friction, Speed, Efficiency, Error Recovery, and Doc Quality, then emits an HTML report with an A–F grade and concrete fixes. Use when the user asks to audit agent experience, test a skill, audit docs for agents, check if a SDK is agent-friendly, validate a SKILL.md, measure agent DX, or benchmark how painful onboarding is for an AI agent. Triggers: 'audit agent experience', 'test this skill', 'audit docs for agents', 'is my SDK agent-friendly', 'run a DX audit', 'agent experience test', 'test my docs', 'how do agents do with my product'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1828,1831,1834,1835,1838,1841],{"name":1829,"slug":1830,"type":15},"Agents","agents",{"name":1832,"slug":1833,"type":15},"Audit","audit",{"name":9,"slug":8,"type":15},{"name":1836,"slug":1837,"type":15},"Engineering","engineering",{"name":1839,"slug":1840,"type":15},"Multi-Agent","multi-agent",{"name":1842,"slug":1843,"type":15},"QA","qa","2026-05-29T06:58:56.259807",{"slug":1846,"name":1846,"fn":1847,"description":1848,"org":1849,"tags":1850,"stars":26,"repoUrl":27,"updatedAt":1859},"autobrowse","run self-improving browser automation","Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1851,1852,1855,1858],{"name":1829,"slug":1830,"type":15},{"name":1853,"slug":1854,"type":15},"Automation","automation",{"name":1856,"slug":1857,"type":15},"Browser Automation","browser-automation",{"name":9,"slug":8,"type":15},"2026-04-23T05:00:30.528336",{"slug":1861,"name":1861,"fn":1862,"description":1863,"org":1864,"tags":1865,"stars":26,"repoUrl":27,"updatedAt":1871},"browser","automate browser interactions via CLI","Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1866,1867,1868],{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1869,"slug":1870,"type":15},"CLI","cli","2026-04-06T18:06:22.005051",{"slug":1873,"name":1873,"fn":1874,"description":1875,"org":1876,"tags":1877,"stars":26,"repoUrl":27,"updatedAt":1889},"browser-to-api","generate OpenAPI specs from browser traffic","Turn a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a `browser-trace` capture. Use when the user wants to discover\u002Fextract API endpoints from a browser session, build an OpenAPI doc from network traffic, or document a third-party site's XHR\u002Ffetch surface for client integration.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1878,1881,1882,1883,1886],{"name":1879,"slug":1880,"type":15},"API Development","api-development",{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1884,"slug":1885,"type":15},"HTTP","http",{"name":1887,"slug":1888,"type":15},"OpenAPI","openapi","2026-05-14T06:07:27.298495",{"slug":1891,"name":1891,"fn":1892,"description":1893,"org":1894,"tags":1895,"stars":26,"repoUrl":27,"updatedAt":1904},"browser-trace","capture and debug browser automation traces","Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network\u002Fconsole\u002FDOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1896,1897,1898,1901],{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1899,"slug":1900,"type":15},"Debugging","debugging",{"name":1902,"slug":1903,"type":15},"Observability","observability","2026-04-28T05:41:33.024656",{"slug":1906,"name":1906,"fn":1907,"description":1908,"org":1909,"tags":1910,"stars":26,"repoUrl":27,"updatedAt":1922},"browser-use-to-stagehand","migrate browser-use scripts to Stagehand","Migrate browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase. Use when the user wants to convert, port, rewrite, or migrate a browser-use Agent script to Stagehand, map browser-use features\u002FAPIs to Stagehand primitives (act\u002Fextract\u002Fobserve\u002Fagent), or move agentic browser automation onto Browserbase with more determinism. Triggers on \"browser-use\", \"browser_use\", or \"Agent(task=...)\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1911,1912,1913,1916,1919],{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1914,"slug":1915,"type":15},"Migration","migration",{"name":1917,"slug":1918,"type":15},"Python","python",{"name":1920,"slug":1921,"type":15},"TypeScript","typescript","2026-06-26T07:57:47.428249",{"slug":4,"name":4,"fn":5,"description":6,"org":1924,"tags":1925,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1926,1927,1928,1929,1930],{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":24,"slug":25,"type":15},16,{"items":1933,"total":2048},[1934,1945,1954,1961,1967,1975,1982,1990,1998,2012,2024,2037],{"slug":85,"name":85,"fn":1935,"description":1936,"org":1937,"tags":1938,"stars":1942,"repoUrl":1943,"updatedAt":1944},"run Browserbase browser automation","Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch\u002Fsearch, diagnostics, and Browse.sh skill discovery\u002Finstallation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase resources, call Browserbase Functions, browse or scaffold Browserbase templates, fetch or search web content, diagnose browse setup, find or install a skill for a website task, discover site-specific Browse.sh skills, or install\u002Frefresh this browse skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1939,1940,1941],{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1869,"slug":1870,"type":15},23676,"https:\u002F\u002Fgithub.com\u002Fbrowserbase\u002Fstagehand","2026-06-06T07:11:24.95733",{"slug":1823,"name":1823,"fn":1824,"description":1825,"org":1946,"tags":1947,"stars":26,"repoUrl":27,"updatedAt":1844},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1948,1949,1950,1951,1952,1953],{"name":1829,"slug":1830,"type":15},{"name":1832,"slug":1833,"type":15},{"name":9,"slug":8,"type":15},{"name":1836,"slug":1837,"type":15},{"name":1839,"slug":1840,"type":15},{"name":1842,"slug":1843,"type":15},{"slug":1846,"name":1846,"fn":1847,"description":1848,"org":1955,"tags":1956,"stars":26,"repoUrl":27,"updatedAt":1859},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1957,1958,1959,1960],{"name":1829,"slug":1830,"type":15},{"name":1853,"slug":1854,"type":15},{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"slug":1861,"name":1861,"fn":1862,"description":1863,"org":1962,"tags":1963,"stars":26,"repoUrl":27,"updatedAt":1871},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1964,1965,1966],{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1869,"slug":1870,"type":15},{"slug":1873,"name":1873,"fn":1874,"description":1875,"org":1968,"tags":1969,"stars":26,"repoUrl":27,"updatedAt":1889},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1970,1971,1972,1973,1974],{"name":1879,"slug":1880,"type":15},{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1884,"slug":1885,"type":15},{"name":1887,"slug":1888,"type":15},{"slug":1891,"name":1891,"fn":1892,"description":1893,"org":1976,"tags":1977,"stars":26,"repoUrl":27,"updatedAt":1904},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1978,1979,1980,1981],{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1899,"slug":1900,"type":15},{"name":1902,"slug":1903,"type":15},{"slug":1906,"name":1906,"fn":1907,"description":1908,"org":1983,"tags":1984,"stars":26,"repoUrl":27,"updatedAt":1922},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1985,1986,1987,1988,1989],{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},{"name":1914,"slug":1915,"type":15},{"name":1917,"slug":1918,"type":15},{"name":1920,"slug":1921,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":1991,"tags":1992,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1993,1994,1995,1996,1997],{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":24,"slug":25,"type":15},{"slug":1999,"name":1999,"fn":2000,"description":2001,"org":2002,"tags":2003,"stars":26,"repoUrl":27,"updatedAt":2011},"competitor-analysis","analyze competitors across features and pricing","Competitor research and intelligence skill. Takes a user's company (with optional\nseed competitor URLs), auto-discovers additional competitors via Browserbase Search API,\ndeeply researches each using a 4-lane pattern (marketing surface, external signal,\npublic benchmarks, strategic diff vs the user's company), and compiles the results\ninto an HTML report with four views: overview, per-competitor deep dive, side-by-side\nfeature\u002Fpricing matrix, and a chronological mentions feed (news, reviews,\nsocial, comparison pages, and public benchmarks).\nUse when the user wants to: (1) analyze competitors, (2) build a competitive matrix,\n(3) extract competitor pricing \u002F features, (4) find comparison pages and online\nmentions of competitors, (5) surface public benchmarks. Triggers: \"competitor analysis\",\n\"analyze competitors\", \"competitive intel\", \"competitor research\", \"competitor pricing\",\n\"feature comparison\", \"price comparison\", \"find comparisons\", \"who's comparing us\",\n\"competitor mentions\", \"competitor benchmarks\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2004,2005,2006,2007,2008],{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":2009,"slug":2010,"type":15},"Strategy","strategy","2026-06-19T09:41:33.392499",{"slug":2013,"name":2013,"fn":2014,"description":2015,"org":2016,"tags":2017,"stars":26,"repoUrl":27,"updatedAt":2023},"cookie-sync","sync Chrome cookies to a Browserbase context","Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2018,2021,2022],{"name":2019,"slug":2020,"type":15},"Auth","auth",{"name":1856,"slug":1857,"type":15},{"name":9,"slug":8,"type":15},"2026-04-06T18:06:23.3251",{"slug":2025,"name":2025,"fn":2026,"description":2027,"org":2028,"tags":2029,"stars":26,"repoUrl":27,"updatedAt":2036},"event-prospecting","research event speakers for sales prospecting","Event prospecting skill. Takes a conference \u002F event speakers URL,\nextracts the people, filters their companies against the user's\nICP, then deep-researches only the speakers at ICP-fit companies.\nOutputs a person-first HTML report where each card answers \"why\nshould the AE talk to this person?\" with all public links and a\none-click DM opener.\nUse when the user wants to: (1) find leads at a specific\nconference, (2) prep for an event, (3) research event speakers,\n(4) build a target list from a sponsor\u002Fexhibitor page,\n(5) scrape conference speakers and rank by ICP fit.\nTriggers: \"find leads at {event}\", \"research speakers at\",\n\"prospect this conference\", \"stripe sessions leads\",\n\"ai engineer summit prospects\", \"event prospecting\",\n\"scrape conference speakers\", \"who should I meet at\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2030,2031,2034,2035],{"name":9,"slug":8,"type":15},{"name":2032,"slug":2033,"type":15},"Prospecting","prospecting",{"name":13,"slug":14,"type":15},{"name":24,"slug":25,"type":15},"2026-04-28T05:41:31.770467",{"slug":2038,"name":2038,"fn":2039,"description":2040,"org":2041,"tags":2042,"stars":26,"repoUrl":27,"updatedAt":2047},"fetch","fetch URLs without a browser session","Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers, follow redirects, or get page source for simple scraping. Prefer it over a browser when JavaScript rendering and page interaction are not needed. Supports proxies and redirect control.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2043,2044],{"name":1884,"slug":1885,"type":15},{"name":2045,"slug":2046,"type":15},"Web Scraping","web-scraping","2026-04-06T18:06:19.462477",17]