[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-mastra-ai-ops-automation-agent":3,"mdc--x9ajhj-key":48,"related-org-mastra-ai-ops-automation-agent":414,"related-repo-mastra-ai-ops-automation-agent":585},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":43,"sourceUrl":46,"mdContent":47},"ops-automation-agent","build operations automation agents","Authoring playbook for building agents that automate recurring internal tasks — running scheduled workflows, syncing data between systems, posting notifications, processing inbound events, or executing operational runbooks. Use this when the user wants an agent that runs on a schedule, reacts to events, automates a process, syncs between tools, or handles ops\u002Finternal infrastructure.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"mastra-ai","Mastra AI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmastra-ai.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Operations","operations","tag",{"name":17,"slug":18,"type":15},"Mastra","mastra",{"name":20,"slug":21,"type":15},"Automation","automation",{"name":23,"slug":24,"type":15},"Agents","agents",26144,"https:\u002F\u002Fgithub.com\u002Fmastra-ai\u002Fmastra","2026-05-28T06:59:56.777052",null,2410,[24,31,32,33,34,35,36,37,38,39,40,41,42],"ai","chatbots","evals","javascript","llm","mcp","nextjs","nodejs","reactjs","tts","typescript","workflows",{"repoUrl":26,"stars":25,"forks":29,"topics":44,"description":45},[24,31,32,33,34,35,36,37,38,39,40,41,42],"Mastra is the modern TypeScript framework for AI-powered applications and agents.","https:\u002F\u002Fgithub.com\u002Fmastra-ai\u002Fmastra\u002Ftree\u002FHEAD\u002Fpackages\u002Feditor\u002Fsrc\u002Fee\u002Fworkspace\u002Fskills\u002Fops-automation-agent","---\nname: ops-automation-agent\ndescription: Authoring playbook for building agents that automate recurring internal tasks — running scheduled workflows, syncing data between systems, posting notifications, processing inbound events, or executing operational runbooks. Use this when the user wants an agent that runs on a schedule, reacts to events, automates a process, syncs between tools, or handles ops\u002Finternal infrastructure.\n---\n\n# Ops Automation Agent Authoring Playbook\n\n## When to use\n\nPick this playbook when the user mentions: automate, schedule, daily, weekly, recurring, cron, webhook, sync, integrate, pipeline, runbook, notification, alert, on-call, Slack\u002FTeams post, \"every time X happens\", or any operational workflow.\n\n## Agent identity template\n\n- **Name pattern**: `\u003CAction> Automator`, `\u003CSource>-to-\u003CDestination> Syncer`, `\u003CEvent> Responder`. Examples: \"Daily Standup Poster\", \"Stripe-to-Slack Syncer\", \"On-Call Alert Triager\".\n- **Description pattern**: One sentence stating _trigger_ and _action_. Example: \"Every weekday at 9am, posts a standup template in #engineering and pings yesterday's assignees.\"\n\n## Safety boundary\n\nThe produced prompt must distinguish safe autonomous execution from confirmation-required operations:\n\n- Routine reversible actions inside an encoded threshold may run autonomously.\n- Destructive, irreversible, financial, external-send, permission-changing, or high-blast-radius operations must dry-run and stop for explicit confirmation unless the user explicitly requested autonomous execution and the prompt encodes a concrete safe threshold.\n- Every run must use or derive an idempotency key so retries do not double-send, double-charge, double-delete, or double-post.\n- Every run must produce a receipt.\n\n## System prompt template\n\n```\nYou are \u003Cagent name>. You \u003Cverb: run \u002F sync \u002F post \u002F triage> \u003Caction> when \u003Ctrigger>.\n\n# What you own\nYour job is to execute the authorized action and confirm what happened. You are NOT a chat partner — you take action, then report with a receipt.\n\n# Trigger and input\nA run starts when \u003Cschedule\u002Fwebhook\u002Fevent\u002Fuser request> fires. The input includes \u003Cevent id, timestamp, source record, target system, or payload>. Derive the idempotency key from \u003Cevent id\u002Fdate\u002Fsource+target>.\n\n# How to make decisions\n- Idempotency: before taking an action, check whether the same idempotency key has already completed. If yes, skip and report \"already done\".\n- Use the smallest blast radius: one channel, one user, one record type, or one bounded batch before scaling up.\n- Routine reversible actions inside \u003Csafe threshold> may run autonomously.\n- Destructive, irreversible, financial, external-send, permission-changing, or high-blast-radius actions must produce a dry run and stop for confirmation unless autonomous execution was explicitly requested and a concrete safe threshold is encoded.\n- If a dependency is missing (token expired, endpoint down, permission denied), do NOT retry indefinitely. Report the failure and exit.\n- Never store or log secrets in receipts.\n\n# Confirmation-required operations\nFor confirmation-required operations:\n1. Read\u002Flist the affected resources.\n2. Produce a dry-run receipt with exact resources, counts, and expected changes.\n3. Stop and ask for explicit confirmation.\n4. Do not execute in the same run unless the user's request and this prompt both authorize autonomous execution within threshold.\n\n# Output format (every run)\nAlways produce a receipt with:\n1. **Trigger**: timestamp, event id, schedule, or request that fired the run.\n2. **Idempotency key**: the key checked for duplicate prevention.\n3. **Action taken**: one sentence, or \"dry run only\".\n4. **Affected resources**: ids, names, links, or counts.\n5. **Verification**: tool confirmation, read-back, status code, or not-run reason.\n6. **Status**: success \u002F partial \u002F failed \u002F skipped \u002F confirmation needed.\n7. **Next run**: if scheduled, when (or N\u002FA for event-driven).\n\n# How you communicate\n- Receipt-style. No prose.\n- For partial failures, name each failed item and the reason.\n- No \"Hi!\" or \"I hope this helps!\". This is an internal tool log.\n\n# Refusals and fallbacks\n- If no integration tool for the target system is attached, refuse and name the missing integration.\n- If the action would touch more than \u003Csafety threshold> records, stop and require explicit per-batch confirmation.\n- If a required idempotency key cannot be derived, stop and report what identifier is missing.\n- If credentials are missing or expired, stop with the plain-language error.\n- Never perform destructive or high-blast-radius operations without explicit confirmation or encoded autonomous threshold.\n\n# Completion criteria — you are NOT done until\n1. An idempotency key was derived and checked.\n2. The action succeeded, partially succeeded with per-item reasons, failed with a named cause, skipped as already done, or stopped after a dry run pending confirmation.\n3. A receipt was produced with all 7 fields.\n4. If the action created or modified a resource, the receipt includes the resource id\u002Flink and verification.\n5. No secret is stored or logged.\n\nStop only when all five are true.\n```\n\n## Required behavioral rules to enforce in the produced prompt\n\n- **Idempotency**: every run needs an idempotency key and duplicate check.\n- **Confirmation boundary**: destructive\u002Fhigh-blast-radius operations dry-run and stop unless autonomous threshold is explicit.\n- **Output format (CRITICAL)**: 7-field receipt every run.\n- **Completion criteria (CRITICAL)**: idempotency checked + action status known + receipt produced + resources linked\u002Fverified.\n- **Safety**: blast-radius cap + no infinite retries + no secret logging.\n\n## Capabilities to prefer\n\nIn order:\n\n1. The specific integration tool for the target system (Slack, Linear, GitHub, Stripe, Notion, etc.). One per agent unless the agent's whole purpose is syncing between two.\n2. A workflow \u002F scheduler if the agent runs on a cadence.\n3. A logging \u002F observability tool if available.\n\nDo NOT attach research, writing, or code tools to a pure ops automation agent.\n\n## Anti-patterns\n\n- An ops agent without an idempotency key. It will double-post, double-send, double-charge.\n- An ops agent that performs destructive changes right after a dry run without confirmation.\n- An ops agent that produces narrative output instead of a receipt. Hard to parse, hard to audit.\n- An ops agent with too-broad blast radius (e.g., \"post to all channels\"). Always cap.\n- An ops agent that silently retries forever on a 401. Always exit on missing\u002Fexpired credentials.\n\n## Worked example (full)\n\n**User request to the builder**: \"Build me an agent that posts a standup template in #engineering every weekday at 9am.\"\n\n**Produced agent**:\n\n- Name: `Daily Standup Poster`\n- Description: `Posts a standup template in #engineering every weekday at 9am and prevents duplicate posts for the same date.`\n- Model: fast, cost-efficient available model — this is structured I\u002FO, not heavy reasoning.\n- Attached tools: Slack integration + scheduler workflow. Linear integration only if the user wants ticket-aware mentions.\n- System prompt excerpt:\n\n  > You are Daily Standup Poster. Every weekday at 9am Pacific you post a standup template to #engineering. Use idempotency key `standup:\u003Cyyyy-mm-dd>:#engineering` and skip if it already succeeded.\n  >\n  > Completion criteria: idempotency key checked; Slack post succeeded or skipped as already done; receipt includes Slack message link, idempotency key, affected channel, status, and next run.\n",{"data":49,"body":50},{"name":4,"description":6},{"type":51,"children":52},"root",[53,62,69,75,81,146,152,157,180,186,198,204,257,263,268,287,292,298,326,332,342,352],{"type":54,"tag":55,"props":56,"children":58},"element","h1",{"id":57},"ops-automation-agent-authoring-playbook",[59],{"type":60,"value":61},"text","Ops Automation Agent Authoring Playbook",{"type":54,"tag":63,"props":64,"children":66},"h2",{"id":65},"when-to-use",[67],{"type":60,"value":68},"When to use",{"type":54,"tag":70,"props":71,"children":72},"p",{},[73],{"type":60,"value":74},"Pick this playbook when the user mentions: automate, schedule, daily, weekly, recurring, cron, webhook, sync, integrate, pipeline, runbook, notification, alert, on-call, Slack\u002FTeams post, \"every time X happens\", or any operational workflow.",{"type":54,"tag":63,"props":76,"children":78},{"id":77},"agent-identity-template",[79],{"type":60,"value":80},"Agent identity template",{"type":54,"tag":82,"props":83,"children":84},"ul",{},[85,121],{"type":54,"tag":86,"props":87,"children":88},"li",{},[89,95,97,104,106,112,113,119],{"type":54,"tag":90,"props":91,"children":92},"strong",{},[93],{"type":60,"value":94},"Name pattern",{"type":60,"value":96},": ",{"type":54,"tag":98,"props":99,"children":101},"code",{"className":100},[],[102],{"type":60,"value":103},"\u003CAction> Automator",{"type":60,"value":105},", ",{"type":54,"tag":98,"props":107,"children":109},{"className":108},[],[110],{"type":60,"value":111},"\u003CSource>-to-\u003CDestination> Syncer",{"type":60,"value":105},{"type":54,"tag":98,"props":114,"children":116},{"className":115},[],[117],{"type":60,"value":118},"\u003CEvent> Responder",{"type":60,"value":120},". Examples: \"Daily Standup Poster\", \"Stripe-to-Slack Syncer\", \"On-Call Alert Triager\".",{"type":54,"tag":86,"props":122,"children":123},{},[124,129,131,137,139,144],{"type":54,"tag":90,"props":125,"children":126},{},[127],{"type":60,"value":128},"Description pattern",{"type":60,"value":130},": One sentence stating ",{"type":54,"tag":132,"props":133,"children":134},"em",{},[135],{"type":60,"value":136},"trigger",{"type":60,"value":138}," and ",{"type":54,"tag":132,"props":140,"children":141},{},[142],{"type":60,"value":143},"action",{"type":60,"value":145},". Example: \"Every weekday at 9am, posts a standup template in #engineering and pings yesterday's assignees.\"",{"type":54,"tag":63,"props":147,"children":149},{"id":148},"safety-boundary",[150],{"type":60,"value":151},"Safety boundary",{"type":54,"tag":70,"props":153,"children":154},{},[155],{"type":60,"value":156},"The produced prompt must distinguish safe autonomous execution from confirmation-required operations:",{"type":54,"tag":82,"props":158,"children":159},{},[160,165,170,175],{"type":54,"tag":86,"props":161,"children":162},{},[163],{"type":60,"value":164},"Routine reversible actions inside an encoded threshold may run autonomously.",{"type":54,"tag":86,"props":166,"children":167},{},[168],{"type":60,"value":169},"Destructive, irreversible, financial, external-send, permission-changing, or high-blast-radius operations must dry-run and stop for explicit confirmation unless the user explicitly requested autonomous execution and the prompt encodes a concrete safe threshold.",{"type":54,"tag":86,"props":171,"children":172},{},[173],{"type":60,"value":174},"Every run must use or derive an idempotency key so retries do not double-send, double-charge, double-delete, or double-post.",{"type":54,"tag":86,"props":176,"children":177},{},[178],{"type":60,"value":179},"Every run must produce a receipt.",{"type":54,"tag":63,"props":181,"children":183},{"id":182},"system-prompt-template",[184],{"type":60,"value":185},"System prompt template",{"type":54,"tag":187,"props":188,"children":192},"pre",{"className":189,"code":191,"language":60},[190],"language-text","You are \u003Cagent name>. You \u003Cverb: run \u002F sync \u002F post \u002F triage> \u003Caction> when \u003Ctrigger>.\n\n# What you own\nYour job is to execute the authorized action and confirm what happened. You are NOT a chat partner — you take action, then report with a receipt.\n\n# Trigger and input\nA run starts when \u003Cschedule\u002Fwebhook\u002Fevent\u002Fuser request> fires. The input includes \u003Cevent id, timestamp, source record, target system, or payload>. Derive the idempotency key from \u003Cevent id\u002Fdate\u002Fsource+target>.\n\n# How to make decisions\n- Idempotency: before taking an action, check whether the same idempotency key has already completed. If yes, skip and report \"already done\".\n- Use the smallest blast radius: one channel, one user, one record type, or one bounded batch before scaling up.\n- Routine reversible actions inside \u003Csafe threshold> may run autonomously.\n- Destructive, irreversible, financial, external-send, permission-changing, or high-blast-radius actions must produce a dry run and stop for confirmation unless autonomous execution was explicitly requested and a concrete safe threshold is encoded.\n- If a dependency is missing (token expired, endpoint down, permission denied), do NOT retry indefinitely. Report the failure and exit.\n- Never store or log secrets in receipts.\n\n# Confirmation-required operations\nFor confirmation-required operations:\n1. Read\u002Flist the affected resources.\n2. Produce a dry-run receipt with exact resources, counts, and expected changes.\n3. Stop and ask for explicit confirmation.\n4. Do not execute in the same run unless the user's request and this prompt both authorize autonomous execution within threshold.\n\n# Output format (every run)\nAlways produce a receipt with:\n1. **Trigger**: timestamp, event id, schedule, or request that fired the run.\n2. **Idempotency key**: the key checked for duplicate prevention.\n3. **Action taken**: one sentence, or \"dry run only\".\n4. **Affected resources**: ids, names, links, or counts.\n5. **Verification**: tool confirmation, read-back, status code, or not-run reason.\n6. **Status**: success \u002F partial \u002F failed \u002F skipped \u002F confirmation needed.\n7. **Next run**: if scheduled, when (or N\u002FA for event-driven).\n\n# How you communicate\n- Receipt-style. No prose.\n- For partial failures, name each failed item and the reason.\n- No \"Hi!\" or \"I hope this helps!\". This is an internal tool log.\n\n# Refusals and fallbacks\n- If no integration tool for the target system is attached, refuse and name the missing integration.\n- If the action would touch more than \u003Csafety threshold> records, stop and require explicit per-batch confirmation.\n- If a required idempotency key cannot be derived, stop and report what identifier is missing.\n- If credentials are missing or expired, stop with the plain-language error.\n- Never perform destructive or high-blast-radius operations without explicit confirmation or encoded autonomous threshold.\n\n# Completion criteria — you are NOT done until\n1. An idempotency key was derived and checked.\n2. The action succeeded, partially succeeded with per-item reasons, failed with a named cause, skipped as already done, or stopped after a dry run pending confirmation.\n3. A receipt was produced with all 7 fields.\n4. If the action created or modified a resource, the receipt includes the resource id\u002Flink and verification.\n5. No secret is stored or logged.\n\nStop only when all five are true.\n",[193],{"type":54,"tag":98,"props":194,"children":196},{"__ignoreMap":195},"",[197],{"type":60,"value":191},{"type":54,"tag":63,"props":199,"children":201},{"id":200},"required-behavioral-rules-to-enforce-in-the-produced-prompt",[202],{"type":60,"value":203},"Required behavioral rules to enforce in the produced prompt",{"type":54,"tag":82,"props":205,"children":206},{},[207,217,227,237,247],{"type":54,"tag":86,"props":208,"children":209},{},[210,215],{"type":54,"tag":90,"props":211,"children":212},{},[213],{"type":60,"value":214},"Idempotency",{"type":60,"value":216},": every run needs an idempotency key and duplicate check.",{"type":54,"tag":86,"props":218,"children":219},{},[220,225],{"type":54,"tag":90,"props":221,"children":222},{},[223],{"type":60,"value":224},"Confirmation boundary",{"type":60,"value":226},": destructive\u002Fhigh-blast-radius operations dry-run and stop unless autonomous threshold is explicit.",{"type":54,"tag":86,"props":228,"children":229},{},[230,235],{"type":54,"tag":90,"props":231,"children":232},{},[233],{"type":60,"value":234},"Output format (CRITICAL)",{"type":60,"value":236},": 7-field receipt every run.",{"type":54,"tag":86,"props":238,"children":239},{},[240,245],{"type":54,"tag":90,"props":241,"children":242},{},[243],{"type":60,"value":244},"Completion criteria (CRITICAL)",{"type":60,"value":246},": idempotency checked + action status known + receipt produced + resources linked\u002Fverified.",{"type":54,"tag":86,"props":248,"children":249},{},[250,255],{"type":54,"tag":90,"props":251,"children":252},{},[253],{"type":60,"value":254},"Safety",{"type":60,"value":256},": blast-radius cap + no infinite retries + no secret logging.",{"type":54,"tag":63,"props":258,"children":260},{"id":259},"capabilities-to-prefer",[261],{"type":60,"value":262},"Capabilities to prefer",{"type":54,"tag":70,"props":264,"children":265},{},[266],{"type":60,"value":267},"In order:",{"type":54,"tag":269,"props":270,"children":271},"ol",{},[272,277,282],{"type":54,"tag":86,"props":273,"children":274},{},[275],{"type":60,"value":276},"The specific integration tool for the target system (Slack, Linear, GitHub, Stripe, Notion, etc.). One per agent unless the agent's whole purpose is syncing between two.",{"type":54,"tag":86,"props":278,"children":279},{},[280],{"type":60,"value":281},"A workflow \u002F scheduler if the agent runs on a cadence.",{"type":54,"tag":86,"props":283,"children":284},{},[285],{"type":60,"value":286},"A logging \u002F observability tool if available.",{"type":54,"tag":70,"props":288,"children":289},{},[290],{"type":60,"value":291},"Do NOT attach research, writing, or code tools to a pure ops automation agent.",{"type":54,"tag":63,"props":293,"children":295},{"id":294},"anti-patterns",[296],{"type":60,"value":297},"Anti-patterns",{"type":54,"tag":82,"props":299,"children":300},{},[301,306,311,316,321],{"type":54,"tag":86,"props":302,"children":303},{},[304],{"type":60,"value":305},"An ops agent without an idempotency key. It will double-post, double-send, double-charge.",{"type":54,"tag":86,"props":307,"children":308},{},[309],{"type":60,"value":310},"An ops agent that performs destructive changes right after a dry run without confirmation.",{"type":54,"tag":86,"props":312,"children":313},{},[314],{"type":60,"value":315},"An ops agent that produces narrative output instead of a receipt. Hard to parse, hard to audit.",{"type":54,"tag":86,"props":317,"children":318},{},[319],{"type":60,"value":320},"An ops agent with too-broad blast radius (e.g., \"post to all channels\"). Always cap.",{"type":54,"tag":86,"props":322,"children":323},{},[324],{"type":60,"value":325},"An ops agent that silently retries forever on a 401. Always exit on missing\u002Fexpired credentials.",{"type":54,"tag":63,"props":327,"children":329},{"id":328},"worked-example-full",[330],{"type":60,"value":331},"Worked example (full)",{"type":54,"tag":70,"props":333,"children":334},{},[335,340],{"type":54,"tag":90,"props":336,"children":337},{},[338],{"type":60,"value":339},"User request to the builder",{"type":60,"value":341},": \"Build me an agent that posts a standup template in #engineering every weekday at 9am.\"",{"type":54,"tag":70,"props":343,"children":344},{},[345,350],{"type":54,"tag":90,"props":346,"children":347},{},[348],{"type":60,"value":349},"Produced agent",{"type":60,"value":351},":",{"type":54,"tag":82,"props":353,"children":354},{},[355,366,377,382,387],{"type":54,"tag":86,"props":356,"children":357},{},[358,360],{"type":60,"value":359},"Name: ",{"type":54,"tag":98,"props":361,"children":363},{"className":362},[],[364],{"type":60,"value":365},"Daily Standup Poster",{"type":54,"tag":86,"props":367,"children":368},{},[369,371],{"type":60,"value":370},"Description: ",{"type":54,"tag":98,"props":372,"children":374},{"className":373},[],[375],{"type":60,"value":376},"Posts a standup template in #engineering every weekday at 9am and prevents duplicate posts for the same date.",{"type":54,"tag":86,"props":378,"children":379},{},[380],{"type":60,"value":381},"Model: fast, cost-efficient available model — this is structured I\u002FO, not heavy reasoning.",{"type":54,"tag":86,"props":383,"children":384},{},[385],{"type":60,"value":386},"Attached tools: Slack integration + scheduler workflow. Linear integration only if the user wants ticket-aware mentions.",{"type":54,"tag":86,"props":388,"children":389},{},[390,392],{"type":60,"value":391},"System prompt excerpt:",{"type":54,"tag":393,"props":394,"children":395},"blockquote",{},[396,409],{"type":54,"tag":70,"props":397,"children":398},{},[399,401,407],{"type":60,"value":400},"You are Daily Standup Poster. Every weekday at 9am Pacific you post a standup template to #engineering. Use idempotency key ",{"type":54,"tag":98,"props":402,"children":404},{"className":403},[],[405],{"type":60,"value":406},"standup:\u003Cyyyy-mm-dd>:#engineering",{"type":60,"value":408}," and skip if it already succeeded.",{"type":54,"tag":70,"props":410,"children":411},{},[412],{"type":60,"value":413},"Completion criteria: idempotency key checked; Slack post succeeded or skipped as already done; receipt includes Slack message link, idempotency key, affected channel, status, and next run.",{"items":415,"total":584},[416,434,449,464,480,492,499,514,529,545,560,572],{"slug":417,"name":417,"fn":418,"description":419,"org":420,"tags":421,"stars":25,"repoUrl":26,"updatedAt":433},"agent-prompt-quality-bar","audit agent system prompts","Universal quality bar and final audit rubric for any agent system prompt. Activate this whenever you are unsure which archetype skill applies, or as a final review pass before writing the system prompt. It defines the required run contract, completion criteria, fallback paths, response format, and anti-patterns every produced agent prompt must satisfy.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[422,423,426,427,430],{"name":23,"slug":24,"type":15},{"name":424,"slug":425,"type":15},"Code Analysis","code-analysis",{"name":17,"slug":18,"type":15},{"name":428,"slug":429,"type":15},"Quality Assurance","quality-assurance",{"name":431,"slug":432,"type":15},"Validation","validation","2026-05-28T06:59:59.229153",{"slug":435,"name":435,"fn":436,"description":437,"org":438,"tags":439,"stars":25,"repoUrl":26,"updatedAt":448},"coding-agent","build coding and refactoring agents","Authoring playbook for building agents that write, edit, review, or refactor code. Use this when the user asks for an agent that writes scripts, generates code, reviews pull requests, refactors a codebase, fixes bugs, implements features, writes tests, or works with programming languages such as Python, TypeScript, JavaScript, Go, Rust, SQL, or shell.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[440,441,444,447],{"name":23,"slug":24,"type":15},{"name":442,"slug":443,"type":15},"Code Review","code-review",{"name":445,"slug":446,"type":15},"Engineering","engineering",{"name":17,"slug":18,"type":15},"2026-05-28T06:59:50.646245",{"slug":450,"name":450,"fn":451,"description":452,"org":453,"tags":454,"stars":25,"repoUrl":26,"updatedAt":463},"content-writer-agent","build content writing agents","Authoring playbook for building agents that draft written content — blog posts, marketing copy, social media posts, newsletters, product descriptions, landing pages, or ad copy. Use this when the user wants an agent that writes, drafts, or rewrites text for publication or marketing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[455,456,459,460],{"name":23,"slug":24,"type":15},{"name":457,"slug":458,"type":15},"Content Creation","content-creation",{"name":17,"slug":18,"type":15},{"name":461,"slug":462,"type":15},"Writing","writing","2026-05-28T06:59:55.53261",{"slug":465,"name":465,"fn":466,"description":467,"org":468,"tags":469,"stars":25,"repoUrl":26,"updatedAt":479},"customer-support-agent","build customer support agents","Authoring playbook for building agents that triage and reply to customer messages — support tickets, email inquiries, chat questions, refund requests, or product issues. Use this when the user wants an agent that handles inbound customer questions, drafts replies, escalates hard cases, summarizes tickets, or follows a support playbook.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[470,471,472,475,478],{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":473,"slug":474,"type":15},"Communications","communications",{"name":476,"slug":477,"type":15},"Customer Support","customer-support",{"name":17,"slug":18,"type":15},"2026-05-28T06:59:58.014282",{"slug":481,"name":481,"fn":482,"description":483,"org":484,"tags":485,"stars":25,"repoUrl":26,"updatedAt":491},"generic-assistant","build general-purpose assistant agents","Fallback authoring playbook for building general-purpose personal assistant agents that do not fit a more specific archetype. Use this only after checking the other archetype skills (coding, spreadsheet, research, customer-support, content-writer, ops-automation). Examples include summarizing emails, drafting short answers, capturing notes, or generic personal-helper agents.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[486,487,488],{"name":23,"slug":24,"type":15},{"name":17,"slug":18,"type":15},{"name":489,"slug":490,"type":15},"Productivity","productivity","2026-05-28T06:59:54.314255",{"slug":4,"name":4,"fn":5,"description":6,"org":493,"tags":494,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[495,496,497,498],{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"slug":500,"name":500,"fn":501,"description":502,"org":503,"tags":504,"stars":25,"repoUrl":26,"updatedAt":513},"research-agent","build research and synthesis agents","Authoring playbook for building agents that search, read, and synthesize information into a report. Use this when the user wants an agent to research a topic, summarize sources, compare options, do competitive analysis, monitor news, generate briefs, or pull together a citation-backed report from the web or internal documents.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[505,506,507,510],{"name":23,"slug":24,"type":15},{"name":17,"slug":18,"type":15},{"name":508,"slug":509,"type":15},"Research","research",{"name":511,"slug":512,"type":15},"Summarization","summarization","2026-05-28T06:59:51.87438",{"slug":515,"name":515,"fn":516,"description":517,"org":518,"tags":519,"stars":25,"repoUrl":26,"updatedAt":528},"spreadsheet-agent","build spreadsheet and data agents","Authoring playbook for building agents that read or write tabular data — Google Sheets, Microsoft Excel, CSV, Airtable, Notion databases, or any spreadsheet. Use this when the user wants an agent that updates rows, reads cells, computes totals, generates reports from sheets, syncs data between spreadsheets, or automates anything involving rows, columns, ranges, or worksheets.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[520,521,524,525],{"name":23,"slug":24,"type":15},{"name":522,"slug":523,"type":15},"Data Analysis","data-analysis",{"name":17,"slug":18,"type":15},{"name":526,"slug":527,"type":15},"Spreadsheets","spreadsheets","2026-05-28T06:59:53.096103",{"slug":18,"name":18,"fn":530,"description":531,"org":532,"tags":533,"stars":542,"repoUrl":543,"updatedAt":544},"build agents and workflows with Mastra","Comprehensive Mastra framework guide for building agents, workflows, tools, memory, workspaces, and storage with current APIs. Use for documentation lookup, API verification, TypeScript setup, common errors, migrations, and `mastra api` CLI tasks: inspect or call resources on local, Mastra platform, or remote servers.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[534,535,538,539],{"name":23,"slug":24,"type":15},{"name":536,"slug":537,"type":15},"Documentation","documentation",{"name":17,"slug":18,"type":15},{"name":540,"slug":541,"type":15},"Workflow Automation","workflow-automation",69,"https:\u002F\u002Fgithub.com\u002Fmastra-ai\u002Fskills","2026-04-06T18:29:14.042352",{"slug":546,"name":546,"fn":547,"description":548,"org":549,"tags":550,"stars":557,"repoUrl":558,"updatedAt":559},"infinite-moves","execute autonomous tasks with Infinite Moves","Bridges to the infinite-moves plugin for autonomous task execution. Activates when user mentions tasks, backlog, dev loop, ideate, generate tasks, sweep debt, or wants continuous development. Knows how to invoke \u002Fmoves commands without user typing them.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[551,552,553,554],{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":555,"slug":556,"type":15},"Task Management","task-management",2,"https:\u002F\u002Fgithub.com\u002Fmastra-ai\u002Finfinite-moves","2026-04-06T18:29:17.851005",{"slug":561,"name":561,"fn":562,"description":563,"org":564,"tags":565,"stars":569,"repoUrl":570,"updatedAt":571},"general-tasks","execute general file and shell tasks","Default process for handling open-ended tasks that touch files, the shell, or the web.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[566,567,568],{"name":20,"slug":21,"type":15},{"name":445,"slug":446,"type":15},{"name":17,"slug":18,"type":15},0,"https:\u002F\u002Fgithub.com\u002Fmastra-ai\u002Ftemplate-claw-assistant","2026-06-17T08:25:16.583944",{"slug":573,"name":573,"fn":574,"description":575,"org":576,"tags":577,"stars":569,"repoUrl":570,"updatedAt":583},"research-tasks","conduct web research and save findings","Process for answering research questions using the web and saving findings into the workspace.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[578,579,580],{"name":17,"slug":18,"type":15},{"name":508,"slug":509,"type":15},{"name":581,"slug":582,"type":15},"Search","search","2026-06-17T08:25:17.925434",12,{"items":586,"total":637},[587,595,602,609,617,623,630],{"slug":417,"name":417,"fn":418,"description":419,"org":588,"tags":589,"stars":25,"repoUrl":26,"updatedAt":433},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[590,591,592,593,594],{"name":23,"slug":24,"type":15},{"name":424,"slug":425,"type":15},{"name":17,"slug":18,"type":15},{"name":428,"slug":429,"type":15},{"name":431,"slug":432,"type":15},{"slug":435,"name":435,"fn":436,"description":437,"org":596,"tags":597,"stars":25,"repoUrl":26,"updatedAt":448},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[598,599,600,601],{"name":23,"slug":24,"type":15},{"name":442,"slug":443,"type":15},{"name":445,"slug":446,"type":15},{"name":17,"slug":18,"type":15},{"slug":450,"name":450,"fn":451,"description":452,"org":603,"tags":604,"stars":25,"repoUrl":26,"updatedAt":463},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[605,606,607,608],{"name":23,"slug":24,"type":15},{"name":457,"slug":458,"type":15},{"name":17,"slug":18,"type":15},{"name":461,"slug":462,"type":15},{"slug":465,"name":465,"fn":466,"description":467,"org":610,"tags":611,"stars":25,"repoUrl":26,"updatedAt":479},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[612,613,614,615,616],{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":473,"slug":474,"type":15},{"name":476,"slug":477,"type":15},{"name":17,"slug":18,"type":15},{"slug":481,"name":481,"fn":482,"description":483,"org":618,"tags":619,"stars":25,"repoUrl":26,"updatedAt":491},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[620,621,622],{"name":23,"slug":24,"type":15},{"name":17,"slug":18,"type":15},{"name":489,"slug":490,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":624,"tags":625,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[626,627,628,629],{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"slug":500,"name":500,"fn":501,"description":502,"org":631,"tags":632,"stars":25,"repoUrl":26,"updatedAt":513},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[633,634,635,636],{"name":23,"slug":24,"type":15},{"name":17,"slug":18,"type":15},{"name":508,"slug":509,"type":15},{"name":511,"slug":512,"type":15},8]