[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71NEK5A805MW75S7NSKBAK0":3,"skill-same:01M71NEK5A805MW75S7NSKBAK0":90},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":29,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M71NEK5A805MW75S7NSKBAK0","gh-fix-ci",null,"Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI\u002FCD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.","q2805187159\u002FAnvil","q2805187159","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F105276843?v=4","01M71KF4TN999VNJX9FY9QT06A","铁甲勇士宋小宝","01M71KF4V97XXQ7AGES97R4Q9F",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fgh-fix-ci\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fgh-fix-ci\u002FSKILL.md",[19,24],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":25,"categoryName":26,"taxonomyType":27,"taxonomyTypeDesc":28},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"fix","ci","gh","fix ci","gh fix ci","URL","when","debug","use","only","github actions","failing","github ci","actions","inspect","for","scope","pr","out of scope","pull","2026-11-10 10:56:23",false,"---\nname: gh-fix-ci\ndescription: Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI\u002FCD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.\nmetadata:\n  short-description: Fix failing Github CI actions\n---\n\n# Gh Pr Checks Plan Fix\n\n## Overview\n\nUse gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure snippet, then propose a fix plan and implement after explicit approval.\n- Depends on the `plan` skill for drafting and approving the fix plan.\n\nPrereq: ensure `gh` is authenticated (for example, run `gh auth login` once), then run `gh auth status` with escalated permissions (include workflow\u002Frepo scopes) so `gh` commands succeed. If sandboxing blocks `gh auth status`, rerun it with `sandbox_permissions=require_escalated`.\n\n## Inputs\n\n- `repo`: path inside the repo (default `.`)\n- `pr`: PR number or URL (optional; defaults to current branch PR)\n- `gh` authentication for the repo host\n\n## Quick start\n\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"\u003Cnumber-or-url>\"`\n- Add `--json` if you want machine-friendly output for summarization.\n\n## Workflow\n\n1. Verify gh authentication.\n   - Run `gh auth status` in the repo with escalated scopes (workflow\u002Frepo) after running `gh auth login`.\n   - If sandboxed auth status fails, rerun the command with `sandbox_permissions=require_escalated` to allow network\u002Fkeyring access.\n   - If unauthenticated, ask the user to log in before proceeding.\n2. Resolve the PR.\n   - Prefer the current branch PR: `gh pr view --json number,url`.\n   - If the user provides a PR number or URL, use that directly.\n3. Inspect failing checks (GitHub Actions only).\n   - Preferred: run the bundled script (handles gh field drift and job-log fallbacks):\n     - `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"\u003Cnumber-or-url>\"`\n     - Add `--json` for machine-friendly output.\n   - Manual fallback:\n     - `gh pr checks \u003Cpr> --json name,state,bucket,link,startedAt,completedAt,workflow`\n       - If a field is rejected, rerun with the available fields reported by `gh`.\n     - For each failing check, extract the run id from `detailsUrl` and run:\n       - `gh run view \u003Crun_id> --json name,workflowName,conclusion,status,url,event,headBranch,headSha`\n       - `gh run view \u003Crun_id> --log`\n     - If the run log says it is still in progress, fetch job logs directly:\n       - `gh api \"\u002Frepos\u002F\u003Cowner>\u002F\u003Crepo>\u002Factions\u002Fjobs\u002F\u003Cjob_id>\u002Flogs\" > \"\u003Cpath>\"`\n4. Scope non-GitHub Actions checks.\n   - If `detailsUrl` is not a GitHub Actions run, label it as external and only report the URL.\n   - Do not attempt Buildkite or other providers; keep the workflow lean.\n5. Summarize failures for the user.\n   - Provide the failing check name, run URL (if any), and a concise log snippet.\n   - Call out missing logs explicitly.\n6. Create a plan.\n   - Use the `plan` skill to draft a concise plan and request approval.\n7. Implement after approval.\n   - Apply the approved plan, summarize diffs\u002Ftests, and ask about opening a PR.\n8. Recheck status.\n   - After changes, suggest re-running the relevant tests and `gh pr checks` to confirm.\n\n## Bundled Resources\n\n### scripts\u002Finspect_pr_checks.py\n\nFetch failing PR checks, pull GitHub Actions logs, and extract a failure snippet. Exits non-zero when failures remain so it can be used in automation.\n\nUsage examples:\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"123\"`\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F123\" --json`\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --max-lines 200 --context 40`\n","# Gh Pr Checks Plan Fix\n\n## Overview\n\nUse gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure snippet, then propose a fix plan and implement after explicit approval.\n- Depends on the `plan` skill for drafting and approving the fix plan.\n\nPrereq: ensure `gh` is authenticated (for example, run `gh auth login` once), then run `gh auth status` with escalated permissions (include workflow\u002Frepo scopes) so `gh` commands succeed. If sandboxing blocks `gh auth status`, rerun it with `sandbox_permissions=require_escalated`.\n\n## Inputs\n\n- `repo`: path inside the repo (default `.`)\n- `pr`: PR number or URL (optional; defaults to current branch PR)\n- `gh` authentication for the repo host\n\n## Quick start\n\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"\u003Cnumber-or-url>\"`\n- Add `--json` if you want machine-friendly output for summarization.\n\n## Workflow\n\n1. Verify gh authentication.\n   - Run `gh auth status` in the repo with escalated scopes (workflow\u002Frepo) after running `gh auth login`.\n   - If sandboxed auth status fails, rerun the command with `sandbox_permissions=require_escalated` to allow network\u002Fkeyring access.\n   - If unauthenticated, ask the user to log in before proceeding.\n2. Resolve the PR.\n   - Prefer the current branch PR: `gh pr view --json number,url`.\n   - If the user provides a PR number or URL, use that directly.\n3. Inspect failing checks (GitHub Actions only).\n   - Preferred: run the bundled script (handles gh field drift and job-log fallbacks):\n     - `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"\u003Cnumber-or-url>\"`\n     - Add `--json` for machine-friendly output.\n   - Manual fallback:\n     - `gh pr checks \u003Cpr> --json name,state,bucket,link,startedAt,completedAt,workflow`\n       - If a field is rejected, rerun with the available fields reported by `gh`.\n     - For each failing check, extract the run id from `detailsUrl` and run:\n       - `gh run view \u003Crun_id> --json name,workflowName,conclusion,status,url,event,headBranch,headSha`\n       - `gh run view \u003Crun_id> --log`\n     - If the run log says it is still in progress, fetch job logs directly:\n       - `gh api \"\u002Frepos\u002F\u003Cowner>\u002F\u003Crepo>\u002Factions\u002Fjobs\u002F\u003Cjob_id>\u002Flogs\" > \"\u003Cpath>\"`\n4. Scope non-GitHub Actions checks.\n   - If `detailsUrl` is not a GitHub Actions run, label it as external and only report the URL.\n   - Do not attempt Buildkite or other providers; keep the workflow lean.\n5. Summarize failures for the user.\n   - Provide the failing check name, run URL (if any), and a concise log snippet.\n   - Call out missing logs explicitly.\n6. Create a plan.\n   - Use the `plan` skill to draft a concise plan and request approval.\n7. Implement after approval.\n   - Apply the approved plan, summarize diffs\u002Ftests, and ask about opening a PR.\n8. Recheck status.\n   - After changes, suggest re-running the relevant tests and `gh pr checks` to confirm.\n\n## Bundled Resources\n\n### scripts\u002Finspect_pr_checks.py\n\nFetch failing PR checks, pull GitHub Actions logs, and extract a failure snippet. Exits non-zero when failures remain so it can be used in automation.\n\nUsage examples:\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"123\"`\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --pr \"https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F123\" --json`\n- `python \"\u003Cpath-to-skill>\u002Fscripts\u002Finspect_pr_checks.py\" --repo \".\" --max-lines 200 --context 40`\n",{"name":5,"metadata":55,"description":7},{"short-description":56},"Fix failing Github CI actions","main","6ffadc67c9777282fa1f9330ec12ac8778064409","skills\u002Fgh-fix-ci",0,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil","https:\u002F\u002Fgithub.com\u002Fq2805187159","Independent Researcher\r\n\r\nEmail: q2805187159@gmail.com\r\n\r\nGithub: q2805187159\r\n\r\nResearch Interests:\r\n- LLM Agents\r\n- Tool Routing\r\n- RAG","2026-06-24 18:31:41",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add q2805187159\u002FAnvil --skill gh-fix-ci",{"tool":71,"command":72},"bunx","bunx skills add q2805187159\u002FAnvil --skill gh-fix-ci",{"tool":74,"command":75},"pnpm","pnpm dlx skills add q2805187159\u002FAnvil --skill gh-fix-ci","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fgh-fix-ci\u002FSKILL.md",true,[79,84],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",11357,{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Finspect_pr_checks.py","SCRIPT","脚本",15071,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fgh-fix-ci\u002Fscripts\u002Finspect_pr_checks.py",[91,121,151,158,184,206],{"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":95,"sourceHtmlUrl":96,"categories":97,"keywords":104,"publishedAt":50},"01M71NPWVVMB1AZ8XGKNJFT0YP","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[98,101],{"categoryNo":99,"categoryName":100,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":102,"categoryName":103,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000009","前端开发",[105,106,107,45,108,109,110,111,112,113,114,115,116,117,118,119,120],"webapp","testing","webapp testing","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots",{"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":125,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":134,"publishedAt":50},"01M71NPTQ96H4XSZVZT422BNRB","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","MIT","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[128,131],{"categoryNo":129,"categoryName":130,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":132,"categoryName":133,"taxonomyType":27,"taxonomyTypeDesc":28},"01JBSEEDCAT000000000000032","设计师",[135,136,117,137,138,45,139,140,141,38,36,142,143,144,145,146,147,148,149,150],"guidelines","design","web design guidelines","web design","vercel","interface","web interface guidelines","best practices","file","code","review","check","compliance","audit","ux","accessibility",{"skillNo":152,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":125,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":157,"publishedAt":50},"01M71NPS2D31Y2BGFYA9DB7CE4","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines copy\u002FSKILL.md",[155,156],{"categoryNo":129,"categoryName":130,"taxonomyType":22,"taxonomyTypeDesc":23},{"categoryNo":132,"categoryName":133,"taxonomyType":27,"taxonomyTypeDesc":28},[135,136,117,137,138,45,139,140,141,38,36,142,143,144,145,146,147,148,149,150],{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":125,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":170,"publishedAt":50},"01M71NPQ9DRT54QSQJ0BHBM3VG","video-generation","Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-generation\u002FSKILL.md",[164,167],{"categoryNo":165,"categoryName":166,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":168,"categoryName":169,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000023","Skill与智能体开发",[171,172,173,45,38,36,174,175,176,177,178,179,180,181,182,183],"Video","video generation","generation","image","create","imagine","requests","generate","videos","reference","prompts","user","structured",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":125,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":191,"publishedAt":50},"01M71NPN57CT154SWXAS52475X","youtube-downloader","Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-downloader\u002FSKILL.md",[190],{"categoryNo":165,"categoryName":166,"taxonomyType":22,"taxonomyTypeDesc":23},[192,193,194,195,196,197,39,38,36,198,115,199,200,201,202,203,179,204,182,205],"youtube","youtube downloader","mp4","as","downloads","Audio","mp3","options","quality","format","settings","grab","formats","download",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":125,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":212,"publishedAt":50},"01M71NPKD95YB8N3J6J78QGFFW","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[213,214,215,216,217,218,219,38,220,36,221,222,223,224,225,226],"verification","verification before completion","running","evidence","complete","prs","claim","assertions","committing","output","claims","work","about","commands"]