[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-uniswap-skill-doctor":3,"mdc--wbr9q-key":30,"related-org-uniswap-skill-doctor":1107,"related-repo-uniswap-skill-doctor":1268},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":19,"repoUrl":20,"updatedAt":21,"license":22,"forks":23,"topics":24,"repo":25,"sourceUrl":28,"mdContent":29},"skill-doctor","audit and optimize agent skills","Audit, map, and improve your Claude Code skills, agents, and slash commands — and mine the current session for new ones worth creating. Use this whenever the user says \"review my skills\", \"optimize my skills\", \"update my skills\", \"update all my skills\", \"maintain my skills\", \"audit my agents\", \"map my skills\", \"what skills do I have\", \"suggest skill improvements\", \"are any of my skills redundant\", \"clean up my skills\", \"turn this into a skill\", \"should this be a skill or an agent\", \"codify this workflow\", or invokes \u002Fskill-map, \u002Fskill-mine, or \u002Fskill-new. Also use PROACTIVELY after finishing a multi-step workflow that the user is likely to repeat (especially right after opening a PR) to ask whether it should become a skill or agent. It inventories every skill\u002Fagent\u002Fcommand across the user's own dirs AND all installed marketplaces, flags overlaps \u002F gaps \u002F weak triggering descriptions, and — when there's real prior work in the session — proposes new or edited skills\u002Fagents grounded in what actually happened.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"uniswap","Uniswap","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Funiswap.png",[12,16],{"name":13,"slug":14,"type":15},"Plugin Development","plugin-development","tag",{"name":17,"slug":18,"type":15},"Agents","agents",39,"https:\u002F\u002Fgithub.com\u002FUniswap\u002Fai-toolkit","2026-07-17T06:08:14.373821",null,10,[],{"repoUrl":20,"stars":19,"forks":23,"topics":26,"description":27},[],"🤖 AI Toolkit - Standardized setup for Claude Code AI workflows. Nx monorepo with reusable agents, commands, and generators for enhanced AI-assisted development.","https:\u002F\u002Fgithub.com\u002FUniswap\u002Fai-toolkit\u002Ftree\u002FHEAD\u002Fpackages\u002Fplugins\u002Fskill-management\u002Fskills\u002Fskill-doctor","---\nname: skill-doctor\ndescription: >\n  Audit, map, and improve your Claude Code skills, agents, and slash commands —\n  and mine the current session for new ones worth creating. Use this whenever the\n  user says \"review my skills\", \"optimize my skills\", \"update my skills\", \"update\n  all my skills\", \"maintain my skills\", \"audit my agents\", \"map my skills\", \"what\n  skills do I have\", \"suggest skill improvements\", \"are any of my skills\n  redundant\", \"clean up my skills\", \"turn this into a skill\", \"should this be a\n  skill or an agent\", \"codify this workflow\", or invokes \u002Fskill-map, \u002Fskill-mine,\n  or \u002Fskill-new. Also use PROACTIVELY after finishing a multi-step workflow that\n  the user is likely to repeat (especially right after opening a PR) to ask\n  whether it should become a skill or agent. It inventories every\n  skill\u002Fagent\u002Fcommand across the user's own dirs AND all installed marketplaces,\n  flags overlaps \u002F gaps \u002F weak triggering descriptions, and — when there's real\n  prior work in the session — proposes new or edited skills\u002Fagents grounded in\n  what actually happened.\n---\n\n# skill-doctor\n\nThe orchestrator\u002Ftriage layer over the user's whole Claude Code customization\nsurface. It does the _finding_ — what to add, merge, fix, or codify — then hands\nthe deep work to the tools that already own it. **Reuse, don't reinvent:**\n\n- **Creating or iterating a skill (drafting, evals, description optimization, packaging)** → invoke the `skill-creator` skill if it's\n  installed (it ships in Anthropic's agent-skills marketplace and bundles\n  `improve_description.py`, `run_loop.py`, `package_skill.py`, `quick_validate.py`).\n- **Tuning an agent's prompt** → delegate to the `agent-optimizer` or `prompt-engineer` agents.\n- **Scoring an agent's capabilities \u002F team fit** → the `agent-capability-analyst` agent.\n- **Cataloging agents** → the `claude-agent-discovery` agent.\n- **\"This is really a standing rule, not a skill\"** → write it into the relevant\n  `CLAUDE.md` (e.g. via an `update-claude-md` skill) or the project's memory store.\n- **Auditing \u002F cleaning up the memory store itself** (orphans vs `MEMORY.md`, stale\n  memories, dedupe, \"scope memories into skills\") → the `memory-doctor` skill if\n  installed, the sibling of this one for the memory surface. skill-doctor _reads_\n  memories as input for skill ideas; memory-doctor _maintains_ the memory files.\n\n## Editable targets — read this first\n\nYou may **edit\u002Fcreate** files under:\n\n- `~\u002F.claude\u002F{skills,agents,commands}\u002F` — the user's personal, non-git config.\n  Edited **in place**.\n- Skill\u002Fagent\u002Fcommand files inside a **git repo** the user owns or contributes to.\n  Changes here ship as a **draft PR** (see \"Delivering changes once approved\"\n  below) — never an in-place edit on the repo's working branch, never a direct\n  commit to its default branch.\n\nInstalled marketplaces and plugin caches (`~\u002F.claude\u002Fplugins\u002Fmarketplaces\u002F…`,\n`~\u002F.claude\u002Fplugins\u002Fcache\u002F…`) are **read-only** install mirrors — map and analyze,\nnever edit. If a worthwhile fix lands on a read-only mirror, fork a copy into a\nwritable location instead. The inventory tags every entry with `writable`; respect\nit.\n\n**Never auto-apply.** Propose a numbered menu and let the user pick. The user\nalways approves _which_ change before you make it.\n\n**Delivering changes once approved:**\n\n- `~\u002F.claude\u002F…` (not a git repo): edit in place; show the before\u002Fafter first.\n- Any file inside a **git repo**: deliver as a **draft PR** automatically — don't\n  ask a second time once the change itself is approved. Detect the repo's default\n  branch (`git symbolic-ref --short refs\u002Fremotes\u002Forigin\u002FHEAD` — it is NOT always\n  `main`), branch off `origin\u002F\u003Cdefault>` in a clean worktree, apply the edit,\n  commit, push, and `gh pr create --draft --base \u003Cdefault>`. Return the PR URL and\n  leave it in draft. Never push to the default branch directly. One draft PR per\n  logical change; group trivially-related edits in the same repo into one PR.\n\n## Run modes\n\nThe skill takes an optional mode argument (the slash commands pass it):\n\n| Mode      | Steps                              | When                                                                               |\n| --------- | ---------------------------------- | ---------------------------------------------------------------------------------- |\n| `map`     | 1–3                                | Pure audit \u002F fresh session. Inventory + analysis + suggestions. No session mining. |\n| `session` | light 1, then 4                    | Mine THIS conversation for skills\u002Fagents to add or fix.                            |\n| `create`  | jump to 4's \"new skill\u002Fagent\" path | \"Turn this into a skill.\" Hand to skill-creator.                                   |\n| `full`    | 1–5                                | Everything. Default when the session contains real work.                           |\n\n### Step 1 — Resolve mode\n\nIf a mode was passed, use it. Otherwise auto-detect: if the session already\ncontains substantive prior work (a real task was carried out, not just this\ninvocation), use `full`; if it's a fresh\u002Fempty session, use `map`. State the\nmode you picked in one line, then run only the steps its row enables.\n\n### Step 2 — Inventory (modes: map, full; light version for session\u002Fcreate)\n\nRun the bundled script — it extracts the signal without you reading hundreds of\nfiles:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fskill-doctor\u002Fscripts\u002Finventory.py\" --cwd \"$PWD\"\n# session\u002Fcreate modes: add --mine-only to limit to writable (own) sources\n```\n\nIt writes `inventory.json` + `inventory.md` to a temp workspace and prints the\npath. **Read `inventory.md`** (compact tables grouped by source + a Flagged\nsection). Do NOT read every underlying file — that's the whole point of the\nscript.\n\nPresent a short summary: counts per source, and the headline flagged issues.\n\n### Step 3 — Analysis pass (modes: map, full)\n\nReason over the map (not the raw files). Produce a **prioritized, numbered list**\nof suggested improvements. For each: target file, problem, proposed change, and\nwhether it's `writable`. Cover:\n\n- **Overlaps \u002F duplicates.** Use the `duplicate_names` and\n  `near_duplicate_descriptions` flags. Ignore `mirror-only` duplicates\n  (marketplace↔plugin-cache are just install mirrors of the same upstream item).\n  Focus on `[editable]` collisions and genuinely distinct skills doing the same\n  job. Recommend a canonical one + merge\u002Fdeprecate the rest.\n- **Gaps.** Recurring needs with no skill. Cross-reference the project's memory\n  store if one exists — many feedback memories encode repeated corrections that\n  may deserve a skill.\n- **Trigger-quality.** Use `weak_or_missing_description` and\n  `no_trigger_language`. For the handful of **writable** items you'll actually\n  propose changing, deep-read them **via a subagent** (Explore or general-purpose)\n  so main context stays bounded — ask the subagent to return the current\n  description + body summary + a tightened description proposal. For rigorous\n  triggering work, hand the item to skill-creator's `improve_description.py` \u002F\n  `run_loop.py` loop.\n- **Oversized bodies.** `oversized_body` items (>500 lines) are candidates for\n  progressive disclosure (move detail into `references\u002F`).\n\nSee `references\u002Fanalysis-rubric.md` for the heuristics (good-description shape,\noverlap judgment, skill-vs-agent-vs-CLAUDE.md decision).\n\n### Step 4 — Session mining (modes: session, create, full)\n\nOnly meaningful if the session contains real prior work. Read the conversation\nand look for:\n\n- **Codify-worthy workflows** — a repeated multi-step sequence, or \"do X like\n  last time.\" Propose a NEW skill or agent: draft `name`, a pushy `description`\n  (per the rubric), and a body outline. Decide skill vs agent vs command using\n  the rubric. In `create` mode, go straight here and hand the draft to the\n  `skill-creator` skill to flesh out + eval.\n- **Undertriggering** — a skill that should have fired this session but didn't.\n  Identify which one and propose a description fix (the description is the\n  trigger mechanism).\n- **Misfire \u002F overtrigger** — a skill that fired wrongly. Tighten its description.\n- **Repeated corrections** — guidance the user gave more than once. Decide\n  whether it belongs in a skill, an agent, or as a standing rule (a `CLAUDE.md`\n  entry \u002F a memory file).\n\nGround every proposal in a specific moment from the conversation — quote the\nturn that motivates it. Vague \"you could add a skill for X\" proposals aren't useful.\n\n### Step 5 — Present & apply (all modes)\n\nShow the consolidated, prioritized menu. Mark each item `[editable]` or\n`[read-only]`. Let the user choose. Then, for accepted items only:\n\n- New\u002Fiterated skill → `skill-creator` skill.\n- Agent prompt tuning → `agent-optimizer` \u002F `prompt-engineer` agents.\n- Standing rule → an `update-claude-md` skill or a memory file.\n- Direct small edits (e.g. a tightened description):\n  - under `~\u002F.claude\u002F…` (non-git) → edit in place; show the before\u002Fafter first.\n  - inside a git repo → open a **draft PR** per \"Delivering changes once\n    approved\" (branch off the repo's default branch in a clean worktree, commit,\n    push, `gh pr create --draft`).\n\nAfter any change, suggest re-running `inventory.py` to confirm the flag cleared.\nFor draft PRs, surface the PR URL and note it's left in draft for review.\n",{"data":31,"body":32},{"name":4,"description":6},{"type":33,"children":34},"root",[35,42,62,242,249,261,301,337,354,362,425,431,436,557,564,583,589,594,675,708,713,719,738,870,883,889,894,974,979,985,1005,1088,1101],{"type":36,"tag":37,"props":38,"children":39},"element","h1",{"id":4},[40],{"type":41,"value":4},"text",{"type":36,"tag":43,"props":44,"children":45},"p",{},[46,48,54,56],{"type":41,"value":47},"The orchestrator\u002Ftriage layer over the user's whole Claude Code customization\nsurface. It does the ",{"type":36,"tag":49,"props":50,"children":51},"em",{},[52],{"type":41,"value":53},"finding",{"type":41,"value":55}," — what to add, merge, fix, or codify — then hands\nthe deep work to the tools that already own it. ",{"type":36,"tag":57,"props":58,"children":59},"strong",{},[60],{"type":41,"value":61},"Reuse, don't reinvent:",{"type":36,"tag":63,"props":64,"children":65},"ul",{},[66,116,142,160,176,202],{"type":36,"tag":67,"props":68,"children":69},"li",{},[70,75,77,84,86,92,94,100,101,107,108,114],{"type":36,"tag":57,"props":71,"children":72},{},[73],{"type":41,"value":74},"Creating or iterating a skill (drafting, evals, description optimization, packaging)",{"type":41,"value":76}," → invoke the ",{"type":36,"tag":78,"props":79,"children":81},"code",{"className":80},[],[82],{"type":41,"value":83},"skill-creator",{"type":41,"value":85}," skill if it's\ninstalled (it ships in Anthropic's agent-skills marketplace and bundles\n",{"type":36,"tag":78,"props":87,"children":89},{"className":88},[],[90],{"type":41,"value":91},"improve_description.py",{"type":41,"value":93},", ",{"type":36,"tag":78,"props":95,"children":97},{"className":96},[],[98],{"type":41,"value":99},"run_loop.py",{"type":41,"value":93},{"type":36,"tag":78,"props":102,"children":104},{"className":103},[],[105],{"type":41,"value":106},"package_skill.py",{"type":41,"value":93},{"type":36,"tag":78,"props":109,"children":111},{"className":110},[],[112],{"type":41,"value":113},"quick_validate.py",{"type":41,"value":115},").",{"type":36,"tag":67,"props":117,"children":118},{},[119,124,126,132,134,140],{"type":36,"tag":57,"props":120,"children":121},{},[122],{"type":41,"value":123},"Tuning an agent's prompt",{"type":41,"value":125}," → delegate to the ",{"type":36,"tag":78,"props":127,"children":129},{"className":128},[],[130],{"type":41,"value":131},"agent-optimizer",{"type":41,"value":133}," or ",{"type":36,"tag":78,"props":135,"children":137},{"className":136},[],[138],{"type":41,"value":139},"prompt-engineer",{"type":41,"value":141}," agents.",{"type":36,"tag":67,"props":143,"children":144},{},[145,150,152,158],{"type":36,"tag":57,"props":146,"children":147},{},[148],{"type":41,"value":149},"Scoring an agent's capabilities \u002F team fit",{"type":41,"value":151}," → the ",{"type":36,"tag":78,"props":153,"children":155},{"className":154},[],[156],{"type":41,"value":157},"agent-capability-analyst",{"type":41,"value":159}," agent.",{"type":36,"tag":67,"props":161,"children":162},{},[163,168,169,175],{"type":36,"tag":57,"props":164,"children":165},{},[166],{"type":41,"value":167},"Cataloging agents",{"type":41,"value":151},{"type":36,"tag":78,"props":170,"children":172},{"className":171},[],[173],{"type":41,"value":174},"claude-agent-discovery",{"type":41,"value":159},{"type":36,"tag":67,"props":177,"children":178},{},[179,184,186,192,194,200],{"type":36,"tag":57,"props":180,"children":181},{},[182],{"type":41,"value":183},"\"This is really a standing rule, not a skill\"",{"type":41,"value":185}," → write it into the relevant\n",{"type":36,"tag":78,"props":187,"children":189},{"className":188},[],[190],{"type":41,"value":191},"CLAUDE.md",{"type":41,"value":193}," (e.g. via an ",{"type":36,"tag":78,"props":195,"children":197},{"className":196},[],[198],{"type":41,"value":199},"update-claude-md",{"type":41,"value":201}," skill) or the project's memory store.",{"type":36,"tag":67,"props":203,"children":204},{},[205,210,212,218,220,226,228,233,235,240],{"type":36,"tag":57,"props":206,"children":207},{},[208],{"type":41,"value":209},"Auditing \u002F cleaning up the memory store itself",{"type":41,"value":211}," (orphans vs ",{"type":36,"tag":78,"props":213,"children":215},{"className":214},[],[216],{"type":41,"value":217},"MEMORY.md",{"type":41,"value":219},", stale\nmemories, dedupe, \"scope memories into skills\") → the ",{"type":36,"tag":78,"props":221,"children":223},{"className":222},[],[224],{"type":41,"value":225},"memory-doctor",{"type":41,"value":227}," skill if\ninstalled, the sibling of this one for the memory surface. skill-doctor ",{"type":36,"tag":49,"props":229,"children":230},{},[231],{"type":41,"value":232},"reads",{"type":41,"value":234},"\nmemories as input for skill ideas; memory-doctor ",{"type":36,"tag":49,"props":236,"children":237},{},[238],{"type":41,"value":239},"maintains",{"type":41,"value":241}," the memory files.",{"type":36,"tag":243,"props":244,"children":246},"h2",{"id":245},"editable-targets-read-this-first",[247],{"type":41,"value":248},"Editable targets — read this first",{"type":36,"tag":43,"props":250,"children":251},{},[252,254,259],{"type":41,"value":253},"You may ",{"type":36,"tag":57,"props":255,"children":256},{},[257],{"type":41,"value":258},"edit\u002Fcreate",{"type":41,"value":260}," files under:",{"type":36,"tag":63,"props":262,"children":263},{},[264,282],{"type":36,"tag":67,"props":265,"children":266},{},[267,273,275,280],{"type":36,"tag":78,"props":268,"children":270},{"className":269},[],[271],{"type":41,"value":272},"~\u002F.claude\u002F{skills,agents,commands}\u002F",{"type":41,"value":274}," — the user's personal, non-git config.\nEdited ",{"type":36,"tag":57,"props":276,"children":277},{},[278],{"type":41,"value":279},"in place",{"type":41,"value":281},".",{"type":36,"tag":67,"props":283,"children":284},{},[285,287,292,294,299],{"type":41,"value":286},"Skill\u002Fagent\u002Fcommand files inside a ",{"type":36,"tag":57,"props":288,"children":289},{},[290],{"type":41,"value":291},"git repo",{"type":41,"value":293}," the user owns or contributes to.\nChanges here ship as a ",{"type":36,"tag":57,"props":295,"children":296},{},[297],{"type":41,"value":298},"draft PR",{"type":41,"value":300}," (see \"Delivering changes once approved\"\nbelow) — never an in-place edit on the repo's working branch, never a direct\ncommit to its default branch.",{"type":36,"tag":43,"props":302,"children":303},{},[304,306,312,314,320,322,327,329,335],{"type":41,"value":305},"Installed marketplaces and plugin caches (",{"type":36,"tag":78,"props":307,"children":309},{"className":308},[],[310],{"type":41,"value":311},"~\u002F.claude\u002Fplugins\u002Fmarketplaces\u002F…",{"type":41,"value":313},",\n",{"type":36,"tag":78,"props":315,"children":317},{"className":316},[],[318],{"type":41,"value":319},"~\u002F.claude\u002Fplugins\u002Fcache\u002F…",{"type":41,"value":321},") are ",{"type":36,"tag":57,"props":323,"children":324},{},[325],{"type":41,"value":326},"read-only",{"type":41,"value":328}," install mirrors — map and analyze,\nnever edit. If a worthwhile fix lands on a read-only mirror, fork a copy into a\nwritable location instead. The inventory tags every entry with ",{"type":36,"tag":78,"props":330,"children":332},{"className":331},[],[333],{"type":41,"value":334},"writable",{"type":41,"value":336},"; respect\nit.",{"type":36,"tag":43,"props":338,"children":339},{},[340,345,347,352],{"type":36,"tag":57,"props":341,"children":342},{},[343],{"type":41,"value":344},"Never auto-apply.",{"type":41,"value":346}," Propose a numbered menu and let the user pick. The user\nalways approves ",{"type":36,"tag":49,"props":348,"children":349},{},[350],{"type":41,"value":351},"which",{"type":41,"value":353}," change before you make it.",{"type":36,"tag":43,"props":355,"children":356},{},[357],{"type":36,"tag":57,"props":358,"children":359},{},[360],{"type":41,"value":361},"Delivering changes once approved:",{"type":36,"tag":63,"props":363,"children":364},{},[365,376],{"type":36,"tag":67,"props":366,"children":367},{},[368,374],{"type":36,"tag":78,"props":369,"children":371},{"className":370},[],[372],{"type":41,"value":373},"~\u002F.claude\u002F…",{"type":41,"value":375}," (not a git repo): edit in place; show the before\u002Fafter first.",{"type":36,"tag":67,"props":377,"children":378},{},[379,381,385,387,391,393,399,401,407,409,415,417,423],{"type":41,"value":380},"Any file inside a ",{"type":36,"tag":57,"props":382,"children":383},{},[384],{"type":41,"value":291},{"type":41,"value":386},": deliver as a ",{"type":36,"tag":57,"props":388,"children":389},{},[390],{"type":41,"value":298},{"type":41,"value":392}," automatically — don't\nask a second time once the change itself is approved. Detect the repo's default\nbranch (",{"type":36,"tag":78,"props":394,"children":396},{"className":395},[],[397],{"type":41,"value":398},"git symbolic-ref --short refs\u002Fremotes\u002Forigin\u002FHEAD",{"type":41,"value":400}," — it is NOT always\n",{"type":36,"tag":78,"props":402,"children":404},{"className":403},[],[405],{"type":41,"value":406},"main",{"type":41,"value":408},"), branch off ",{"type":36,"tag":78,"props":410,"children":412},{"className":411},[],[413],{"type":41,"value":414},"origin\u002F\u003Cdefault>",{"type":41,"value":416}," in a clean worktree, apply the edit,\ncommit, push, and ",{"type":36,"tag":78,"props":418,"children":420},{"className":419},[],[421],{"type":41,"value":422},"gh pr create --draft --base \u003Cdefault>",{"type":41,"value":424},". Return the PR URL and\nleave it in draft. Never push to the default branch directly. One draft PR per\nlogical change; group trivially-related edits in the same repo into one PR.",{"type":36,"tag":243,"props":426,"children":428},{"id":427},"run-modes",[429],{"type":41,"value":430},"Run modes",{"type":36,"tag":43,"props":432,"children":433},{},[434],{"type":41,"value":435},"The skill takes an optional mode argument (the slash commands pass it):",{"type":36,"tag":437,"props":438,"children":439},"table",{},[440,464],{"type":36,"tag":441,"props":442,"children":443},"thead",{},[444],{"type":36,"tag":445,"props":446,"children":447},"tr",{},[448,454,459],{"type":36,"tag":449,"props":450,"children":451},"th",{},[452],{"type":41,"value":453},"Mode",{"type":36,"tag":449,"props":455,"children":456},{},[457],{"type":41,"value":458},"Steps",{"type":36,"tag":449,"props":460,"children":461},{},[462],{"type":41,"value":463},"When",{"type":36,"tag":465,"props":466,"children":467},"tbody",{},[468,491,513,535],{"type":36,"tag":445,"props":469,"children":470},{},[471,481,486],{"type":36,"tag":472,"props":473,"children":474},"td",{},[475],{"type":36,"tag":78,"props":476,"children":478},{"className":477},[],[479],{"type":41,"value":480},"map",{"type":36,"tag":472,"props":482,"children":483},{},[484],{"type":41,"value":485},"1–3",{"type":36,"tag":472,"props":487,"children":488},{},[489],{"type":41,"value":490},"Pure audit \u002F fresh session. Inventory + analysis + suggestions. No session mining.",{"type":36,"tag":445,"props":492,"children":493},{},[494,503,508],{"type":36,"tag":472,"props":495,"children":496},{},[497],{"type":36,"tag":78,"props":498,"children":500},{"className":499},[],[501],{"type":41,"value":502},"session",{"type":36,"tag":472,"props":504,"children":505},{},[506],{"type":41,"value":507},"light 1, then 4",{"type":36,"tag":472,"props":509,"children":510},{},[511],{"type":41,"value":512},"Mine THIS conversation for skills\u002Fagents to add or fix.",{"type":36,"tag":445,"props":514,"children":515},{},[516,525,530],{"type":36,"tag":472,"props":517,"children":518},{},[519],{"type":36,"tag":78,"props":520,"children":522},{"className":521},[],[523],{"type":41,"value":524},"create",{"type":36,"tag":472,"props":526,"children":527},{},[528],{"type":41,"value":529},"jump to 4's \"new skill\u002Fagent\" path",{"type":36,"tag":472,"props":531,"children":532},{},[533],{"type":41,"value":534},"\"Turn this into a skill.\" Hand to skill-creator.",{"type":36,"tag":445,"props":536,"children":537},{},[538,547,552],{"type":36,"tag":472,"props":539,"children":540},{},[541],{"type":36,"tag":78,"props":542,"children":544},{"className":543},[],[545],{"type":41,"value":546},"full",{"type":36,"tag":472,"props":548,"children":549},{},[550],{"type":41,"value":551},"1–5",{"type":36,"tag":472,"props":553,"children":554},{},[555],{"type":41,"value":556},"Everything. Default when the session contains real work.",{"type":36,"tag":558,"props":559,"children":561},"h3",{"id":560},"step-1-resolve-mode",[562],{"type":41,"value":563},"Step 1 — Resolve mode",{"type":36,"tag":43,"props":565,"children":566},{},[567,569,574,576,581],{"type":41,"value":568},"If a mode was passed, use it. Otherwise auto-detect: if the session already\ncontains substantive prior work (a real task was carried out, not just this\ninvocation), use ",{"type":36,"tag":78,"props":570,"children":572},{"className":571},[],[573],{"type":41,"value":546},{"type":41,"value":575},"; if it's a fresh\u002Fempty session, use ",{"type":36,"tag":78,"props":577,"children":579},{"className":578},[],[580],{"type":41,"value":480},{"type":41,"value":582},". State the\nmode you picked in one line, then run only the steps its row enables.",{"type":36,"tag":558,"props":584,"children":586},{"id":585},"step-2-inventory-modes-map-full-light-version-for-sessioncreate",[587],{"type":41,"value":588},"Step 2 — Inventory (modes: map, full; light version for session\u002Fcreate)",{"type":36,"tag":43,"props":590,"children":591},{},[592],{"type":41,"value":593},"Run the bundled script — it extracts the signal without you reading hundreds of\nfiles:",{"type":36,"tag":595,"props":596,"children":601},"pre",{"className":597,"code":598,"language":599,"meta":600,"style":600},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fskill-doctor\u002Fscripts\u002Finventory.py\" --cwd \"$PWD\"\n# session\u002Fcreate modes: add --mine-only to limit to writable (own) sources\n","bash","",[602],{"type":36,"tag":78,"props":603,"children":604},{"__ignoreMap":600},[605,665],{"type":36,"tag":606,"props":607,"children":610},"span",{"class":608,"line":609},"line",1,[611,617,623,629,634,640,645,650,655,660],{"type":36,"tag":606,"props":612,"children":614},{"style":613},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[615],{"type":41,"value":616},"python3",{"type":36,"tag":606,"props":618,"children":620},{"style":619},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[621],{"type":41,"value":622}," \"${",{"type":36,"tag":606,"props":624,"children":626},{"style":625},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[627],{"type":41,"value":628},"CLAUDE_PLUGIN_ROOT",{"type":36,"tag":606,"props":630,"children":631},{"style":619},[632],{"type":41,"value":633},"}",{"type":36,"tag":606,"props":635,"children":637},{"style":636},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[638],{"type":41,"value":639},"\u002Fskills\u002Fskill-doctor\u002Fscripts\u002Finventory.py",{"type":36,"tag":606,"props":641,"children":642},{"style":619},[643],{"type":41,"value":644},"\"",{"type":36,"tag":606,"props":646,"children":647},{"style":636},[648],{"type":41,"value":649}," --cwd",{"type":36,"tag":606,"props":651,"children":652},{"style":619},[653],{"type":41,"value":654}," \"",{"type":36,"tag":606,"props":656,"children":657},{"style":625},[658],{"type":41,"value":659},"$PWD",{"type":36,"tag":606,"props":661,"children":662},{"style":619},[663],{"type":41,"value":664},"\"\n",{"type":36,"tag":606,"props":666,"children":668},{"class":608,"line":667},2,[669],{"type":36,"tag":606,"props":670,"children":672},{"style":671},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[673],{"type":41,"value":674},"# session\u002Fcreate modes: add --mine-only to limit to writable (own) sources\n",{"type":36,"tag":43,"props":676,"children":677},{},[678,680,686,688,694,696,706],{"type":41,"value":679},"It writes ",{"type":36,"tag":78,"props":681,"children":683},{"className":682},[],[684],{"type":41,"value":685},"inventory.json",{"type":41,"value":687}," + ",{"type":36,"tag":78,"props":689,"children":691},{"className":690},[],[692],{"type":41,"value":693},"inventory.md",{"type":41,"value":695}," to a temp workspace and prints the\npath. ",{"type":36,"tag":57,"props":697,"children":698},{},[699,701],{"type":41,"value":700},"Read ",{"type":36,"tag":78,"props":702,"children":704},{"className":703},[],[705],{"type":41,"value":693},{"type":41,"value":707}," (compact tables grouped by source + a Flagged\nsection). Do NOT read every underlying file — that's the whole point of the\nscript.",{"type":36,"tag":43,"props":709,"children":710},{},[711],{"type":41,"value":712},"Present a short summary: counts per source, and the headline flagged issues.",{"type":36,"tag":558,"props":714,"children":716},{"id":715},"step-3-analysis-pass-modes-map-full",[717],{"type":41,"value":718},"Step 3 — Analysis pass (modes: map, full)",{"type":36,"tag":43,"props":720,"children":721},{},[722,724,729,731,736],{"type":41,"value":723},"Reason over the map (not the raw files). Produce a ",{"type":36,"tag":57,"props":725,"children":726},{},[727],{"type":41,"value":728},"prioritized, numbered list",{"type":41,"value":730},"\nof suggested improvements. For each: target file, problem, proposed change, and\nwhether it's ",{"type":36,"tag":78,"props":732,"children":734},{"className":733},[],[735],{"type":41,"value":334},{"type":41,"value":737},". Cover:",{"type":36,"tag":63,"props":739,"children":740},{},[741,783,793,845],{"type":36,"tag":67,"props":742,"children":743},{},[744,749,751,757,759,765,767,773,775,781],{"type":36,"tag":57,"props":745,"children":746},{},[747],{"type":41,"value":748},"Overlaps \u002F duplicates.",{"type":41,"value":750}," Use the ",{"type":36,"tag":78,"props":752,"children":754},{"className":753},[],[755],{"type":41,"value":756},"duplicate_names",{"type":41,"value":758}," and\n",{"type":36,"tag":78,"props":760,"children":762},{"className":761},[],[763],{"type":41,"value":764},"near_duplicate_descriptions",{"type":41,"value":766}," flags. Ignore ",{"type":36,"tag":78,"props":768,"children":770},{"className":769},[],[771],{"type":41,"value":772},"mirror-only",{"type":41,"value":774}," duplicates\n(marketplace↔plugin-cache are just install mirrors of the same upstream item).\nFocus on ",{"type":36,"tag":78,"props":776,"children":778},{"className":777},[],[779],{"type":41,"value":780},"[editable]",{"type":41,"value":782}," collisions and genuinely distinct skills doing the same\njob. Recommend a canonical one + merge\u002Fdeprecate the rest.",{"type":36,"tag":67,"props":784,"children":785},{},[786,791],{"type":36,"tag":57,"props":787,"children":788},{},[789],{"type":41,"value":790},"Gaps.",{"type":41,"value":792}," Recurring needs with no skill. Cross-reference the project's memory\nstore if one exists — many feedback memories encode repeated corrections that\nmay deserve a skill.",{"type":36,"tag":67,"props":794,"children":795},{},[796,801,803,809,810,816,818,822,824,829,831,836,838,843],{"type":36,"tag":57,"props":797,"children":798},{},[799],{"type":41,"value":800},"Trigger-quality.",{"type":41,"value":802}," Use ",{"type":36,"tag":78,"props":804,"children":806},{"className":805},[],[807],{"type":41,"value":808},"weak_or_missing_description",{"type":41,"value":758},{"type":36,"tag":78,"props":811,"children":813},{"className":812},[],[814],{"type":41,"value":815},"no_trigger_language",{"type":41,"value":817},". For the handful of ",{"type":36,"tag":57,"props":819,"children":820},{},[821],{"type":41,"value":334},{"type":41,"value":823}," items you'll actually\npropose changing, deep-read them ",{"type":36,"tag":57,"props":825,"children":826},{},[827],{"type":41,"value":828},"via a subagent",{"type":41,"value":830}," (Explore or general-purpose)\nso main context stays bounded — ask the subagent to return the current\ndescription + body summary + a tightened description proposal. For rigorous\ntriggering work, hand the item to skill-creator's ",{"type":36,"tag":78,"props":832,"children":834},{"className":833},[],[835],{"type":41,"value":91},{"type":41,"value":837}," \u002F\n",{"type":36,"tag":78,"props":839,"children":841},{"className":840},[],[842],{"type":41,"value":99},{"type":41,"value":844}," loop.",{"type":36,"tag":67,"props":846,"children":847},{},[848,853,855,861,863,869],{"type":36,"tag":57,"props":849,"children":850},{},[851],{"type":41,"value":852},"Oversized bodies.",{"type":41,"value":854}," ",{"type":36,"tag":78,"props":856,"children":858},{"className":857},[],[859],{"type":41,"value":860},"oversized_body",{"type":41,"value":862}," items (>500 lines) are candidates for\nprogressive disclosure (move detail into ",{"type":36,"tag":78,"props":864,"children":866},{"className":865},[],[867],{"type":41,"value":868},"references\u002F",{"type":41,"value":115},{"type":36,"tag":43,"props":871,"children":872},{},[873,875,881],{"type":41,"value":874},"See ",{"type":36,"tag":78,"props":876,"children":878},{"className":877},[],[879],{"type":41,"value":880},"references\u002Fanalysis-rubric.md",{"type":41,"value":882}," for the heuristics (good-description shape,\noverlap judgment, skill-vs-agent-vs-CLAUDE.md decision).",{"type":36,"tag":558,"props":884,"children":886},{"id":885},"step-4-session-mining-modes-session-create-full",[887],{"type":41,"value":888},"Step 4 — Session mining (modes: session, create, full)",{"type":36,"tag":43,"props":890,"children":891},{},[892],{"type":41,"value":893},"Only meaningful if the session contains real prior work. Read the conversation\nand look for:",{"type":36,"tag":63,"props":895,"children":896},{},[897,937,947,957],{"type":36,"tag":67,"props":898,"children":899},{},[900,905,907,913,915,921,923,928,930,935],{"type":36,"tag":57,"props":901,"children":902},{},[903],{"type":41,"value":904},"Codify-worthy workflows",{"type":41,"value":906}," — a repeated multi-step sequence, or \"do X like\nlast time.\" Propose a NEW skill or agent: draft ",{"type":36,"tag":78,"props":908,"children":910},{"className":909},[],[911],{"type":41,"value":912},"name",{"type":41,"value":914},", a pushy ",{"type":36,"tag":78,"props":916,"children":918},{"className":917},[],[919],{"type":41,"value":920},"description",{"type":41,"value":922},"\n(per the rubric), and a body outline. Decide skill vs agent vs command using\nthe rubric. In ",{"type":36,"tag":78,"props":924,"children":926},{"className":925},[],[927],{"type":41,"value":524},{"type":41,"value":929}," mode, go straight here and hand the draft to the\n",{"type":36,"tag":78,"props":931,"children":933},{"className":932},[],[934],{"type":41,"value":83},{"type":41,"value":936}," skill to flesh out + eval.",{"type":36,"tag":67,"props":938,"children":939},{},[940,945],{"type":36,"tag":57,"props":941,"children":942},{},[943],{"type":41,"value":944},"Undertriggering",{"type":41,"value":946}," — a skill that should have fired this session but didn't.\nIdentify which one and propose a description fix (the description is the\ntrigger mechanism).",{"type":36,"tag":67,"props":948,"children":949},{},[950,955],{"type":36,"tag":57,"props":951,"children":952},{},[953],{"type":41,"value":954},"Misfire \u002F overtrigger",{"type":41,"value":956}," — a skill that fired wrongly. Tighten its description.",{"type":36,"tag":67,"props":958,"children":959},{},[960,965,967,972],{"type":36,"tag":57,"props":961,"children":962},{},[963],{"type":41,"value":964},"Repeated corrections",{"type":41,"value":966}," — guidance the user gave more than once. Decide\nwhether it belongs in a skill, an agent, or as a standing rule (a ",{"type":36,"tag":78,"props":968,"children":970},{"className":969},[],[971],{"type":41,"value":191},{"type":41,"value":973},"\nentry \u002F a memory file).",{"type":36,"tag":43,"props":975,"children":976},{},[977],{"type":41,"value":978},"Ground every proposal in a specific moment from the conversation — quote the\nturn that motivates it. Vague \"you could add a skill for X\" proposals aren't useful.",{"type":36,"tag":558,"props":980,"children":982},{"id":981},"step-5-present-apply-all-modes",[983],{"type":41,"value":984},"Step 5 — Present & apply (all modes)",{"type":36,"tag":43,"props":986,"children":987},{},[988,990,995,997,1003],{"type":41,"value":989},"Show the consolidated, prioritized menu. Mark each item ",{"type":36,"tag":78,"props":991,"children":993},{"className":992},[],[994],{"type":41,"value":780},{"type":41,"value":996}," or\n",{"type":36,"tag":78,"props":998,"children":1000},{"className":999},[],[1001],{"type":41,"value":1002},"[read-only]",{"type":41,"value":1004},". Let the user choose. Then, for accepted items only:",{"type":36,"tag":63,"props":1006,"children":1007},{},[1008,1020,1038,1050],{"type":36,"tag":67,"props":1009,"children":1010},{},[1011,1013,1018],{"type":41,"value":1012},"New\u002Fiterated skill → ",{"type":36,"tag":78,"props":1014,"children":1016},{"className":1015},[],[1017],{"type":41,"value":83},{"type":41,"value":1019}," skill.",{"type":36,"tag":67,"props":1021,"children":1022},{},[1023,1025,1030,1032,1037],{"type":41,"value":1024},"Agent prompt tuning → ",{"type":36,"tag":78,"props":1026,"children":1028},{"className":1027},[],[1029],{"type":41,"value":131},{"type":41,"value":1031}," \u002F ",{"type":36,"tag":78,"props":1033,"children":1035},{"className":1034},[],[1036],{"type":41,"value":139},{"type":41,"value":141},{"type":36,"tag":67,"props":1039,"children":1040},{},[1041,1043,1048],{"type":41,"value":1042},"Standing rule → an ",{"type":36,"tag":78,"props":1044,"children":1046},{"className":1045},[],[1047],{"type":41,"value":199},{"type":41,"value":1049}," skill or a memory file.",{"type":36,"tag":67,"props":1051,"children":1052},{},[1053,1055],{"type":41,"value":1054},"Direct small edits (e.g. a tightened description):\n",{"type":36,"tag":63,"props":1056,"children":1057},{},[1058,1070],{"type":36,"tag":67,"props":1059,"children":1060},{},[1061,1063,1068],{"type":41,"value":1062},"under ",{"type":36,"tag":78,"props":1064,"children":1066},{"className":1065},[],[1067],{"type":41,"value":373},{"type":41,"value":1069}," (non-git) → edit in place; show the before\u002Fafter first.",{"type":36,"tag":67,"props":1071,"children":1072},{},[1073,1075,1079,1081,1087],{"type":41,"value":1074},"inside a git repo → open a ",{"type":36,"tag":57,"props":1076,"children":1077},{},[1078],{"type":41,"value":298},{"type":41,"value":1080}," per \"Delivering changes once\napproved\" (branch off the repo's default branch in a clean worktree, commit,\npush, ",{"type":36,"tag":78,"props":1082,"children":1084},{"className":1083},[],[1085],{"type":41,"value":1086},"gh pr create --draft",{"type":41,"value":115},{"type":36,"tag":43,"props":1089,"children":1090},{},[1091,1093,1099],{"type":41,"value":1092},"After any change, suggest re-running ",{"type":36,"tag":78,"props":1094,"children":1096},{"className":1095},[],[1097],{"type":41,"value":1098},"inventory.py",{"type":41,"value":1100}," to confirm the flag cleared.\nFor draft PRs, surface the PR URL and note it's left in draft for review.",{"type":36,"tag":1102,"props":1103,"children":1104},"style",{},[1105],{"type":41,"value":1106},"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":1108,"total":1267},[1109,1130,1145,1158,1171,1184,1197,1210,1224,1235,1246,1257],{"slug":1110,"name":1110,"fn":1111,"description":1112,"org":1113,"tags":1114,"stars":1127,"repoUrl":1128,"updatedAt":1129},"configurator","configure auction smart contract parameters","Configure CCA (Continuous Clearing Auction) smart contract parameters through an interactive bulk form flow. Use when user says \"configure auction\", \"cca auction\", \"setup token auction\", \"auction configuration\", \"continuous auction\", or mentions CCA contracts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1115,1118,1121,1124],{"name":1116,"slug":1117,"type":15},"Configuration","configuration",{"name":1119,"slug":1120,"type":15},"Ethereum","ethereum",{"name":1122,"slug":1123,"type":15},"Smart Contracts","smart-contracts",{"name":1125,"slug":1126,"type":15},"Web3","web3",215,"https:\u002F\u002Fgithub.com\u002FUniswap\u002Funiswap-ai","2026-07-17T06:08:08.974641",{"slug":1131,"name":1131,"fn":1132,"description":1133,"org":1134,"tags":1135,"stars":1127,"repoUrl":1128,"updatedAt":1144},"copy-trade","copy trades from crypto wallets","This skill should be used when the user asks to \"copy trades from\" a wallet, \"mirror a wallet\", \"follow this address\", set up \"copy trading\", \"track and replicate a trader\", or mirror another account's swaps bounded by guardrails. Watches a target wallet and mirrors its trades, filtered by chain, asset match, position size, and the follower's own portfolio state.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1136,1139,1140,1143],{"name":1137,"slug":1138,"type":15},"Automation","automation",{"name":1119,"slug":1120,"type":15},{"name":1141,"slug":1142,"type":15},"Trading","trading",{"name":1125,"slug":1126,"type":15},"2026-07-17T06:04:21.974052",{"slug":1146,"name":1146,"fn":1147,"description":1148,"org":1149,"tags":1150,"stars":1127,"repoUrl":1128,"updatedAt":1157},"dca-bot","automate dollar cost average token purchases","This skill should be used when the user wants to \"dca into\" a token, \"buy X every day\", set up a \"recurring buy\", \"dollar cost average\" into an asset, \"schedule a buy\", or \"auto-buy on a dip\". Buys a fixed amount into a token on a schedule, optionally only when a condition holds (for example only when ETH is below a price threshold). The host agent's scheduler wakes the skill on a cadence; each wake is one self-contained run.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1151,1152,1155,1156],{"name":1137,"slug":1138,"type":15},{"name":1153,"slug":1154,"type":15},"DeFi","defi",{"name":1141,"slug":1142,"type":15},{"name":1125,"slug":1126,"type":15},"2026-07-17T06:05:37.160647",{"slug":1159,"name":1159,"fn":1160,"description":1161,"org":1162,"tags":1163,"stars":1127,"repoUrl":1128,"updatedAt":1170},"deployer","deploy Uniswap CCA smart contracts","Deploy CCA (Continuous Clearing Auction) smart contracts using the Factory pattern. Use when user says \"deploy auction\", \"deploy cca\", \"factory deployment\", or wants to deploy a configured auction.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1164,1167,1168,1169],{"name":1165,"slug":1166,"type":15},"Deployment","deployment",{"name":1119,"slug":1120,"type":15},{"name":1122,"slug":1123,"type":15},{"name":1125,"slug":1126,"type":15},"2026-07-17T06:08:09.661977",{"slug":1172,"name":1172,"fn":1173,"description":1174,"org":1175,"tags":1176,"stars":1127,"repoUrl":1128,"updatedAt":1183},"index-bot","create and rebalance asset portfolios","This skill should be used when the user asks to \"create an index\", \"build a basket of top assets\", \"buy a weighted basket\", \"make a portfolio of assets\", \"equal-weight basket\", \"rebalance my portfolio\", \"track the top N tokens\", or wants an automated, weighted multi-asset basket that buys in one pass and rebalances on a cadence. Builds the basket spec, delegates each buy and rebalance swap to the swap-integration Trading API flow, and records target weights in state.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1177,1178,1181,1182],{"name":1119,"slug":1120,"type":15},{"name":1179,"slug":1180,"type":15},"Portfolio Management","portfolio-management",{"name":1141,"slug":1142,"type":15},{"name":1125,"slug":1126,"type":15},"2026-07-17T06:04:22.328253",{"slug":1185,"name":1185,"fn":1186,"description":1187,"org":1188,"tags":1189,"stars":1127,"repoUrl":1128,"updatedAt":1196},"liquidity-planner","plan and create liquidity positions","This skill should be used when the user asks to \"provide liquidity\", \"create LP position\", \"add liquidity to pool\", \"become a liquidity provider\", \"create v3 position\", \"create v4 position\", \"concentrated liquidity\", \"set price range\", or mentions providing liquidity, LP positions, or liquidity pools on Uniswap. Generates deep links to create positions in the Uniswap interface.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1190,1191,1192,1195],{"name":1153,"slug":1154,"type":15},{"name":1119,"slug":1120,"type":15},{"name":1193,"slug":1194,"type":15},"Liquidity","liquidity",{"name":1125,"slug":1126,"type":15},"2026-07-17T06:08:09.315325",{"slug":1198,"name":1198,"fn":1199,"description":1200,"org":1201,"tags":1202,"stars":1127,"repoUrl":1128,"updatedAt":1209},"lp-integration","integrate Uniswap liquidity provisioning","Integrate Uniswap liquidity provisioning (LP) into applications via the LP REST API. Use when the user says \"LP API\", \"liquidity provisioning API\", \"provide liquidity programmatically\", \"create LP position via API\", \"add liquidity via API\", \"increase liquidity\", \"decrease liquidity\", \"remove liquidity\", \"claim LP fees\", \"collect LP fees\", \"manage LP positions in code\", or mentions building a backend, bot, or frontend that creates or manages Uniswap v2\u002Fv3\u002Fv4 liquidity positions through an API. Also use when debugging LP API calls (e.g. \u002Flp\u002Fcreate, \u002Flp\u002Fcheck_approval, \u002Flp\u002Fincrease, \u002Flp\u002Fdecrease, \u002Flp\u002Fclaim_fees), unexpected response fields, the approval or EIP-712 permit flow, or transaction-building errors for liquidity positions. For generating deep links to the Uniswap web app instead of calling the API, use the liquidity-planner skill; for using the Uniswap v4 SDK directly rather than the REST API, use the v4-sdk-integration skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1203,1206,1207,1208],{"name":1204,"slug":1205,"type":15},"API Development","api-development",{"name":1153,"slug":1154,"type":15},{"name":1193,"slug":1194,"type":15},{"name":1125,"slug":1126,"type":15},"2026-07-17T06:08:13.704465",{"slug":1211,"name":1211,"fn":1212,"description":1213,"org":1214,"tags":1215,"stars":1127,"repoUrl":1128,"updatedAt":1223},"pay-with-any-token","pay HTTP 402 challenges with Uniswap","Pay HTTP 402 payment challenges using tokens via the Tempo CLI and Uniswap Trading API. Use when the user encounters a 402 Payment Required response, needs to fulfill a machine payment, mentions \"MPP\", \"Tempo payment\", \"pay for API access\", \"HTTP 402\", \"x402\", \"machine payment protocol\", \"pay-with-any-token\", \"use tempo\", \"tempo request\", or \"tempo wallet\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1216,1217,1220,1221],{"name":1153,"slug":1154,"type":15},{"name":1218,"slug":1219,"type":15},"Payments","payments",{"name":1141,"slug":1142,"type":15},{"name":1222,"slug":1222,"type":15},"x402","2026-07-17T06:04:29.756086",{"slug":1225,"name":1225,"fn":1226,"description":1227,"org":1228,"tags":1229,"stars":1127,"repoUrl":1128,"updatedAt":1234},"pay-with-app","pay 402 payment challenges","Pay HTTP 402 payment challenges issued by OKX's Agent Payments Protocol (APP) on X Layer using tokens from any chain via the Uniswap Trading API. Use this skill whenever the user encounters a 402 challenge whose network resolves to X Layer (chain 196), mentions \"APP\", \"Agent Payments Protocol\", \"OKX agent payment\", \"OKX Onchain OS\", \"OKX agentic wallet\", \"x402 on X Layer\", \"USDT0\", \"x42\", \"Instant Payment\", \"Batch Payment\", \"pay for X Layer API\", or wants to pay an OKX-backed merchant. Even when the user does not explicitly say APP, prefer this skill for any 402 challenge whose network resolves to X Layer (chain 196). For 402 challenges on other chains (Ethereum, Base, Arbitrum, Tempo) use pay-with-any-token instead.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1230,1231,1232,1233],{"name":1204,"slug":1205,"type":15},{"name":1218,"slug":1219,"type":15},{"name":1125,"slug":1126,"type":15},{"name":1222,"slug":1222,"type":15},"2026-07-17T06:07:38.795043",{"slug":1236,"name":1236,"fn":1237,"description":1238,"org":1239,"tags":1240,"stars":1127,"repoUrl":1128,"updatedAt":1245},"swap-integration","integrate Uniswap swap functionality","Integrate Uniswap swaps into applications. Use when user says \"integrate swaps\", \"uniswap\", \"trading api\", \"add swap functionality\", \"build a swap frontend\", \"create a swap script\", \"smart contract swap integration\", \"use Universal Router\", \"Trading API\", or mentions swapping tokens via Uniswap.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1241,1242,1243,1244],{"name":1204,"slug":1205,"type":15},{"name":1153,"slug":1154,"type":15},{"name":1141,"slug":1142,"type":15},{"name":1125,"slug":1126,"type":15},"2026-07-17T06:08:10.354222",{"slug":1247,"name":1247,"fn":1248,"description":1249,"org":1250,"tags":1251,"stars":1127,"repoUrl":1128,"updatedAt":1256},"swap-planner","plan and execute token swaps","This skill should be used when the user asks to \"swap tokens\", \"trade ETH for USDC\", \"exchange tokens on Uniswap\", \"buy tokens\", \"sell tokens\", \"convert ETH to stablecoins\", \"find memecoins\", \"discover tokens\", \"research tokens\", \"tokens to buy\", \"find tokens to swap\", \"what should I buy\", or mentions swapping, trading, researching, discovering, buying, or exchanging tokens on any Uniswap-supported chain. Supports both known token swaps and token discovery workflows (discovery uses keyword search and web search — there is no live \"trending\" feed). Generates deep links to execute swaps in the Uniswap interface.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1252,1253,1254,1255],{"name":1153,"slug":1154,"type":15},{"name":1193,"slug":1194,"type":15},{"name":1141,"slug":1142,"type":15},{"name":1125,"slug":1126,"type":15},"2026-07-17T06:08:10.008152",{"slug":1258,"name":1258,"fn":1259,"description":1260,"org":1261,"tags":1262,"stars":1127,"repoUrl":1128,"updatedAt":1266},"v4-hook-generator","generate Uniswap v4 hook contracts","Generate Uniswap v4 hook contracts via OpenZeppelin MCP. Use when building custom swap logic, async swaps, hook-owned liquidity, custom curves, dynamic fees, MEV protection, limit orders, or oracle hooks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1263,1264,1265],{"name":1119,"slug":1120,"type":15},{"name":1122,"slug":1123,"type":15},{"name":1125,"slug":1126,"type":15},"2026-07-17T06:04:19.17669",19,{"items":1269,"total":1326},[1270,1283,1302,1321],{"slug":1271,"name":1271,"fn":1272,"description":1273,"org":1274,"tags":1275,"stars":19,"repoUrl":20,"updatedAt":1282},"debug-issue","debug code errors and crashes","Systematic debugging workflow for any code error, crash, test failure, or unexpected behavior. Use this skill whenever a user mentions an error, bug, exception, crash, test failure, or says something \"isn't working\", \"is broken\", \"keeps failing\", or \"isn't behaving as expected\" — even if they haven't used the word \"debug\". Also trigger when the user pastes a stack trace, error message, or unexpected output and asks why. Don't wait for the user to say \"debug\"; if they're describing a problem with running code, this skill applies. Trigger phrases include: \"getting an error\", \"this crashes\", \"why is this failing\", \"help me fix this\", \"it broke\", \"not working\", \"exception thrown\", \"stack trace\", \"test is failing\", \"something is wrong with\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1276,1279],{"name":1277,"slug":1278,"type":15},"Code Analysis","code-analysis",{"name":1280,"slug":1281,"type":15},"Debugging","debugging","2026-07-17T06:08:14.044038",{"slug":1284,"name":1284,"fn":1285,"description":1286,"org":1287,"tags":1288,"stars":19,"repoUrl":20,"updatedAt":1301},"generate-document","generate professional documents in multiple formats","Generate professional documents in multiple formats (PDF, DOCX, HTML, ODT, EPUB, RTF). Use when the user says \"make a PDF\", \"generate a report\", \"create a document\", \"export to Word\", \"make a Word doc\", \"convert to PDF\", \"export findings\", \"create documentation\", or wants to save analysis results as a formatted document.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1289,1292,1295,1298],{"name":1290,"slug":1291,"type":15},"Documents","documents",{"name":1293,"slug":1294,"type":15},"DOCX","docx",{"name":1296,"slug":1297,"type":15},"HTML","html",{"name":1299,"slug":1300,"type":15},"PDF","pdf","2026-07-17T06:07:16.218183",{"slug":1303,"name":1303,"fn":1304,"description":1305,"org":1306,"tags":1307,"stars":19,"repoUrl":20,"updatedAt":1320},"mermaid-diagram","generate Mermaid.js diagrams for visualization","Generate syntactically valid Mermaid.js diagrams. Use when user says \"create a mermaid diagram\", \"generate a flowchart\", \"draw a sequence diagram\", \"visualize with mermaid\", \"mermaid architecture diagram\", \"create a class diagram\", \"make a state diagram\", \"ER diagram\", \"Gantt chart\", \"gitGraph\", or when generating any Mermaid code block in markdown. Also use when asked to fix or debug a broken Mermaid diagram.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1308,1311,1314,1317],{"name":1309,"slug":1310,"type":15},"Design","design",{"name":1312,"slug":1313,"type":15},"Diagrams","diagrams",{"name":1315,"slug":1316,"type":15},"Documentation","documentation",{"name":1318,"slug":1319,"type":15},"Visualization","visualization","2026-07-17T06:05:36.621782",{"slug":4,"name":4,"fn":5,"description":6,"org":1322,"tags":1323,"stars":19,"repoUrl":20,"updatedAt":21},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1324,1325],{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},4]