[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FEB8GTJC6ZHDK67T40R20":3,"skill-same:01M79FEB8GTJC6ZHDK67T40R20":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M79FEB8GTJC6ZHDK67T40R20","workflow-from-chats",null,"Extract preferences from agent chats → skills, rules, workflow docs. For learning preferences, mining feedback, personalizing workflows.","BumpyClock\u002Fagent-templates","BumpyClock","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1883824?v=4","01M79EW0FDP9MFXH1FKH800S7T","Aditya Sharma","01M79EW0G27TTKZWTFQ8W5HVB4",2,"MIT","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fworkflow-from-chats\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: workflow-from-chats\ndescription: \"Extract preferences from agent chats → skills, rules, workflow docs. For learning preferences, mining feedback, personalizing workflows.\"\nsource: https:\u002F\u002Fgithub.com\u002Fshaneholloman\u002Fcursor-plugins\u002Ftree\u002Fmain\u002Fcursor-team-kit\u002Fskills\u002Fworkflow-from-chats\nlicense: MIT\ndisable-model-invocation: true\n---\n\n# Workflow From Chats\n\nInfer durable working preferences and repeated manual workflows from recent work. Do not summarize chats; extract reusable workflow guidance. Create only high-confidence missing assets.\n\n## Scope\n\n- Default: last 30 days unless user specifies different window. If less history available, use all.\n- Use local transcript sources available to current agent runtime. If location unclear, search local agent\u002Fsession directories before asking.\n- Read parent conversations first. Subagent content = supporting evidence; cite only parent conversations or user-visible summaries.\n- Do not expose local transcript paths, secrets, customer data, private chat content, credentials, or unrelated personal details.\n- Scan chats from `~\u002F.codex`, `~\u002F.pi\u002F`, `~\u002F.claude` and `~\u002F.copilot` unless user specifies a single agent.\n- Look broadly across coding, research, writing, planning, communication, operations, analysis, personal administration.\n\n## Evidence Order\n\n1. Recent Codex sessions and task summaries.\n2. Codex Memories and rollout summaries for cross-session repeated patterns.\n3. Chronicle (if enabled) for discovery outside Codex. Confirm important details in relevant source system.\n4. Existing skills, custom agents, automations — new work reuses\u002Fextends what already exists.\n\n## Workflow\n\n1. State target workflow or preference surface in one paragraph.\n2. Build internal inventory: topic, approximate date, completion state, related subagents, why it may contain preference evidence.\n3. Scan for explicit preferences, corrections, workflow markers: \"I prefer\", \"always\", \"never\", \"not what I asked\", \"stop\", \"review\", \"PR\", \"CI\", \"logs\", \"skill\", etc.\n4. Extract preference atoms and workflow candidates: trigger, inputs, workflow steps, decision rules, quality bar, output, stop condition, evidence, confidence.\n5. Rate confidence: strong, medium, weak, contradicted.\n6. Cluster by workflow shape: shipping, review, simplification, debugging, capture, communication, delegation, validation, planning, operations, research, analysis, writing, git hygiene.\n7. Check each candidate against existing skills, custom agents, docs, scripts, cron jobs, launch agents, other automations before recommending new asset.\n8. Produce compact shortlist before writing files.\n9. Choose artifact: new skill, skill edit, custom subagent, automation, rule, workflow doc, learned doc, or no artifact.\n10. Create\u002Fextend only high-confidence missing items. Narrow, practical, source-aware, easy to validate.\n11. Draft reusable guidance only. Drop anecdotes that won't help future tasks.\n\n## Candidate Gate\n\nAct on a candidate only when:\n- occurred ≥2 times, or clearly likely to recur and costly to repeat;\n- has stable inputs, repeatable procedure, clear output\u002Fstopping condition;\n- would materially improve speed, quality, consistency, or reliability;\n- not already adequately covered.\n\nSkip one-off, ambiguous, sensitive, poorly evidenced, speculative, overlapping, or overly broad work.\n\n## Confidence\n\n- Strong: explicit user preference, workflow-changing correction, repeated parent-chat pattern, or direct request to encode behavior.\n- Medium: accepted workflow, repeated tool\u002Fmodel\u002Fvalidation preference, or subagent consensus parent used successfully.\n- Weak: agent-chosen behavior with no user feedback, one ambiguous transcript, or likely task-specific correction.\n- Contradicted: evidence points incompatible directions; ask user before writing files.\n\n## Artifact Choice\n\n- Skill: recurring multi-step workflow\u002Fplaybook with clear triggers.\n- Custom subagent: bounded specialist role or investigation task suitable for delegation.\n- Automation: scheduled\u002Frecurring check, report, reminder, or monitor.\n- Extend existing: adequate asset exists but needs narrow improvement.\n- Rule: broad behavior applying across tasks.\n- Learned doc: repo-specific rationale, pitfalls, failure modes, architecture decision.\n- Workflow doc: useful context not reliably triggerable.\n- No artifact: situational, stale, low-confidence, or privacy-sensitive observation.\n\n## Output\n\nConcise synthesis:\n- Target workflow.\n- Evidence corpus (cite parent conversation summaries only).\n- Preference profile.\n- Adopt, consider, dismissed.\n- Proposed artifacts.\n- Compact shortlist: repeated workflow, supporting evidence + dates, frequency\u002Fconfidence, recommended form, why worth\u002Fnot worth creating.\n- Created or extended.\n- Deliberately skipped.\n- Needs more evidence before packaging.\n- Open questions only if they block writing.\n","# Workflow From Chats\n\nInfer durable working preferences and repeated manual workflows from recent work. Do not summarize chats; extract reusable workflow guidance. Create only high-confidence missing assets.\n\n## Scope\n\n- Default: last 30 days unless user specifies different window. If less history available, use all.\n- Use local transcript sources available to current agent runtime. If location unclear, search local agent\u002Fsession directories before asking.\n- Read parent conversations first. Subagent content = supporting evidence; cite only parent conversations or user-visible summaries.\n- Do not expose local transcript paths, secrets, customer data, private chat content, credentials, or unrelated personal details.\n- Scan chats from `~\u002F.codex`, `~\u002F.pi\u002F`, `~\u002F.claude` and `~\u002F.copilot` unless user specifies a single agent.\n- Look broadly across coding, research, writing, planning, communication, operations, analysis, personal administration.\n\n## Evidence Order\n\n1. Recent Codex sessions and task summaries.\n2. Codex Memories and rollout summaries for cross-session repeated patterns.\n3. Chronicle (if enabled) for discovery outside Codex. Confirm important details in relevant source system.\n4. Existing skills, custom agents, automations — new work reuses\u002Fextends what already exists.\n\n## Workflow\n\n1. State target workflow or preference surface in one paragraph.\n2. Build internal inventory: topic, approximate date, completion state, related subagents, why it may contain preference evidence.\n3. Scan for explicit preferences, corrections, workflow markers: \"I prefer\", \"always\", \"never\", \"not what I asked\", \"stop\", \"review\", \"PR\", \"CI\", \"logs\", \"skill\", etc.\n4. Extract preference atoms and workflow candidates: trigger, inputs, workflow steps, decision rules, quality bar, output, stop condition, evidence, confidence.\n5. Rate confidence: strong, medium, weak, contradicted.\n6. Cluster by workflow shape: shipping, review, simplification, debugging, capture, communication, delegation, validation, planning, operations, research, analysis, writing, git hygiene.\n7. Check each candidate against existing skills, custom agents, docs, scripts, cron jobs, launch agents, other automations before recommending new asset.\n8. Produce compact shortlist before writing files.\n9. Choose artifact: new skill, skill edit, custom subagent, automation, rule, workflow doc, learned doc, or no artifact.\n10. Create\u002Fextend only high-confidence missing items. Narrow, practical, source-aware, easy to validate.\n11. Draft reusable guidance only. Drop anecdotes that won't help future tasks.\n\n## Candidate Gate\n\nAct on a candidate only when:\n- occurred ≥2 times, or clearly likely to recur and costly to repeat;\n- has stable inputs, repeatable procedure, clear output\u002Fstopping condition;\n- would materially improve speed, quality, consistency, or reliability;\n- not already adequately covered.\n\nSkip one-off, ambiguous, sensitive, poorly evidenced, speculative, overlapping, or overly broad work.\n\n## Confidence\n\n- Strong: explicit user preference, workflow-changing correction, repeated parent-chat pattern, or direct request to encode behavior.\n- Medium: accepted workflow, repeated tool\u002Fmodel\u002Fvalidation preference, or subagent consensus parent used successfully.\n- Weak: agent-chosen behavior with no user feedback, one ambiguous transcript, or likely task-specific correction.\n- Contradicted: evidence points incompatible directions; ask user before writing files.\n\n## Artifact Choice\n\n- Skill: recurring multi-step workflow\u002Fplaybook with clear triggers.\n- Custom subagent: bounded specialist role or investigation task suitable for delegation.\n- Automation: scheduled\u002Frecurring check, report, reminder, or monitor.\n- Extend existing: adequate asset exists but needs narrow improvement.\n- Rule: broad behavior applying across tasks.\n- Learned doc: repo-specific rationale, pitfalls, failure modes, architecture decision.\n- Workflow doc: useful context not reliably triggerable.\n- No artifact: situational, stale, low-confidence, or privacy-sensitive observation.\n\n## Output\n\nConcise synthesis:\n- Target workflow.\n- Evidence corpus (cite parent conversation summaries only).\n- Preference profile.\n- Adopt, consider, dismissed.\n- Proposed artifacts.\n- Compact shortlist: repeated workflow, supporting evidence + dates, frequency\u002Fconfidence, recommended form, why worth\u002Fnot worth creating.\n- Created or extended.\n- Deliberately skipped.\n- Needs more evidence before packaging.\n- Open questions only if they block writing.\n",{"name":5,"source":24,"license":15,"description":7,"disable-model-invocation":25},"https:\u002F\u002Fgithub.com\u002Fshaneholloman\u002Fcursor-plugins\u002Ftree\u002Fmain\u002Fcursor-team-kit\u002Fskills\u002Fworkflow-from-chats",true,"main","e24b64bdac040ad169ed16b14853eff1b20cd726","skills_archive\u002Fworkflow-from-chats",0,"https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates","https:\u002F\u002Fgithub.com\u002FBumpyClock","2026-11-14 03:12:06",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add BumpyClock\u002Fagent-templates --skill workflow-from-chats",{"tool":39,"command":40},"bunx","bunx skills add BumpyClock\u002Fagent-templates --skill workflow-from-chats",{"tool":42,"command":43},"pnpm","pnpm dlx skills add BumpyClock\u002Fagent-templates --skill workflow-from-chats","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fworkflow-from-chats\u002FSKILL.md",[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",331,"https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fworkflow-from-chats\u002Fagents\u002Fopenai.yaml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79FEE6E257MWVEBY43X0NVN","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79FE7TMNGVZZ0M8NV4N0X6N","winui3-csharp-app","WinUI 3 \u002F Windows App SDK desktop apps in C#\u002FXAML. MVVM, bindings, navigation, Mica\u002FAcrylic, windowing, packaging, performance.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwinui3-csharp-app\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79FE31HY46BHN67CQGB7MVJ","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79FE0N7MGWDG8SCD60FWTV5","what-did-i-get-done","Summarize authored commits over a user-specified time period into a concise status update.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwhat-did-i-get-done\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79FDYBJG9QNCQC0MMVBDT80","weekly-review","Produce a short weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fweekly-review\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79FDPNS485H1SB2Z848H9H3","web-animation-design","Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use, animation best practices, or accessibility considerations for motion. Triggers on: easing, ease-out, ease-in, ease-in-out, cubic-bezier, bounce, spring physics, keyframes, transform, opacity, fade, slide, scale, hover effects, microinteractions, Framer Motion, React Spring, GSAP, CSS transitions, entrance\u002Fexit animations, page transitions, stagger, will-change, GPU acceleration, prefers-reduced-motion, modal\u002Fdropdown\u002Ftooltip\u002Fpopover\u002Fdrawer animations, gesture animations, drag interactions, button press feel, feels janky, make it smooth.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fweb-skills\u002Fweb-animation-design\u002FSKILL.md",[],[]]