[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77K3FGSMAX2S0ECQ48CQWQE":3,"skill-same:01M77K3FGSMAX2S0ECQ48CQWQE":54},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M77K3FGSMAX2S0ECQ48CQWQE","triage",null,"Classify work into Quick, Standard, or Full tiers from deterministic signals. Use when routing new work or re-scoring scope mid-flight. Does not run the doc pipeline or implementation phases.","grdavies\u002Fshipwright","grdavies","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2638082?v=4","01M77JZCZJTWB8WBWX4NNW8MNP","Ross Davies","01M77JZD0S2Q4JZEM0310T9A73",2,"MIT","https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: triage\ndescription: Classify work into Quick, Standard, or Full tiers from deterministic signals. Use when routing new work or re-scoring scope mid-flight. Does not run the doc pipeline or implementation phases.\nmetadata:\n  shipwright-capability:\n    version: 1\n    triggers:\n      -\n        type: phase_default\n        selectionFamily: workflow\n        command: sw-triage\n    metadata:\n      skill: triage\n      selectionFamily: workflow\n---\n# Triage rubric (`\u002Fsw-triage`)\n\nDeterministic tier classifier. Auditable — same inputs → same tier. Not model judgment.\n\n\n**Model tier:** cheap — resolve via `python3 scripts\u002Fsw_bootstrap.py resolve-model-tier.py -- --skill triage`. When using the Task tool for subagent dispatch, resolve concrete model IDs from `models.tiers` in config (never semantic tier names in subagent `model:` frontmatter).\n\n## Inputs\n\nCollect before scoring:\n\n1. **File count** — number of files likely touched (user estimate or `git diff --stat` scope).\n2. **Risk keywords** — scan description + file paths for triggers (case-insensitive).\n3. **Ambiguity markers** — vague scope language in the request.\n4. **Override** — optional `--tier \u003Cquick|standard|full>` forces tier (record override).\n5. **Misroute re-entry** — `--re-score` when a Quick item's scope grew mid-flight.\n\n## Risk triggers (hard floor → ≥ Standard)\n\nEach keyword is **tagged**. **Any tag match** forces at least Standard regardless of file count.\n**`security`-tagged** entries flow into doc-review selection via `signal_context.derived_tags` and manifest\n`text_token` triggers on `sw-security-reviewer` (see `core\u002Fsw-reference\u002Fcapability-manifest.md` — not\nduplicated here).\n\n| Keyword | Category |\n| --- | --- |\n| `auth` | security |\n| `authn` | security |\n| `authz` | security |\n| `authentication` | security |\n| `authorization` | security |\n| `login` | security |\n| `session` | security |\n| `oauth` | security |\n| `jwt` | security |\n| `payment` | security |\n| `payments` | security |\n| `billing` | security |\n| `PII` | security |\n| `credentials` | security |\n| `token` | security |\n| `encryption` | security |\n| `public api` | security |\n| `public endpoint` | security |\n| `external api` | security |\n| `webhook` | security |\n| `stripe` | billing-routing |\n| `paddle` | billing-routing |\n| `subscription` | billing-routing |\n| `migration` | data-migration |\n| `data migration` | data-migration |\n| `schema migration` | data-migration |\n| `backfill` | data-migration |\n\n## Ambiguity markers (bias upward)\n\nAny match adds +1 to the score:\n\n- `maybe`, `possibly`, `not sure`, `unclear`, `TBD`, `figure out`\n- `explore`, `investigate`, `spike`, `prototype`\n- missing acceptance criteria on a multi-file change\n\n## File-count score\n\n| Files | Base tier |\n|-------|-----------|\n| 0–1 | Quick |\n| 2–5 | Standard |\n| 6+ | Full |\n\n## Resolution algorithm\n\n```\n1. If override flag set → use override tier; record \"override: \u003Ctier>\".\n2. If any risk trigger matches (any category) → floor = Standard.\n3. Compute base tier from file count.\n4. If ambiguity markers present → bump one tier (Quick→Standard, Standard→Full).\n5. If mixed\u002Finsufficient signals (no file count, empty description) → Standard (conservative).\n6. final = max(base tier, floor) using order Quick \u003C Standard \u003C Full.\n7. When advisory rigor is supplied, merge via `scripts\u002Ftriage_lib.merge_tier_monotonic` (union\u002Fmax-rigor).\n   Tier reductions require an authorized R7 reduction path — never file-count alone for Full.\n8. On --re-score with prior tier Quick and new score > Quick → promote; report misroute recovery.\n\nMechanical scoring lives in `scripts\u002Ftriage_lib.py` (`classify_triage`, `merge_triage_monotonic`).\n**Monotonic merge:** union\u002Fmax-rigor of mechanical set vs advisory rigor; reductions below the\nmechanical floor require R7 authorization (detector no-fire or human waiver) — file-count alone\n(including rename-only churn) is not a sole Full trigger.\n```\n\n## Output contract\n\nReport:\n\n```text\nTier: \u003CQuick|Standard|Full>\nSignals:\n  - file_count: \u003Cn> → \u003Cbase tier>\n  - risk_triggers: [\u003Cmatches>] → floor Standard (if any)\n  - ambiguity: [\u003Cmatches>] → bumped (if any)\n  - override: \u003Ctier> (if set)\n  - misroute_reentry: promoted from Quick (if applicable)\nNext: \u003Croute>\n```\n\nRoutes:\n\n- **Quick** → implementation workstream (`\u002Fsw-execute` when available); no doc artifacts.\n- **Standard** → `\u002Fsw-prd` (skip brainstorm) or `\u002Fsw-doc`.\n- **Full** → `\u002Fsw-brainstorm` or `\u002Fsw-doc`.\n\n## Misroute re-entry\n\nWhen implementation reveals scope growth on a Quick-classified item:\n\n1. Re-run `\u002Fsw-triage --re-score` with updated file list and description.\n2. If new tier > Quick, route into Standard\u002FFull pipeline.\n3. Record prior Quick classification in the output for audit.\n\n## Test matrix (structural)\n\n| Case | Input | Expected |\n|------|-------|----------|\n| Trivial | 1 file, no risk keyword | Quick |\n| Bounded feature | 4 files, no risk | Standard |\n| Risk floor | 1 file + \"auth\" | Standard (not Quick) |\n| Billing floor only | 1 file + \"stripe\" | Standard (not Quick); does not fire security persona |\n| Migration floor only | 1 file + \"migration\" | Standard (not Quick); does not fire security persona |\n| Ambiguous | 2 files + \"maybe refactor\" | Standard or Full |\n| Conservative default | empty file count | Standard |\n| Override | `--tier full` on 1-file change | Full + override recorded |\n| Misroute | `--re-score`, was Quick, now 6 files | Standard or Full |\n\n## Quick tier and graph-native `\u002Fsw-ship` (PRD 271 R7\u002FR15)\n\nQuick-classified work has **no frozen task list** — `\u002Fsw-deliver` does not apply. Entry remains\n**`\u002Fsw-ship`**: the same operator command compiles Quick work to a fixed WorkflowGraph via\n`scripts\u002Fgraph\u002Fquick_ship_compile.py` (`canonicalPhaseChains.sw-ship` in\n`kernel-classification.json`). Topology is configuration-declared only — no adaptive capability selection.\n\nGraph-native Quick does **not** add `\u002Fsw-graph-*` slash commands; live node progress and explain stay on\n`\u002Fsw-status`. On misroute (`--re-score` above Quick), route to Standard or Full — do not stretch Quick onto\nmulti-phase deliver.\n\n","# Triage rubric (`\u002Fsw-triage`)\n\nDeterministic tier classifier. Auditable — same inputs → same tier. Not model judgment.\n\n\n**Model tier:** cheap — resolve via `python3 scripts\u002Fsw_bootstrap.py resolve-model-tier.py -- --skill triage`. When using the Task tool for subagent dispatch, resolve concrete model IDs from `models.tiers` in config (never semantic tier names in subagent `model:` frontmatter).\n\n## Inputs\n\nCollect before scoring:\n\n1. **File count** — number of files likely touched (user estimate or `git diff --stat` scope).\n2. **Risk keywords** — scan description + file paths for triggers (case-insensitive).\n3. **Ambiguity markers** — vague scope language in the request.\n4. **Override** — optional `--tier \u003Cquick|standard|full>` forces tier (record override).\n5. **Misroute re-entry** — `--re-score` when a Quick item's scope grew mid-flight.\n\n## Risk triggers (hard floor → ≥ Standard)\n\nEach keyword is **tagged**. **Any tag match** forces at least Standard regardless of file count.\n**`security`-tagged** entries flow into doc-review selection via `signal_context.derived_tags` and manifest\n`text_token` triggers on `sw-security-reviewer` (see `core\u002Fsw-reference\u002Fcapability-manifest.md` — not\nduplicated here).\n\n| Keyword | Category |\n| --- | --- |\n| `auth` | security |\n| `authn` | security |\n| `authz` | security |\n| `authentication` | security |\n| `authorization` | security |\n| `login` | security |\n| `session` | security |\n| `oauth` | security |\n| `jwt` | security |\n| `payment` | security |\n| `payments` | security |\n| `billing` | security |\n| `PII` | security |\n| `credentials` | security |\n| `token` | security |\n| `encryption` | security |\n| `public api` | security |\n| `public endpoint` | security |\n| `external api` | security |\n| `webhook` | security |\n| `stripe` | billing-routing |\n| `paddle` | billing-routing |\n| `subscription` | billing-routing |\n| `migration` | data-migration |\n| `data migration` | data-migration |\n| `schema migration` | data-migration |\n| `backfill` | data-migration |\n\n## Ambiguity markers (bias upward)\n\nAny match adds +1 to the score:\n\n- `maybe`, `possibly`, `not sure`, `unclear`, `TBD`, `figure out`\n- `explore`, `investigate`, `spike`, `prototype`\n- missing acceptance criteria on a multi-file change\n\n## File-count score\n\n| Files | Base tier |\n|-------|-----------|\n| 0–1 | Quick |\n| 2–5 | Standard |\n| 6+ | Full |\n\n## Resolution algorithm\n\n```\n1. If override flag set → use override tier; record \"override: \u003Ctier>\".\n2. If any risk trigger matches (any category) → floor = Standard.\n3. Compute base tier from file count.\n4. If ambiguity markers present → bump one tier (Quick→Standard, Standard→Full).\n5. If mixed\u002Finsufficient signals (no file count, empty description) → Standard (conservative).\n6. final = max(base tier, floor) using order Quick \u003C Standard \u003C Full.\n7. When advisory rigor is supplied, merge via `scripts\u002Ftriage_lib.merge_tier_monotonic` (union\u002Fmax-rigor).\n   Tier reductions require an authorized R7 reduction path — never file-count alone for Full.\n8. On --re-score with prior tier Quick and new score > Quick → promote; report misroute recovery.\n\nMechanical scoring lives in `scripts\u002Ftriage_lib.py` (`classify_triage`, `merge_triage_monotonic`).\n**Monotonic merge:** union\u002Fmax-rigor of mechanical set vs advisory rigor; reductions below the\nmechanical floor require R7 authorization (detector no-fire or human waiver) — file-count alone\n(including rename-only churn) is not a sole Full trigger.\n```\n\n## Output contract\n\nReport:\n\n```text\nTier: \u003CQuick|Standard|Full>\nSignals:\n  - file_count: \u003Cn> → \u003Cbase tier>\n  - risk_triggers: [\u003Cmatches>] → floor Standard (if any)\n  - ambiguity: [\u003Cmatches>] → bumped (if any)\n  - override: \u003Ctier> (if set)\n  - misroute_reentry: promoted from Quick (if applicable)\nNext: \u003Croute>\n```\n\nRoutes:\n\n- **Quick** → implementation workstream (`\u002Fsw-execute` when available); no doc artifacts.\n- **Standard** → `\u002Fsw-prd` (skip brainstorm) or `\u002Fsw-doc`.\n- **Full** → `\u002Fsw-brainstorm` or `\u002Fsw-doc`.\n\n## Misroute re-entry\n\nWhen implementation reveals scope growth on a Quick-classified item:\n\n1. Re-run `\u002Fsw-triage --re-score` with updated file list and description.\n2. If new tier > Quick, route into Standard\u002FFull pipeline.\n3. Record prior Quick classification in the output for audit.\n\n## Test matrix (structural)\n\n| Case | Input | Expected |\n|------|-------|----------|\n| Trivial | 1 file, no risk keyword | Quick |\n| Bounded feature | 4 files, no risk | Standard |\n| Risk floor | 1 file + \"auth\" | Standard (not Quick) |\n| Billing floor only | 1 file + \"stripe\" | Standard (not Quick); does not fire security persona |\n| Migration floor only | 1 file + \"migration\" | Standard (not Quick); does not fire security persona |\n| Ambiguous | 2 files + \"maybe refactor\" | Standard or Full |\n| Conservative default | empty file count | Standard |\n| Override | `--tier full` on 1-file change | Full + override recorded |\n| Misroute | `--re-score`, was Quick, now 6 files | Standard or Full |\n\n## Quick tier and graph-native `\u002Fsw-ship` (PRD 271 R7\u002FR15)\n\nQuick-classified work has **no frozen task list** — `\u002Fsw-deliver` does not apply. Entry remains\n**`\u002Fsw-ship`**: the same operator command compiles Quick work to a fixed WorkflowGraph via\n`scripts\u002Fgraph\u002Fquick_ship_compile.py` (`canonicalPhaseChains.sw-ship` in\n`kernel-classification.json`). Topology is configuration-declared only — no adaptive capability selection.\n\nGraph-native Quick does **not** add `\u002Fsw-graph-*` slash commands; live node progress and explain stay on\n`\u002Fsw-status`. On misroute (`--re-score` above Quick), route to Standard or Full — do not stretch Quick onto\nmulti-phase deliver.\n\n",{"name":5,"metadata":24,"description":7},{"shipwright-capability":25},{"version":26,"metadata":27,"triggers":29},1,{"skill":5,"selectionFamily":28},"workflow",[30],{"type":31,"command":32,"selectionFamily":28},"phase_default","sw-triage","main","2633b37cdc50086084cc9c0ce6c994871d3e7aad","core\u002Fskills\u002Ftriage",0,"https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright","https:\u002F\u002Fgithub.com\u002Fgrdavies","2026-11-03 23:44:15",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add grdavies\u002Fshipwright --skill triage",{"tool":46,"command":47},"bunx","bunx skills add grdavies\u002Fshipwright --skill triage",{"tool":49,"command":50},"pnpm","pnpm dlx skills add grdavies\u002Fshipwright --skill triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Ftriage\u002FSKILL.md",true,[],[55,62,69,76,82,89],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M77K4Z004VAMY705XQKJAH4Y","wrong-name","Missing use when phrase and wrong directory name for critical lint failure.","https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fscripts\u002Ftest\u002Ffixtures\u002Fworkflow-pack-sdk\u002Fnegative\u002Fbad-instruction\u002Fskills\u002Fbad-skill\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M77K4WR3WP22SBT6053PYWAK","demo-skill","Demo workflow pack skill fixture. Use when validating workflow-pack-sdk golden paths in CI.","https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fscripts\u002Ftest\u002Ffixtures\u002Fworkflow-pack-sdk\u002Fgolden\u002Fvalid-pack\u002Fskills\u002Fdemo-skill\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M77K4SV48XDDDQ81PD09G9N6","good-skill","Validates Agent Skills spec conformance for fixture trees. Use when testing skills-spec-guard pass paths across core and dist mirrors. Does not ship production skills.","https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fscripts\u002Ftest\u002Ffixtures\u002Fskills-spec\u002Fpass-valid\u002Fcore\u002Fskills\u002Fgood-skill\u002FSKILL.md",[],[],{"skillNo":77,"name":57,"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},"01M77K4PWVT96VMTMMFE2Y80GJ","Fixture with name\u002Fdir mismatch for guard failure tests. Use when verifying skills-spec-guard rejects invalid identity. Does not ship production skills.","https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fscripts\u002Ftest\u002Ffixtures\u002Fskills-spec\u002Ffail-name-mismatch\u002Fcore\u002Fskills\u002Fgood-skill\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},"01M77K4KSS5Z0Q0DEAA8PV9316","bad-description","Missing the required when trigger phrase in this fixture skill.","https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fscripts\u002Ftest\u002Ffixtures\u002Fskills-spec\u002Ffail-description-shape\u002Fcore\u002Fskills\u002Fbad-description\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":6,"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},"01M77K4H9HK5FDF84D65228XFA","dropin-demo","https:\u002F\u002Fgithub.com\u002Fgrdavies\u002Fshipwright\u002Fblob\u002Fmain\u002Fscripts\u002Ftest\u002Ffixtures\u002Fcapability-select\u002Fdropin\u002Fcore\u002Fskills\u002Fdropin-demo\u002FSKILL.md",[],[]]