[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78F8PSCAQ47PPD22ET0RPP3":3,"skill-same:01M78F8PSCAQ47PPD22ET0RPP3":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78F8PSCAQ47PPD22ET0RPP3","e-code-review",null,"Code review at one of five effort levels that match the built-in \u002Fcode-review recipes step for step: low, medium, high, xhigh, max. Triggers: \u002Fe-code-review with an optional level and an optional --fix.","jl-cmd-projects\u002Fclaude-dev-env","jl-cmd-projects","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F338158757?v=4","01M78F4M55P4QY5YPN27XBQA9N","01M78F4M65AGEYC88NV6PW4715",7,"MIT","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: e-code-review\ndescription: >-\n  Code review at one of five effort levels that match the built-in\n  \u002Fcode-review recipes step for step: low, medium, high, xhigh, max.\n  Triggers: \u002Fe-code-review with an optional level and an optional --fix.\n---\n\n# e-code-review\n\n**Pick a level, load its file, run it.** Each file has the same steps, angles, caps, and fields as the built-in `\u002Fcode-review` recipe for that level. Only the wording differs, where this repo's prose rules require it. A question about `\u002Fcode-review` asks about the built-in recipe, so answer it from the built-in text and use these files only for `\u002Fe-code-review`.\n\n| Level | File | Shape |\n|---|---|---|\n| `low` | [reference\u002Flow.md](reference\u002Flow.md) | 1 diff pass, no verify, at most 4 findings |\n| `medium` | [reference\u002Fmedium.md](reference\u002Fmedium.md) | 1 careful diff pass, at most 15 findings |\n| `high` | [reference\u002Fhigh.md](reference\u002Fhigh.md) | 8 inline angles, dedup with no verify, at most 10 findings |\n| `xhigh` | [reference\u002Fxhigh.md](reference\u002Fxhigh.md) | 10 inline angles, dedup, gap sweep, at most 15 findings |\n| `max` | [reference\u002Fmax.md](reference\u002Fmax.md) | 10 subagent angles, 1-vote verify, gap sweep, at most 15 findings |\n\n## Level\n\nWith no level, or an unknown one, run `high`.\n\nThe level sets review depth. Child agents take their model and effort from [Subagent model and effort](~\u002F.claude\u002Fdocs\u002Frule-guides\u002Fsubagent-model-effort.md).\n\n## Target\n\nA PR number, branch name, or file path after the level is the review target. With no target, the review reads the current diff.\n\n## Report\n\nEach level file reports through the ReportFindings tool. When the host has no ReportFindings tool, print the findings in its place, most severe first, one per line as `file:line — summary`. `--fix` reports its outcomes the same way, with the outcome at the end of each line.\n\n## --fix\n\n`--fix` works with every level. It lives in one file, [reference\u002Ffix.md](reference\u002Ffix.md). No level file carries its own fix steps.\n\n## The process\n\n### Native GitHub evidence pilot\n\nKeep one coordinator responsible for native review requests. Record the request comment and full candidate head. Read raw GitHub review records to retain commit_id; normalized connector output can omit it. Completed reviews can contain findings. The quota_notice_ids field records historical usage-limit comments. Driver replies and resolved threads provide no clean completion proof.\n\nUse process-local GITHUB_TOKEN or GH_TOKEN authentication without printing credentials. A code-review usage-limit response stops further triggers until capacity is verified. Preserve the hold; review permission changes and credit purchases require separate authorization. Capture API bytes as UTF-8 before decoding them so Windows shell output encoding preserves review headings.\n\nInspect a candidate from the shared source checkout:\n\n```powershell\npython packages\u002Fclaude-dev-env\u002Fscripts\u002Fcodex_review_observer.py \u003Cowner\u002Frepository> \u003Cpull-request> \u003Cfull-head>\npython -m pytest packages\u002Fclaude-dev-env\u002Fscripts\u002Ftests\u002Ftest_codex_review_observer.py packages\u002Fclaude-dev-env\u002Fscripts\u002Ftests\u002Ftest_codex_review_guidance.py -q --override-ini=\"addopts=\" -p no:cacheprovider\n```\n\nThe current observer holds admission for every supported diagnostic. Require captured successful native completion with full-head and attempt coverage before adding a clean verdict. After a repair push, review the new head and preserve all existing checks. Keep current repository contracts authoritative over copied hosted policy.\n\n1. Read the level and the optional `--fix` flag. Load the level file.\n2. Run it end to end, ending in its ReportFindings call.\n3. With `--fix`, load `reference\u002Ffix.md` and run it on those findings.\n","# e-code-review\n\n**Pick a level, load its file, run it.** Each file has the same steps, angles, caps, and fields as the built-in `\u002Fcode-review` recipe for that level. Only the wording differs, where this repo's prose rules require it. A question about `\u002Fcode-review` asks about the built-in recipe, so answer it from the built-in text and use these files only for `\u002Fe-code-review`.\n\n| Level | File | Shape |\n|---|---|---|\n| `low` | [reference\u002Flow.md](reference\u002Flow.md) | 1 diff pass, no verify, at most 4 findings |\n| `medium` | [reference\u002Fmedium.md](reference\u002Fmedium.md) | 1 careful diff pass, at most 15 findings |\n| `high` | [reference\u002Fhigh.md](reference\u002Fhigh.md) | 8 inline angles, dedup with no verify, at most 10 findings |\n| `xhigh` | [reference\u002Fxhigh.md](reference\u002Fxhigh.md) | 10 inline angles, dedup, gap sweep, at most 15 findings |\n| `max` | [reference\u002Fmax.md](reference\u002Fmax.md) | 10 subagent angles, 1-vote verify, gap sweep, at most 15 findings |\n\n## Level\n\nWith no level, or an unknown one, run `high`.\n\nThe level sets review depth. Child agents take their model and effort from [Subagent model and effort](~\u002F.claude\u002Fdocs\u002Frule-guides\u002Fsubagent-model-effort.md).\n\n## Target\n\nA PR number, branch name, or file path after the level is the review target. With no target, the review reads the current diff.\n\n## Report\n\nEach level file reports through the ReportFindings tool. When the host has no ReportFindings tool, print the findings in its place, most severe first, one per line as `file:line — summary`. `--fix` reports its outcomes the same way, with the outcome at the end of each line.\n\n## --fix\n\n`--fix` works with every level. It lives in one file, [reference\u002Ffix.md](reference\u002Ffix.md). No level file carries its own fix steps.\n\n## The process\n\n### Native GitHub evidence pilot\n\nKeep one coordinator responsible for native review requests. Record the request comment and full candidate head. Read raw GitHub review records to retain commit_id; normalized connector output can omit it. Completed reviews can contain findings. The quota_notice_ids field records historical usage-limit comments. Driver replies and resolved threads provide no clean completion proof.\n\nUse process-local GITHUB_TOKEN or GH_TOKEN authentication without printing credentials. A code-review usage-limit response stops further triggers until capacity is verified. Preserve the hold; review permission changes and credit purchases require separate authorization. Capture API bytes as UTF-8 before decoding them so Windows shell output encoding preserves review headings.\n\nInspect a candidate from the shared source checkout:\n\n```powershell\npython packages\u002Fclaude-dev-env\u002Fscripts\u002Fcodex_review_observer.py \u003Cowner\u002Frepository> \u003Cpull-request> \u003Cfull-head>\npython -m pytest packages\u002Fclaude-dev-env\u002Fscripts\u002Ftests\u002Ftest_codex_review_observer.py packages\u002Fclaude-dev-env\u002Fscripts\u002Ftests\u002Ftest_codex_review_guidance.py -q --override-ini=\"addopts=\" -p no:cacheprovider\n```\n\nThe current observer holds admission for every supported diagnostic. Require captured successful native completion with full-head and attempt coverage before adding a clean verdict. After a repair push, review the new head and preserve all existing checks. Keep current repository contracts authoritative over copied hosted policy.\n\n1. Read the level and the optional `--fix` flag. Load the level file.\n2. Run it end to end, ending in its ReportFindings call.\n3. With `--fix`, load `reference\u002Ffix.md` and run it on those findings.\n",{"name":5,"description":7},"main","974284b42eeb4609e94d4ebc1f6e36df400d54ca","packages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review",1,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects","2026-11-15 05:02:47",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add jl-cmd-projects\u002Fclaude-dev-env --skill e-code-review",{"tool":36,"command":37},"bunx","bunx skills add jl-cmd-projects\u002Fclaude-dev-env --skill e-code-review",{"tool":39,"command":40},"pnpm","pnpm dlx skills add jl-cmd-projects\u002Fclaude-dev-env --skill e-code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002FSKILL.md",true,[44,50,54,58,62,66],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"reference\u002Ffix.md","REFERENCE","参考文档",570,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002Freference\u002Ffix.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"reference\u002Fhigh.md",6579,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002Freference\u002Fhigh.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"reference\u002Flow.md",2069,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002Freference\u002Flow.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"reference\u002Fmax.md",8808,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002Freference\u002Fmax.md",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":64,"sourceHtmlUrl":65},"reference\u002Fmedium.md",1573,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002Freference\u002Fmedium.md",{"path":67,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":68,"sourceHtmlUrl":69},"reference\u002Fxhigh.md",8082,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills\u002Fe-code-review\u002Freference\u002Fxhigh.md",[71,78,85,92,99,106],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M78FER7S09AE87MMJFT1E87E","update","Fast-forwards a local repository's main branch to a remote's main after confirming the repo path and source remote through AskUserQuestion. Use when the user says '\u002Fupdate', 'update main', 'fast-forward main', 'sync main from origin', 'pull latest main into \u003Cpath>', or 'bring main up to date'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fupdate\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M78FENWZS01MB4PMGX6801X6","source-command-sr-loop","Converging cleanup loop: repeat \u002Fsimplify until clean, then repeat \u002Fcode-review --fix until clean","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsource-command-sr-loop\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M78FEGZ7JDWEG3RM78M9Y8F8","skill-builder","Skill lifecycle: classify, scaffold, write via the skill-writer-agent, self-audit, compose sub-skills, polish description triggers, enforce deterministic scripts. Triggers: build a skill, new skill workflow, improve this skill, optimize skill description, skill development lifecycle, skill modularity, skill composition, description trigger catalog, deterministic skill scripts.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fskill-builder\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M78FEDEYHJYKTER9S566DMEZ","session-tidy","Audit, clean, and consolidate session logs in the Obsidian vault. Fixes format drift, resolves orphaned next-steps, updates stale statuses, and generates project rollup summaries. Use when session logs feel cluttered or before starting a new project milestone. Triggers on '\u002Fsession-tidy', 'tidy sessions', 'clean up session logs', 'session audit'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-tidy\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M78FE8QR789SKBF3A78N2T13","session-log","Logs a session report as an HTML page, tracks vault context, extracts decisions, and outputs a \u002Frename command. Use for \u002Fsession-log, 'journal this session', 'log this work', 'session report', 'summarize\u002Flog\u002Frecord this session', 'save session', 'capture session', or 'document what we did'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-log\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":18},"01M78FE4JDJHKTJPWRWNQEX2HT","run-claude-dev-env","Build, install, run, and test the claude-dev-env installer. Use when asked to run claude-dev-env, install the Claude Code config into ~\u002F.claude, drive the installer, smoke-test it against a sandbox, or run its test suite.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Frun-claude-dev-env\u002FSKILL.md",[],[]]