[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EV9CXV5A5CVMSSZF7FPERH":3,"skill-same:01M7EV9CXV5A5CVMSSZF7FPERH":62},{"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":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M7EV9CXV5A5CVMSSZF7FPERH","ax-extract-workflow",null,"Reconstruct workflow behind a past coding-agent artifact using local ax sessions\u002Fcommits\u002Fskills\u002Ftool traces. Use when asked how X was built.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevelopment\u002Fax-extract-workflow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ax-extract-workflow\ndescription: \"Reconstruct workflow behind a past coding-agent artifact using local ax sessions\u002Fcommits\u002Fskills\u002Ftool traces. Use when asked how X was built.\"\ncategory: development\nrisk: safe\nsource: community\nsource_repo: Necmttn\u002Fax\nsource_type: community\ndate_added: \"2026-06-21\"\nauthor: Necmttn\ntags: [ai-coding, workflow-reconstruction, session-analysis, observability]\ntools: [claude, cursor, gemini, codex-cli]\nlicense: \"AGPL-3.0-only\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fax\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# ax Extract Workflow\n\n## Overview\n\nUse this skill to reconstruct the workflow behind a past coding-agent artifact:\na shipped feature, PR, demo, refactor, report, or other concrete result. It uses\nthe local `ax` graph to connect commits, sessions, turns, skills, and tool traces\ninto a short \"how this got made\" narrative.\n\n`ax` must be installed, available on `PATH`, and able to reach its local database.\nIf ax cannot connect to its DB, report the connection failure and stop instead of\nguessing from memory.\n\n## When to Use This Skill\n\n- Use when the user asks \"how did we build X?\", \"what made X work?\", or \"extract the workflow behind this artifact.\"\n- Use when the anchor is a commit SHA, date, feature name, PR, session, or repo-local artifact.\n- Use when the user wants the sequence of agent skills, prompts, commands, decisions, and checks that led to a result.\n- Do not use for a generic activity summary; use normal session listing instead.\n\n## How It Works\n\n### Step 1: Resolve the Anchor\n\nIdentify the best anchor from the user's request:\n\n- Commit SHA: use it directly.\n- Date or date range: inspect sessions around the date.\n- Topic, feature, or artifact name: search recall for related turns, commits, and skills.\n- \"This repo recently\": list recent sessions for the current repo.\n\n```bash\nax recall \"live ingest dashboard\" --sources=turn,commit,skill --scope=here\nax sessions near abc1234 --json\nax sessions around 2026-06-15 --days=3 --json\nax sessions here --days=14\n```\n\nThese commands are read-only inspection commands.\n\n### Step 2: Pick Relevant Sessions\n\nChoose the few sessions most likely to explain the artifact. Prefer sessions\nthat mention the artifact, touch related files, include relevant commits, or have\nskills and tool calls that match the work.\n\nIf several candidates are plausible, show the user the candidates and ask which\none to inspect.\n\n### Step 3: Inspect the Session Trail\n\nOpen each selected session and look for:\n\n- skills used and their order\n- user steering points and clarified constraints\n- files, tests, and commands that changed the direction of the work\n- subagent or tool traces that produced key evidence\n- verification steps before the result was considered done\n\n```bash\nax sessions show \u003Csession-id> --json\nax sessions show \u003Csession-id> --by-role\nax recall \"specific keyword from the artifact\" --sources=turn,commit --scope=here\n```\n\n### Step 4: Write the Reconstruction\n\nReturn the result inline unless the user asks for a file. Keep it short and\nevidence-grounded:\n\n1. Anchor: the date, commit, feature, or artifact you resolved.\n2. Ordered workflow: 4-8 steps showing the skill or action and what it produced.\n3. Key decisions: the user or agent choices that changed the path.\n4. Verification: tests, reviews, checks, or manual evidence.\n5. Reproducer brief: the compact recipe for doing similar work again.\n\nUse session IDs, commit SHAs, and file paths as citations when available.\n\n## Examples\n\n### Reconstruct a Feature from a Commit\n\n```bash\nax sessions near 8f31c2a --json\nax sessions show \u003Csession-id> --by-role\nax sessions show \u003Csession-id> --json\n```\n\nOutput shape:\n\n```text\nAnchor: 8f31c2a, live ingest dashboard\n\nWorkflow:\n1. Problem framing -> narrowed the failure to stale dashboard polling.\n2. Session recall -> found the earlier ingest-stream design and constraints.\n3. Implementation -> wired the server event bus and browser subscription.\n4. Verification -> ran typecheck and refreshed the dashboard locally.\n\nReproducer brief:\nStart from the failing artifact, find nearby sessions, inspect role-grouped\nskills, then summarize the smallest ordered path from framing to verification.\n```\n\n### Reconstruct Work Around a Date\n\n```bash\nax sessions around 2026-06-15 --days=2 --json\nax recall \"otel receiver\" --sources=turn,commit,skill --scope=here\n```\n\nUse this when the user remembers when the work happened but not the commit.\n\n## Best Practices\n\n- Start from the most concrete anchor available: SHA beats date, date beats vague topic.\n- Treat ax as the source of truth; do not invent missing skills, costs, commands, or decisions.\n- Quote sparingly and only when a user decision or command matters to the reconstruction.\n- Keep private transcript details private; summarize rather than dumping logs.\n- Separate \"what happened\" from \"what to repeat next time.\"\n\n## Limitations\n\n- Requires a working local ax installation and reachable local ax database.\n- Only sees sessions, commits, skills, and tool traces that ax has ingested.\n- Session data can be incomplete when an agent provider omits tool output, cost, or reasoning data.\n- It reconstructs workflow, not correctness; still inspect the code and run project checks when making engineering decisions.\n\n## Security & Safety Notes\n\n- Do not upload private transcripts, session logs, prompts, tool outputs, or local database exports.\n- Redact secrets, tokens, customer data, file contents, and private conversation text from summaries.\n- Use read-only ax inspection commands unless the user explicitly asks for a separate maintenance action.\n- Do not run commands that mutate `.ax\u002F`, regenerate indexes, publish reports, or alter repositories as part of reconstruction.\n\n## Related Skills\n\n- `@agenttrace-session-audit` - Use for local agent-session health, cost, latency, and tool-failure audits.\n- `@domain-modeling` - Use when the reconstruction reveals terminology or architectural decisions that should be captured.\n- `@planning-with-files` - Use when the user wants to turn the reconstructed recipe into a new plan with tracked notes.\n","# ax Extract Workflow\n\n## Overview\n\nUse this skill to reconstruct the workflow behind a past coding-agent artifact:\na shipped feature, PR, demo, refactor, report, or other concrete result. It uses\nthe local `ax` graph to connect commits, sessions, turns, skills, and tool traces\ninto a short \"how this got made\" narrative.\n\n`ax` must be installed, available on `PATH`, and able to reach its local database.\nIf ax cannot connect to its DB, report the connection failure and stop instead of\nguessing from memory.\n\n## When to Use This Skill\n\n- Use when the user asks \"how did we build X?\", \"what made X work?\", or \"extract the workflow behind this artifact.\"\n- Use when the anchor is a commit SHA, date, feature name, PR, session, or repo-local artifact.\n- Use when the user wants the sequence of agent skills, prompts, commands, decisions, and checks that led to a result.\n- Do not use for a generic activity summary; use normal session listing instead.\n\n## How It Works\n\n### Step 1: Resolve the Anchor\n\nIdentify the best anchor from the user's request:\n\n- Commit SHA: use it directly.\n- Date or date range: inspect sessions around the date.\n- Topic, feature, or artifact name: search recall for related turns, commits, and skills.\n- \"This repo recently\": list recent sessions for the current repo.\n\n```bash\nax recall \"live ingest dashboard\" --sources=turn,commit,skill --scope=here\nax sessions near abc1234 --json\nax sessions around 2026-06-15 --days=3 --json\nax sessions here --days=14\n```\n\nThese commands are read-only inspection commands.\n\n### Step 2: Pick Relevant Sessions\n\nChoose the few sessions most likely to explain the artifact. Prefer sessions\nthat mention the artifact, touch related files, include relevant commits, or have\nskills and tool calls that match the work.\n\nIf several candidates are plausible, show the user the candidates and ask which\none to inspect.\n\n### Step 3: Inspect the Session Trail\n\nOpen each selected session and look for:\n\n- skills used and their order\n- user steering points and clarified constraints\n- files, tests, and commands that changed the direction of the work\n- subagent or tool traces that produced key evidence\n- verification steps before the result was considered done\n\n```bash\nax sessions show \u003Csession-id> --json\nax sessions show \u003Csession-id> --by-role\nax recall \"specific keyword from the artifact\" --sources=turn,commit --scope=here\n```\n\n### Step 4: Write the Reconstruction\n\nReturn the result inline unless the user asks for a file. Keep it short and\nevidence-grounded:\n\n1. Anchor: the date, commit, feature, or artifact you resolved.\n2. Ordered workflow: 4-8 steps showing the skill or action and what it produced.\n3. Key decisions: the user or agent choices that changed the path.\n4. Verification: tests, reviews, checks, or manual evidence.\n5. Reproducer brief: the compact recipe for doing similar work again.\n\nUse session IDs, commit SHAs, and file paths as citations when available.\n\n## Examples\n\n### Reconstruct a Feature from a Commit\n\n```bash\nax sessions near 8f31c2a --json\nax sessions show \u003Csession-id> --by-role\nax sessions show \u003Csession-id> --json\n```\n\nOutput shape:\n\n```text\nAnchor: 8f31c2a, live ingest dashboard\n\nWorkflow:\n1. Problem framing -> narrowed the failure to stale dashboard polling.\n2. Session recall -> found the earlier ingest-stream design and constraints.\n3. Implementation -> wired the server event bus and browser subscription.\n4. Verification -> ran typecheck and refreshed the dashboard locally.\n\nReproducer brief:\nStart from the failing artifact, find nearby sessions, inspect role-grouped\nskills, then summarize the smallest ordered path from framing to verification.\n```\n\n### Reconstruct Work Around a Date\n\n```bash\nax sessions around 2026-06-15 --days=2 --json\nax recall \"otel receiver\" --sources=turn,commit,skill --scope=here\n```\n\nUse this when the user remembers when the work happened but not the commit.\n\n## Best Practices\n\n- Start from the most concrete anchor available: SHA beats date, date beats vague topic.\n- Treat ax as the source of truth; do not invent missing skills, costs, commands, or decisions.\n- Quote sparingly and only when a user decision or command matters to the reconstruction.\n- Keep private transcript details private; summarize rather than dumping logs.\n- Separate \"what happened\" from \"what to repeat next time.\"\n\n## Limitations\n\n- Requires a working local ax installation and reachable local ax database.\n- Only sees sessions, commits, skills, and tool traces that ax has ingested.\n- Session data can be incomplete when an agent provider omits tool output, cost, or reasoning data.\n- It reconstructs workflow, not correctness; still inspect the code and run project checks when making engineering decisions.\n\n## Security & Safety Notes\n\n- Do not upload private transcripts, session logs, prompts, tool outputs, or local database exports.\n- Redact secrets, tokens, customer data, file contents, and private conversation text from summaries.\n- Use read-only ax inspection commands unless the user explicitly asks for a separate maintenance action.\n- Do not run commands that mutate `.ax\u002F`, regenerate indexes, publish reports, or alter repositories as part of reconstruction.\n\n## Related Skills\n\n- `@agenttrace-session-audit` - Use for local agent-session health, cost, latency, and tool-failure audits.\n- `@domain-modeling` - Use when the reconstruction reveals terminology or architectural decisions that should be captured.\n- `@planning-with-files` - Use when the user wants to turn the reconstructed recipe into a new plan with tracked notes.\n",{"name":5,"risk":24,"tags":25,"tools":30,"author":35,"source":36,"license":37,"category":38,"date_added":39,"description":7,"source_repo":40,"source_type":36,"license_source":41},"safe",[26,27,28,29],"ai-coding","workflow-reconstruction","session-analysis","observability",[31,32,33,34],"claude","cursor","gemini","codex-cli","Necmttn","community","AGPL-3.0-only","development","2026-06-21","Necmttn\u002Fax","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fax\u002Fblob\u002Fmain\u002FLICENSE","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fdevelopment\u002Fax-extract-workflow","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill ax-extract-workflow",{"tool":54,"command":55},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill ax-extract-workflow",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill ax-extract-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevelopment\u002Fax-extract-workflow\u002FSKILL.md",true,[],[63,72,79,86,93,100],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":71},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":71},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":71},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":71},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":71},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":71},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]