[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ATW565PP8TSQYEDAFECGJB":3,"skill-same:01M7ATW565PP8TSQYEDAFECGJB":55},{"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":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7ATW565PP8TSQYEDAFECGJB","specrew-drift-check",null,"Detect drift between the spec, plan, tasks, and implementation; record findings to drift-log.md before review concludes.","alonf\u002FKeyContextAI","alonf","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F554150?v=4","01M7ATEPSCNKG13BVTKA74VG59","Alon Fliess","01M7ATEPSZ4YMBM9W25SKM3GES",0,"MIT","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecrew-drift-check\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"specrew-drift-check\"\ndescription: \"Detect drift between the spec, plan, tasks, and implementation; record findings to drift-log.md before review concludes.\"\ndomain: \"lifecycle-review\"\nconfidence: \"high\"\nsource: \"Specrew governance pillar — review\u002Fcloseout ceremony helper\"\n---\n\n# specrew-drift-check\n\n**Type**: Analysis Skill  \n**Schema**: v1  \n**Status**: Active execution\u002Freview method\n\n## Purpose\n\nDetect specification drift by comparing delivered output against the cited requirement and return a review-ready drift decision with evidence.\n\n## When to Use\n\n- After each task completion\n- During Review\u002FDemo as the batch fallback\n- Any time a reviewer or implementer suspects the output and the spec disagree\n\n## Inputs\n\n| Input | Type | Required | Description |\n| ----- | ---- | -------- | ----------- |\n| task_id | string | Yes | Task identifier for the completed work (for example `T-012`) |\n| task_output | string\u002Fpath | Yes | The deliverable or output from the completed task |\n| requirement_ref | string | Yes | Requirement identifier (for example `FR-003`) |\n| requirement_text | string | Yes | Full text of the requirement from the spec |\n| spec_path | path | Yes | Path to the authoritative spec file |\n| drift_log_path | path | No | Path to `iterations\u002FNNN\u002Fdrift-log.md` when the result should be prepared for immediate logging |\n| reviewer_notes | string\u002Farray | No | Existing reviewer concerns or context that should be tested against the requirement |\n\n## Process\n\n1. Confirm the authority before judging the output:\n   - locate `requirement_ref` in `spec_path`\n   - use the spec text as authoritative if `requirement_text` was copied inaccurately\n   - extract required behavior, explicit constraints, exclusions, and deferred scope\n2. Gather concrete evidence from `task_output`:\n   - identify the files, commands, artifacts, or behavior that prove what was delivered\n   - do not return PASS based on intention or a status note alone\n3. Compare the delivered output to three drift questions:\n   - Did we omit something required?\n   - Did we add something not authorized?\n   - Did we contradict the requirement or a documented deferral?\n4. Classify each mismatch for reviewer clarity:\n   - `gold-plating` = unauthorized added behavior\n   - `incomplete` = required behavior missing or only partially delivered\n   - `violation` = delivered behavior contradicts the requirement or accepted scope boundary\n5. Choose a resolution path for each drift event:\n   - `spec-updated`\n   - `implementation-reverted`\n   - `deferred`\n   - `human-decision`\n6. Produce a drift-log-ready result:\n   - PASS: provide explicit evidence summary and say no drift event is required\n   - DRIFT: emit contract-aligned event data and a Markdown snippet that can be copied into `drift-log.md`, including `Class closure` (or `NONE — \u003Cwhy>`)\n   - if `drift_log_path` points at a zero-drift placeholder log, note that the summary text must be updated when the first event is added\n\n## Outputs\n\n| Output | Type | Description |\n| ------ | ---- | ----------- |\n| verdict | enum: PASS, DRIFT | Whether drift was detected |\n| evidence_summary | string | Concrete evidence used to justify the verdict |\n| drift_events[] | array | List of detected drift events (empty if PASS) |\n| drift_events[].type | enum: gold-plating, incomplete, violation | Type of drift |\n| drift_events[].drift_id | string | Drift event identifier (for example `DR-001`) |\n| drift_events[].detected_at | ISO datetime | When the drift was identified |\n| drift_events[].task_ref | string | Task that triggered the check |\n| drift_events[].requirement_ref | string | Requirement identifier for the violated or exceeded requirement |\n| drift_events[].severity | enum: minor, moderate, critical | Severity level for review routing |\n| drift_events[].description | string | What deviated and how |\n| drift_events[].requirement_citation | string | Specific requirement text violated |\n| drift_events[].resolution | enum: spec-updated, implementation-reverted, deferred, human-decision | Chosen resolution path |\n| drift_events[].resolution_detail | string | What should happen next to resolve the drift |\n| drift_events[].log_snippet | string | Markdown-ready snippet aligned to the drift-log contract |\n| drift_events[].class_closure | string | Mechanism that makes recurrence impossible\u002Floud, or `NONE — \u003Cwhy>` |\n| drift_log_update_note | string | Guidance for updating `drift-log.md` summary text when needed |\n\n## Side Effects\n\n- Intended to append or prepare entries for `iterations\u002FNNN\u002Fdrift-log.md`\n- When the first drift event is detected, the zero-drift placeholder summary in `drift-log.md` must be replaced with the real event count and resolution status\n- No side effects if verdict is PASS\n\n## Error Handling\n\n- If `spec_path` is not found: return DRIFT with reason `spec file missing`\n- If `requirement_ref` is not found in the spec: return DRIFT with reason `requirement not in spec`\n- If `task_output` is empty: return DRIFT with reason `task output missing evidence`\n- If the copied `requirement_text` disagrees with the spec: continue with the spec text and report `stale requirement text supplied`\n\n## Review Standard\n\nThis skill is only complete when:\n\n1. PASS results cite concrete evidence, not optimism\n2. DRIFT results can be copied into `drift-log.md` without reformatting\n3. every drift event is traceable to both a task and an authoritative requirement citation\n","# specrew-drift-check\n\n**Type**: Analysis Skill  \n**Schema**: v1  \n**Status**: Active execution\u002Freview method\n\n## Purpose\n\nDetect specification drift by comparing delivered output against the cited requirement and return a review-ready drift decision with evidence.\n\n## When to Use\n\n- After each task completion\n- During Review\u002FDemo as the batch fallback\n- Any time a reviewer or implementer suspects the output and the spec disagree\n\n## Inputs\n\n| Input | Type | Required | Description |\n| ----- | ---- | -------- | ----------- |\n| task_id | string | Yes | Task identifier for the completed work (for example `T-012`) |\n| task_output | string\u002Fpath | Yes | The deliverable or output from the completed task |\n| requirement_ref | string | Yes | Requirement identifier (for example `FR-003`) |\n| requirement_text | string | Yes | Full text of the requirement from the spec |\n| spec_path | path | Yes | Path to the authoritative spec file |\n| drift_log_path | path | No | Path to `iterations\u002FNNN\u002Fdrift-log.md` when the result should be prepared for immediate logging |\n| reviewer_notes | string\u002Farray | No | Existing reviewer concerns or context that should be tested against the requirement |\n\n## Process\n\n1. Confirm the authority before judging the output:\n   - locate `requirement_ref` in `spec_path`\n   - use the spec text as authoritative if `requirement_text` was copied inaccurately\n   - extract required behavior, explicit constraints, exclusions, and deferred scope\n2. Gather concrete evidence from `task_output`:\n   - identify the files, commands, artifacts, or behavior that prove what was delivered\n   - do not return PASS based on intention or a status note alone\n3. Compare the delivered output to three drift questions:\n   - Did we omit something required?\n   - Did we add something not authorized?\n   - Did we contradict the requirement or a documented deferral?\n4. Classify each mismatch for reviewer clarity:\n   - `gold-plating` = unauthorized added behavior\n   - `incomplete` = required behavior missing or only partially delivered\n   - `violation` = delivered behavior contradicts the requirement or accepted scope boundary\n5. Choose a resolution path for each drift event:\n   - `spec-updated`\n   - `implementation-reverted`\n   - `deferred`\n   - `human-decision`\n6. Produce a drift-log-ready result:\n   - PASS: provide explicit evidence summary and say no drift event is required\n   - DRIFT: emit contract-aligned event data and a Markdown snippet that can be copied into `drift-log.md`, including `Class closure` (or `NONE — \u003Cwhy>`)\n   - if `drift_log_path` points at a zero-drift placeholder log, note that the summary text must be updated when the first event is added\n\n## Outputs\n\n| Output | Type | Description |\n| ------ | ---- | ----------- |\n| verdict | enum: PASS, DRIFT | Whether drift was detected |\n| evidence_summary | string | Concrete evidence used to justify the verdict |\n| drift_events[] | array | List of detected drift events (empty if PASS) |\n| drift_events[].type | enum: gold-plating, incomplete, violation | Type of drift |\n| drift_events[].drift_id | string | Drift event identifier (for example `DR-001`) |\n| drift_events[].detected_at | ISO datetime | When the drift was identified |\n| drift_events[].task_ref | string | Task that triggered the check |\n| drift_events[].requirement_ref | string | Requirement identifier for the violated or exceeded requirement |\n| drift_events[].severity | enum: minor, moderate, critical | Severity level for review routing |\n| drift_events[].description | string | What deviated and how |\n| drift_events[].requirement_citation | string | Specific requirement text violated |\n| drift_events[].resolution | enum: spec-updated, implementation-reverted, deferred, human-decision | Chosen resolution path |\n| drift_events[].resolution_detail | string | What should happen next to resolve the drift |\n| drift_events[].log_snippet | string | Markdown-ready snippet aligned to the drift-log contract |\n| drift_events[].class_closure | string | Mechanism that makes recurrence impossible\u002Floud, or `NONE — \u003Cwhy>` |\n| drift_log_update_note | string | Guidance for updating `drift-log.md` summary text when needed |\n\n## Side Effects\n\n- Intended to append or prepare entries for `iterations\u002FNNN\u002Fdrift-log.md`\n- When the first drift event is detected, the zero-drift placeholder summary in `drift-log.md` must be replaced with the real event count and resolution status\n- No side effects if verdict is PASS\n\n## Error Handling\n\n- If `spec_path` is not found: return DRIFT with reason `spec file missing`\n- If `requirement_ref` is not found in the spec: return DRIFT with reason `requirement not in spec`\n- If `task_output` is empty: return DRIFT with reason `task output missing evidence`\n- If the copied `requirement_text` disagrees with the spec: continue with the spec text and report `stale requirement text supplied`\n\n## Review Standard\n\nThis skill is only complete when:\n\n1. PASS results cite concrete evidence, not optimism\n2. DRIFT results can be copied into `drift-log.md` without reformatting\n3. every drift event is traceable to both a task and an authoritative requirement citation\n",{"name":5,"domain":24,"source":25,"confidence":26,"description":7},"lifecycle-review","Specrew governance pillar — review\u002Fcloseout ceremony helper","high","main","176da577bfd98859f793bdd1312690c6c3940c67",".claude\u002Fskills\u002Fspecrew-drift-check","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI","https:\u002F\u002Fgithub.com\u002Falonf","http:\u002F\u002Falonfliess.me","CTO & Founder of Zionet.\r\nMicrosoft Regional Director and Foundry MVP.\r\n","2026-08-28 05:21:35",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add alonf\u002FKeyContextAI --skill specrew-drift-check",{"tool":41,"command":42},"bunx","bunx skills add alonf\u002FKeyContextAI --skill specrew-drift-check",{"tool":44,"command":45},"pnpm","pnpm dlx skills add alonf\u002FKeyContextAI --skill specrew-drift-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecrew-drift-check\u002FSKILL.md",true,[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},".specrew-managed","OTHER","其他",76,"https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecrew-drift-check\u002F.specrew-managed",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AVHRWWXA0BQ5PXNA8FG30W","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AVHABPRYXYM3GWJY1RW92A","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7AVH4KNP3TCVQDRVS70VP19","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7AVH18JDSA55Z7KK2GH6X49","test-discipline","Update tests when changing APIs — no exceptions","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftest-discipline\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7AVGVGWYD7NBNXAV4PAZJ92","squad","Squad's command catalog and interactive menu. Invoke via \u002Fsquad (slash command) or natural language (\"squad commands\", \"what can squad do\", \"show me squad options\"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI command or the Squad coordinator agent.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7AVGPSFT1WHW3PK35DHS5XK","squad-version-check","Internals of how @bradygaster\u002Fsquad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad-version-check\u002FSKILL.md",[],[]]