[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78C127TPYNJBX0B4BCF7246":3,"skill-same:01M78C127TPYNJBX0B4BCF7246":106},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":47},"01M78C127TPYNJBX0B4BCF7246","review-session",null,"Review an agent session for evidence-backed friction and the smallest measurable remedies.","adriancodes\u002Fskills","adriancodes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F940414?v=4","01M6NJ91CRRXPC6RRKWM4CVEGJ","Adrian Martin","01M78BV1DGXZ4VG3VVC30VH0MC",1,"MIT","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: review-session\ndescription: Review an agent session for evidence-backed friction and the smallest measurable remedies.\ndisable-model-invocation: true\nlicense: MIT\nmetadata:\n  category: Improvement\n  summary: Turns observed session failures into bounded remedies without inventing causes or applying unrequested policy changes.\n---\n\n# Review Session\n\nTrace each recommendation to an observed event. Apply remedies only when the user requests application.\n\n## Scope\n\nUse when explicitly invoked to review a session's effectiveness.\n\nDo not use for:\n\n- Diagnosing a live defect: use `diagnose`; reproduce and discriminate causes if unavailable.\n- Authoring a skill: tell the user to run `create-skill`. If it is not installed, confirm the skill's job and compare it with a cheaper mechanism.\n- Editing persistent project instructions: tell the user to run `write-agent-instructions`. If it is not installed, verify the instruction defect and test a minimal change.\n- General opinions about agent quality without session evidence: request the missing trace or limit the review to available facts.\n\n## Workflow\n\n### 1. Reconstruct the useful sequence\n\nReview the session the user names.\nWith none named, review the current conversation and say that turns removed by compaction are not covered.\nRead its tool results, artifacts, and the relevant repository state.\nIdentify the intended outcome and what actually happened.\nSeparate observations from causal hypotheses.\nKeep gaps, unlogged time, and inaccessible evidence explicit.\nQuote only the minimum context needed to identify a failure.\nRedact secrets and unrelated private data.\n\nDone when every reported friction point has an evidence pointer and a consequence.\n\n### 2. Find the owning mechanism\n\nInspect existing checks, scripts, instruction layers, and local conventions.\nDistinguish an absent mechanism from one that failed or was never run.\nUse a deterministic check for a mechanical defect.\nPrefer wiring or repairing an existing check over adding prose.\nUse a bounded instruction change only for demonstrated instruction-related behavior.\nLeave unresolved product choices with their owner.\n\nDone when each proposed remedy addresses the observed failure in the appropriate layer.\n\n### 3. Test the proposed effect\n\nReplay a safe existing check against the original failing input when possible.\nVerify check descriptions against runtime output rather than source spelling.\nShow how the smallest remedy would change that result.\nDefine a downstream task for behavioral remedies.\nReport an unavailable replay as a limit rather than an accomplished prevention.\nCompare expected consequence and effort.\nRank at most three remedies and identify the first useful one.\n\nDone when recommendations have a checkable effect and no unsupported universal guarantee.\n\n### 4. Save the review\n\nFollow the requested location or use `docs\u002Fsession-reviews\u002F\u003Ctopic>.md`.\nInclude the observed issue, evidence, remedy, effect check, and unresolved limit.\nKeep review-only work to the report.\nApply an explicitly requested remedy within its bounded scope.\nVerify any applied change with its owning workflow.\n\nDone when the review is inspectable and application status is unambiguous.\n\n## Worked example\n\n> Issue: `retrys` reached main; the formatter passed it.\n> Evidence: the CI log runs only the formatter; `check-config.mjs` exists and is not in the CI command.\n> Remedy: add `check-config.mjs` to the CI command.\n> Effect check: replayed the checker on the misspelled file; it exits non-zero.\n> Limit: the delay before the fix is unlogged; no cause is claimed.\n\n## Verification\n\nCheck recommendations against actual events and existing mechanisms.\nCheck that the report contains no invented causal story or unrequested policy edit.\nRecommend the smallest remedy whose effect the evidence can support.\n","# Review Session\n\nTrace each recommendation to an observed event. Apply remedies only when the user requests application.\n\n## Scope\n\nUse when explicitly invoked to review a session's effectiveness.\n\nDo not use for:\n\n- Diagnosing a live defect: use `diagnose`; reproduce and discriminate causes if unavailable.\n- Authoring a skill: tell the user to run `create-skill`. If it is not installed, confirm the skill's job and compare it with a cheaper mechanism.\n- Editing persistent project instructions: tell the user to run `write-agent-instructions`. If it is not installed, verify the instruction defect and test a minimal change.\n- General opinions about agent quality without session evidence: request the missing trace or limit the review to available facts.\n\n## Workflow\n\n### 1. Reconstruct the useful sequence\n\nReview the session the user names.\nWith none named, review the current conversation and say that turns removed by compaction are not covered.\nRead its tool results, artifacts, and the relevant repository state.\nIdentify the intended outcome and what actually happened.\nSeparate observations from causal hypotheses.\nKeep gaps, unlogged time, and inaccessible evidence explicit.\nQuote only the minimum context needed to identify a failure.\nRedact secrets and unrelated private data.\n\nDone when every reported friction point has an evidence pointer and a consequence.\n\n### 2. Find the owning mechanism\n\nInspect existing checks, scripts, instruction layers, and local conventions.\nDistinguish an absent mechanism from one that failed or was never run.\nUse a deterministic check for a mechanical defect.\nPrefer wiring or repairing an existing check over adding prose.\nUse a bounded instruction change only for demonstrated instruction-related behavior.\nLeave unresolved product choices with their owner.\n\nDone when each proposed remedy addresses the observed failure in the appropriate layer.\n\n### 3. Test the proposed effect\n\nReplay a safe existing check against the original failing input when possible.\nVerify check descriptions against runtime output rather than source spelling.\nShow how the smallest remedy would change that result.\nDefine a downstream task for behavioral remedies.\nReport an unavailable replay as a limit rather than an accomplished prevention.\nCompare expected consequence and effort.\nRank at most three remedies and identify the first useful one.\n\nDone when recommendations have a checkable effect and no unsupported universal guarantee.\n\n### 4. Save the review\n\nFollow the requested location or use `docs\u002Fsession-reviews\u002F\u003Ctopic>.md`.\nInclude the observed issue, evidence, remedy, effect check, and unresolved limit.\nKeep review-only work to the report.\nApply an explicitly requested remedy within its bounded scope.\nVerify any applied change with its owning workflow.\n\nDone when the review is inspectable and application status is unambiguous.\n\n## Worked example\n\n> Issue: `retrys` reached main; the formatter passed it.\n> Evidence: the CI log runs only the formatter; `check-config.mjs` exists and is not in the CI command.\n> Remedy: add `check-config.mjs` to the CI command.\n> Effect check: replayed the checker on the misspelled file; it exits non-zero.\n> Limit: the delay before the fix is unlogged; no cause is claimed.\n\n## Verification\n\nCheck recommendations against actual events and existing mechanisms.\nCheck that the report contains no invented causal story or unrequested policy edit.\nRecommend the smallest remedy whose effect the evidence can support.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":27},{"summary":25,"category":26},"Turns observed session failures into bounded remedies without inventing causes or applying unrequested policy changes.","Improvement",true,"main","9a3fe345285b86c3071deb2ecb302dff99a855b8","skills\u002Freview-session",0,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills","https:\u002F\u002Fgithub.com\u002Fadriancodes","2026-11-12 06:06:49",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":27},[37,40,43],{"tool":38,"command":39},"npx","npx skills add adriancodes\u002Fskills --skill review-session",{"tool":41,"command":42},"bunx","bunx skills add adriancodes\u002Fskills --skill review-session",{"tool":44,"command":45},"pnpm","pnpm dlx skills add adriancodes\u002Fskills --skill review-session","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002FSKILL.md",[48,54,58,64,68,72,76,80,84,88,92,98,102],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",43,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"evals\u002Fbudget.json",873,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fbudget.json",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"evals\u002Fcases-initial.jsonl","OTHER","其他",17008,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fcases-initial.jsonl",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"evals\u002Fcases.jsonl",20973,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fcases.jsonl",{"path":69,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":70,"sourceHtmlUrl":71},"evals\u002Ffixtures\u002FREADME.md",212,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Ffixtures\u002FREADME.md",{"path":73,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":74,"sourceHtmlUrl":75},"evals\u002Fmatrix.json",1250,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fmatrix.json",{"path":77,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":78,"sourceHtmlUrl":79},"evals\u002Fresults\u002FREADME.md",1435,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fresults\u002FREADME.md",{"path":81,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":82,"sourceHtmlUrl":83},"evals\u002Frubric.md",3318,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Frubric.md",{"path":85,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":86,"sourceHtmlUrl":87},"evals\u002Frun.md",4054,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Frun.md",{"path":89,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":90,"sourceHtmlUrl":91},"evals\u002Fscore-input.schema.json",635,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fscore-input.schema.json",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"evals\u002Fscore.mjs","SCRIPT","脚本",180,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fscore.mjs",{"path":99,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":100,"sourceHtmlUrl":101},"evals\u002Fsuite-manifest-i1.json",11876,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fsuite-manifest-i1.json",{"path":103,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":104,"sourceHtmlUrl":105},"evals\u002Fsuite-manifest-i2.json",15637,"https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-session\u002Fevals\u002Fsuite-manifest-i2.json",[107,114,121,128,135,142],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M78C1QNZAXX06QMDJ8R65TTV","write-agent-instructions","Make the smallest evidence-backed change to persistent project instructions and test downstream behavior.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-agent-instructions\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M78C1K3QVP67S0TRERZ5YNGB","verify-work","Use when a finished, runnable artifact (a script, config, parser, prompt, or CLI, not a diff under review) must survive hostile input before shipping: the user asks to \"verify this script\", \"find the loopholes\", \"test this properly against bad input\", or asks \"is this ready to ship\" about one. Also when a shipped artifact failed on an input nobody tried, or when verification so far is a happy-path smoke test.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify-work\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M78C1DDYDEQ7H1HNW84VW1V3","understand-codebase","Use when the user asks to \"understand this codebase\", \"how does this feature work in this repo?\", \"trace this feature through the code\", or needs onboarding, an architecture explanation, or answers about unfamiliar code. Also use for read-only code-path questions before a change.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Funderstand-codebase\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":19},"01M78C18C6TG62PY1PQBGCSKXR","tdd","Use when writing or changing production behavior: implementing a feature, fixing a bug whose cause is already known, or altering stored, transformed, migrated, serialized, or externally transmitted data. Also use when a user says \"use TDD\", \"test first\", or \"red-green-refactor\", and when code is being written before a failing test. For a failure whose cause is unknown, diagnose first.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":19},"01M78C151714X4Z3VQW5F23FZW","simplify-code","Use when the user asks to \"simplify this code\", \"remove the fluff\", or \"clean up this over-engineered module\", or wants working code that is bloated, duplicated, over-abstracted, or dependency-heavy reduced without changing behavior.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsimplify-code\u002FSKILL.md",[],[],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":19},"01M78C0XJK1YEAQWV7NA2GYBRE","review-code","Use when a user asks to \"review this branch\", \"review this PR\", \"review my changes\", or \"review since main\". Also use when asked whether a branch, PR, or diff is ready to merge or ship, and for work-in-progress diffs, staged changes, suspected regressions in a patch, or checking implementation against a specification.","https:\u002F\u002Fgithub.com\u002Fadriancodes\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-code\u002FSKILL.md",[],[]]