[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AHASPNN7PR3XS13CS0Y9DP":3,"skill-same:01M7AHASPNN7PR3XS13CS0Y9DP":46},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7AHASPNN7PR3XS13CS0Y9DP","auto-phase",null,"Autonomous multi-phase release execution. Reads a PHASE-PLAN.md with stages 1-N and executes them end-to-end, running focused checks per stage and one integrated validation pass. Keeps independent final review for risky aggregate changes, committing with clean scope, and advancing automatically. Halts only when a validation gate fails twice or a critique surfaces an unresolvable issue. Use for multi-stage release plans, phased restructures, or any numbered-phase execution. NOT for single-stage work (use \u002Fship), plan creation (use brainstorming), or work without a written phase plan. Use when you have a numbered-phase plan ready for execution.","SamyakJhaveri\u002Floam","SamyakJhaveri","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39847642?v=4","01M7AH87180VZDSRHE20JD1S32","Samyak Jhaveri","01M7AH871WNGEHDVNXJM2B520R",0,"MIT","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fcultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fauto-phase\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: auto-phase\ndisable-model-invocation: true\ndescription: >\n  Autonomous multi-phase release execution. Reads a PHASE-PLAN.md with stages 1-N\n  and executes them end-to-end, running focused checks per stage and one integrated\n  validation pass. Keeps independent final review for risky aggregate changes, committing\n  with clean scope, and advancing automatically. Halts only when a validation gate\n  fails twice or a critique surfaces an unresolvable issue. Use for multi-stage\n  release plans, phased restructures, or any numbered-phase execution. NOT for\n  single-stage work (use \u002Fship), plan creation (use brainstorming), or work without\n  a written phase plan. Use when you have a numbered-phase plan ready for execution.\nargument-hint: \"[path to phase plan, defaults to PHASE-PLAN.md]\"\n---\n\n# Auto-Phase: Autonomous Multi-Stage Execution\n\nReads a phase plan and executes stages autonomously. Each stage gets focused evidence.\nOne owner validates the integrated source fingerprint.\n\n**Requires the `ship` and `session-critique` skills** (plus `validate`, which\n`ship` also depends on). If they are not installed, stop and say so rather than\nimprovising the gates.\n\n## When to Use\n\n- You have a PHASE-PLAN.md (or similar) with numbered stages 1-N\n- Each stage is self-contained and can be validated independently\n- You want autonomous execution with human oversight only on failures\n\n## When NOT to Use\n\n- Single-stage work -> use `\u002Fship`\n- No written phase plan exists -> write one first (use brainstorming + writing-plans)\n- Exploratory or uncertain work -> plan first, then auto-phase\n\n## Prerequisites\n\n1. A phase plan file exists (default: `PHASE-PLAN.md` in project root)\n2. Each stage in the plan specifies: what to implement, expected output, done criteria\n3. The project has `\u002Fvalidate` and `\u002Fsession-critique` available\n\n## Procedure\n\n### Step 1: Read and parse the phase plan\n\n```bash\nPLAN_FILE=\"${ARGUMENTS:-PHASE-PLAN.md}\"\n[ -f \"$PLAN_FILE\" ] && echo \"Plan found: $PLAN_FILE\" || echo \"ERROR: $PLAN_FILE not found\"\n```\n\nParse the plan to identify:\n- Total number of stages\n- Each stage's scope, files, and done criteria\n- Dependencies between stages (if any)\n\nPresent the parsed stage list to the user for confirmation before starting.\n\n### Step 2: Execute stages autonomously\n\nFor each stage (1 through N):\n\n#### 2a. Announce stage start\n\n```\n=== STAGE K\u002FN: [Stage Title] ===\nStatus: STARTING\n```\n\n#### 2b. Implement the stage's changes\n\nFollow the stage's instructions from the plan. Make the code changes, create\nfiles, modify configurations, whatever the stage specifies.\n\n#### 2c. Run focused stage checks\n\nRun only the checks that cover this stage's changed behavior. Record the exact command,\nexit code, and summary in `TASKS.md`. Do not run the full project gate here unless this is\nthe final integrated stage.\n\nIf a focused check fails:\n\n- **First failure:** Fix the issue and re-run the focused check.\n- **Second failure on same stage:** HALT. Report the failure and ask the user.\n\n```\n=== STAGE K\u002FN: VALIDATION FAILED (attempt 2\u002F2) ===\nFailure: [description]\nAction: Halting for user input. The stage contract may need revision.\n```\n\n#### 2d. Record review risk\n\nRecord whether the stage affects security, a trust boundary, architecture, or several\nsubsystems. Do not run a per-stage generic critique when the final aggregate reviewer will\ninspect the same work.\n\n#### 2e. Commit with clean scope\n\nCommit inline with git. The commit must contain ONLY this stage's changes.\nNever bundle changes from other stages.\n\n```bash\ngit status --short\ngit add \u003Cthis stage's paths>\ngit commit -m \"\u003Ctype>: \u003Cstage K subject>\"\ngit rev-parse --short HEAD\n```\n\nBefore commit, use `\u002Fvalidate` for the exact stage fingerprint when the repository requires\na validated receipt for every commit. Reuse a valid receipt. If the content changed, run\nvalidation before the commit rather than probing with a failed commit attempt.\n\n#### 2f. Update progress tracking\n\nAfter successful commit, update `TASKS.md` (create if it doesn't exist):\n\n```markdown\n## Auto-Phase Progress\n\n| Stage | Status | Commit | Notes |\n|-------|--------|--------|-------|\n| 1 | DONE | abc1234 | [summary] |\n| 2 | DONE | def5678 | [summary] |\n| 3 | IN PROGRESS | - | - |\n```\n\n#### 2g. Advance to next stage\n\n```\n=== STAGE K\u002FN: COMPLETE ===\nCommit: [hash]\nAdvancing to Stage K+1...\n```\n\n### Step 3: Integrated validation and review\n\nThe validation owner invokes `\u002Fvalidate` once for the final integrated fingerprint. Reuse\nan existing receipt only when `validation.py check` accepts it.\n\nIf any stage recorded review risk, invoke `\u002Fsession-critique` once over the fixed aggregate\ndiff. Reuse a durable review for the same fingerprint. A fix lands as its own follow-up\ncommit. Repeat review only after material behavior changes or for a named unresolved risk.\n\n### Step 4: Completion report\n\nAfter all stages complete:\n\n```\n=== AUTO-PHASE COMPLETE ===\nPlan: [plan file]\nStages: N\u002FN completed\nCommits: [list of hashes]\nTotal changes: [file count summary]\n\nAll stages passed validation; the end-of-plan critique ran.\n```\n\n## Stopping Conditions\n\n| Condition | Action |\n|-----------|--------|\n| Validation fails twice on same stage | HALT, ask user, stage contract likely needs revision |\n| Critique finds unresolvable issue | HALT, present issue and ask user |\n| Plan file not found | HALT, report error immediately |\n| Stage instructions are ambiguous | HALT, ask user to clarify before implementing |\n| All stages complete | Report summary, pipeline done |\n\n## Hard Rules\n\n1. **One stage at a time.** Never start stage K+1 before stage K is committed.\n2. **Never bundle cross-stage changes.** Each commit contains exactly one stage.\n3. **Never skip focused checks or integrated validation.** Keep one independent final\n   review when the aggregate change meets the risk conditions in Step 3.\n4. **Halt on ambiguity.** If a stage's instructions are unclear, ask, don't guess.\n5. **Track progress.** Update TASKS.md after every stage so a fresh session can resume.\n","# Auto-Phase: Autonomous Multi-Stage Execution\n\nReads a phase plan and executes stages autonomously. Each stage gets focused evidence.\nOne owner validates the integrated source fingerprint.\n\n**Requires the `ship` and `session-critique` skills** (plus `validate`, which\n`ship` also depends on). If they are not installed, stop and say so rather than\nimprovising the gates.\n\n## When to Use\n\n- You have a PHASE-PLAN.md (or similar) with numbered stages 1-N\n- Each stage is self-contained and can be validated independently\n- You want autonomous execution with human oversight only on failures\n\n## When NOT to Use\n\n- Single-stage work -> use `\u002Fship`\n- No written phase plan exists -> write one first (use brainstorming + writing-plans)\n- Exploratory or uncertain work -> plan first, then auto-phase\n\n## Prerequisites\n\n1. A phase plan file exists (default: `PHASE-PLAN.md` in project root)\n2. Each stage in the plan specifies: what to implement, expected output, done criteria\n3. The project has `\u002Fvalidate` and `\u002Fsession-critique` available\n\n## Procedure\n\n### Step 1: Read and parse the phase plan\n\n```bash\nPLAN_FILE=\"${ARGUMENTS:-PHASE-PLAN.md}\"\n[ -f \"$PLAN_FILE\" ] && echo \"Plan found: $PLAN_FILE\" || echo \"ERROR: $PLAN_FILE not found\"\n```\n\nParse the plan to identify:\n- Total number of stages\n- Each stage's scope, files, and done criteria\n- Dependencies between stages (if any)\n\nPresent the parsed stage list to the user for confirmation before starting.\n\n### Step 2: Execute stages autonomously\n\nFor each stage (1 through N):\n\n#### 2a. Announce stage start\n\n```\n=== STAGE K\u002FN: [Stage Title] ===\nStatus: STARTING\n```\n\n#### 2b. Implement the stage's changes\n\nFollow the stage's instructions from the plan. Make the code changes, create\nfiles, modify configurations, whatever the stage specifies.\n\n#### 2c. Run focused stage checks\n\nRun only the checks that cover this stage's changed behavior. Record the exact command,\nexit code, and summary in `TASKS.md`. Do not run the full project gate here unless this is\nthe final integrated stage.\n\nIf a focused check fails:\n\n- **First failure:** Fix the issue and re-run the focused check.\n- **Second failure on same stage:** HALT. Report the failure and ask the user.\n\n```\n=== STAGE K\u002FN: VALIDATION FAILED (attempt 2\u002F2) ===\nFailure: [description]\nAction: Halting for user input. The stage contract may need revision.\n```\n\n#### 2d. Record review risk\n\nRecord whether the stage affects security, a trust boundary, architecture, or several\nsubsystems. Do not run a per-stage generic critique when the final aggregate reviewer will\ninspect the same work.\n\n#### 2e. Commit with clean scope\n\nCommit inline with git. The commit must contain ONLY this stage's changes.\nNever bundle changes from other stages.\n\n```bash\ngit status --short\ngit add \u003Cthis stage's paths>\ngit commit -m \"\u003Ctype>: \u003Cstage K subject>\"\ngit rev-parse --short HEAD\n```\n\nBefore commit, use `\u002Fvalidate` for the exact stage fingerprint when the repository requires\na validated receipt for every commit. Reuse a valid receipt. If the content changed, run\nvalidation before the commit rather than probing with a failed commit attempt.\n\n#### 2f. Update progress tracking\n\nAfter successful commit, update `TASKS.md` (create if it doesn't exist):\n\n```markdown\n## Auto-Phase Progress\n\n| Stage | Status | Commit | Notes |\n|-------|--------|--------|-------|\n| 1 | DONE | abc1234 | [summary] |\n| 2 | DONE | def5678 | [summary] |\n| 3 | IN PROGRESS | - | - |\n```\n\n#### 2g. Advance to next stage\n\n```\n=== STAGE K\u002FN: COMPLETE ===\nCommit: [hash]\nAdvancing to Stage K+1...\n```\n\n### Step 3: Integrated validation and review\n\nThe validation owner invokes `\u002Fvalidate` once for the final integrated fingerprint. Reuse\nan existing receipt only when `validation.py check` accepts it.\n\nIf any stage recorded review risk, invoke `\u002Fsession-critique` once over the fixed aggregate\ndiff. Reuse a durable review for the same fingerprint. A fix lands as its own follow-up\ncommit. Repeat review only after material behavior changes or for a named unresolved risk.\n\n### Step 4: Completion report\n\nAfter all stages complete:\n\n```\n=== AUTO-PHASE COMPLETE ===\nPlan: [plan file]\nStages: N\u002FN completed\nCommits: [list of hashes]\nTotal changes: [file count summary]\n\nAll stages passed validation; the end-of-plan critique ran.\n```\n\n## Stopping Conditions\n\n| Condition | Action |\n|-----------|--------|\n| Validation fails twice on same stage | HALT, ask user, stage contract likely needs revision |\n| Critique finds unresolvable issue | HALT, present issue and ask user |\n| Plan file not found | HALT, report error immediately |\n| Stage instructions are ambiguous | HALT, ask user to clarify before implementing |\n| All stages complete | Report summary, pipeline done |\n\n## Hard Rules\n\n1. **One stage at a time.** Never start stage K+1 before stage K is committed.\n2. **Never bundle cross-stage changes.** Each commit contains exactly one stage.\n3. **Never skip focused checks or integrated validation.** Keep one independent final\n   review when the aggregate change meets the risk conditions in Step 3.\n4. **Halt on ambiguity.** If a stage's instructions are unclear, ask, don't guess.\n5. **Track progress.** Update TASKS.md after every stage so a fresh session can resume.\n",{"name":5,"description":24,"argument-hint":25,"disable-model-invocation":26},"Autonomous multi-phase release execution. Reads a PHASE-PLAN.md with stages 1-N and executes them end-to-end, running focused checks per stage and one integrated validation pass. Keeps independent final review for risky aggregate changes, committing with clean scope, and advancing automatically. Halts only when a validation gate fails twice or a critique surfaces an unresolvable issue. Use for multi-stage release plans, phased restructures, or any numbered-phase execution. NOT for single-stage work (use \u002Fship), plan creation (use brainstorming), or work without a written phase plan. Use when you have a numbered-phase plan ready for execution.\n","[path to phase plan, defaults to PHASE-PLAN.md]",true,"main","85a41de587b98bb440cccf78f081a6bee67fe90e","cultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fauto-phase","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri","2026-11-15 04:06:30",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":26},[35,38,41],{"tool":36,"command":37},"npx","npx skills add SamyakJhaveri\u002Floam --skill auto-phase",{"tool":39,"command":40},"bunx","bunx skills add SamyakJhaveri\u002Floam --skill auto-phase",{"tool":42,"command":43},"pnpm","pnpm dlx skills add SamyakJhaveri\u002Floam --skill auto-phase","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fcultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fauto-phase\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7AHGVPTGK3JGQ9XYG5XJ6PR","verify-loam","Prove a Loam change in a real rendered project: copier-render this checkout, then drive headless and interactive Claude Code sessions, stubbed Codex runs and copier updates in the render and capture hook, memory, deny-rule, update and check evidence. Use before shipping any seed, hook, settings or copier.yml change.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.claude\u002Fskills\u002Fverify-loam\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7AHGEDXX7GWJ32S9BZAEWAJ","hypothesis-tree","Persistent hypothesis tree for multi-step, multi-session investigations. Use when a \"why does X fail\" question branches into sub-hypotheses that must survive across sessions, or when falsifiable claims need tracking with dated, linked evidence. Maintains one markdown file with add, update, review, and prune subcommands, each gated on verifying the cited evidence file exists and supports the claim. NOT for a single-session bug hunt, a one-command question, or general note-taking.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Fhypothesis-tree\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7AHGADA1CX9M0B0QSFJYGW5","fable-prompting","Which Claude Fable 5.2 guide sections you can act on from a session, and which Claude Code already injects. Use before writing a Fable session prompt or brief.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Ffable-prompting\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7AHG7AGBSQ6HH04C70TSM8H","catchup","Read-only session bootstrap briefing of git state, commits, handoff, tasks and red flags. Use when resuming work, starting a fresh session, or unsure of project state.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Fcatchup\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AHG52XX2N7AT7JNHS6MN1S","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Farchitecture-working\u002Ftooling\u002Fmattpocock-skills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AHG00SXGAGJA7C6XA193J6","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Farchitecture-working\u002Ftooling\u002Fmattpocock-skills\u002Fwizard\u002FSKILL.md",[],[]]