[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADM5TYNGNAGSHZ45DR75B1":3,"skill-same:01M6ADM5TYNGNAGSHZ45DR75B1":85},{"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":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M6ADM5TYNGNAGSHZ45DR75B1","deep-analysis",null,"Perform a deep architectural analysis or security review requiring extended reasoning. Use for complex architecture decisions, security audits, or when standard analysis is not finding the root cause.","davila7\u002Fclaude-with-skills","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHY7XW1NT6J5EJ61Q42B",13,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F02-intermediate\u002Flesson-07-model-and-effort\u002Fexamples\u002Fdeep-analysis\u002FSKILL.md",[],[19,20,21,22,23,24],"deep analysis","review","security","architecture","security review","reasoning","2026-11-10 10:12:30",false,"---\ntitle: \"deep-analysis\"\nname: deep-analysis\ndescription: Perform a deep architectural analysis or security review requiring extended reasoning. Use for complex architecture decisions, security audits, or when standard analysis is not finding the root cause.\nmodel: opus\neffort: high\ndisable-model-invocation: true\n---\n\n## Deep analysis\n\nultrathink\n\nPerform a thorough analysis of the described problem or codebase area. Do not skip steps under time or context pressure. This skill intentionally uses extended reasoning — use it.\n\n### Step 1: Gather all relevant context\n\nBefore forming any hypothesis, collect the raw material:\n\n- Read all files directly involved in the problem area\n- Check git history for the relevant files: `git log --oneline --follow -20 \u003Cfile>` for each key file, then `git show \u003Chash>` for commits that look relevant\n- Look for tests that cover the area: they describe the intended behavior\n- Look for related configuration (environment variables, feature flags, build configuration)\n- Check for any documentation: comments, ADRs, or README sections that mention the area\n\nDo not stop gathering context when you think you understand the issue. The full picture often requires reading more than the most obvious files.\n\n### Step 2: Identify the core issue or question\n\nState, in one or two sentences, what the fundamental question or problem is. Separate it from symptoms. For example:\n\n- Symptom: \"The API returns 500 errors intermittently\"\n- Core question: \"Is this a race condition in the connection pool, an unhandled exception in a specific code path, or an infrastructure issue?\"\n\nIf you are doing an architectural analysis, state the specific decision or tradeoff being evaluated.\n\n### Step 3: Consider multiple hypotheses or approaches\n\nDo not converge on the first plausible explanation. List at least three distinct hypotheses or approaches:\n\n- For bug analysis: three distinct root causes that could explain the observed behavior\n- For architecture decisions: three distinct design approaches with different tradeoff profiles\n- For security reviews: three distinct vulnerability classes to investigate\n\nFor each, note what evidence would confirm or rule it out.\n\n### Step 4: Evaluate tradeoffs\n\nFor each hypothesis or approach, evaluate:\n\n**Evidence for**: What in the codebase supports this explanation or approach?\n**Evidence against**: What contradicts it or makes it unlikely?\n**Risk**: If this hypothesis is wrong or this approach is chosen, what goes wrong?\n**Cost to verify or implement**: How much effort would confirming or executing this require?\n\nWork through the evidence systematically. Update your confidence in each hypothesis as you find more evidence. It is correct to change your assessment mid-analysis — note when you do and why.\n\n### Step 5: Give a concrete recommendation with justification\n\nState the conclusion clearly:\n\n- For bug analysis: the most likely root cause, the specific code location (file and line number), and the minimal fix\n- For architecture decisions: the recommended approach and the specific reasons it is better than the alternatives for this codebase and team context\n- For security reviews: each vulnerability found (severity, affected code path, file:line reference), the remediation, and any areas that need further investigation by a human\n\nDo not hedge to the point of uselessness. If the evidence points to one conclusion, say so. If there is genuine uncertainty, say specifically what information would resolve it.\n\n### Notes\n\nCite specific files and line numbers for every specific claim. A claim without a file:line reference is an opinion, not a finding.\n","## Deep analysis\n\nultrathink\n\nPerform a thorough analysis of the described problem or codebase area. Do not skip steps under time or context pressure. This skill intentionally uses extended reasoning — use it.\n\n### Step 1: Gather all relevant context\n\nBefore forming any hypothesis, collect the raw material:\n\n- Read all files directly involved in the problem area\n- Check git history for the relevant files: `git log --oneline --follow -20 \u003Cfile>` for each key file, then `git show \u003Chash>` for commits that look relevant\n- Look for tests that cover the area: they describe the intended behavior\n- Look for related configuration (environment variables, feature flags, build configuration)\n- Check for any documentation: comments, ADRs, or README sections that mention the area\n\nDo not stop gathering context when you think you understand the issue. The full picture often requires reading more than the most obvious files.\n\n### Step 2: Identify the core issue or question\n\nState, in one or two sentences, what the fundamental question or problem is. Separate it from symptoms. For example:\n\n- Symptom: \"The API returns 500 errors intermittently\"\n- Core question: \"Is this a race condition in the connection pool, an unhandled exception in a specific code path, or an infrastructure issue?\"\n\nIf you are doing an architectural analysis, state the specific decision or tradeoff being evaluated.\n\n### Step 3: Consider multiple hypotheses or approaches\n\nDo not converge on the first plausible explanation. List at least three distinct hypotheses or approaches:\n\n- For bug analysis: three distinct root causes that could explain the observed behavior\n- For architecture decisions: three distinct design approaches with different tradeoff profiles\n- For security reviews: three distinct vulnerability classes to investigate\n\nFor each, note what evidence would confirm or rule it out.\n\n### Step 4: Evaluate tradeoffs\n\nFor each hypothesis or approach, evaluate:\n\n**Evidence for**: What in the codebase supports this explanation or approach?\n**Evidence against**: What contradicts it or makes it unlikely?\n**Risk**: If this hypothesis is wrong or this approach is chosen, what goes wrong?\n**Cost to verify or implement**: How much effort would confirming or executing this require?\n\nWork through the evidence systematically. Update your confidence in each hypothesis as you find more evidence. It is correct to change your assessment mid-analysis — note when you do and why.\n\n### Step 5: Give a concrete recommendation with justification\n\nState the conclusion clearly:\n\n- For bug analysis: the most likely root cause, the specific code location (file and line number), and the minimal fix\n- For architecture decisions: the recommended approach and the specific reasons it is better than the alternatives for this codebase and team context\n- For security reviews: each vulnerability found (severity, affected code path, file:line reference), the remediation, and any areas that need further investigation by a human\n\nDo not hedge to the point of uselessness. If the evidence points to one conclusion, say so. If there is genuine uncertainty, say specifically what information would resolve it.\n\n### Notes\n\nCite specific files and line numbers for every specific claim. A claim without a file:line reference is an opinion, not a finding.\n",{"name":5,"model":30,"title":5,"effort":31,"description":7,"disable-model-invocation":32},"opus","high",true,"main","55e6468ba43345d07c8a68de983e58403db57c25","src\u002Fcontent\u002Fdocs\u002F02-intermediate\u002Flesson-07-model-and-effort\u002Fexamples\u002Fdeep-analysis",1,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills","https:\u002F\u002Fclaude-with-skills.vercel.app","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-05-15 21:54:25",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":32},[45,48,51],{"tool":46,"command":47},"npx","npx skills add davila7\u002Fclaude-with-skills --skill deep-analysis",{"tool":49,"command":50},"bunx","bunx skills add davila7\u002Fclaude-with-skills --skill deep-analysis",{"tool":52,"command":53},"pnpm","pnpm dlx skills add davila7\u002Fclaude-with-skills --skill deep-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F02-intermediate\u002Flesson-07-model-and-effort\u002Fexamples\u002Fdeep-analysis\u002FSKILL.md",[56,61,67,73,77,81],{"path":57,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"LICENSE","许可证",1070,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fsystematic-debugging\u002FLICENSE",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fcondition-based-waiting-example.ts","SCRIPT","脚本",5054,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fsystematic-debugging\u002Freferences\u002Fcondition-based-waiting-example.ts",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fcondition-based-waiting.md","REFERENCE","参考文档",3767,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fsystematic-debugging\u002Freferences\u002Fcondition-based-waiting.md",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fdefense-in-depth.md",3665,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fsystematic-debugging\u002Freferences\u002Fdefense-in-depth.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Froot-cause-tracing.md",5546,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fsystematic-debugging\u002Freferences\u002Froot-cause-tracing.md",{"path":82,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Ffind-polluter.sh",3491,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fsystematic-debugging\u002Fscripts\u002Ffind-polluter.sh",[86,102,113,119,126,136],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":25},"01M6ADNEC991ZW0GD2D4MY6NEP","tag-version","Bump the package version and create an annotated git tag. Accepts a semantic version number (1.2.0) or a bump type (patch, minor, major). Does not push — use the publish skill to push. Use as part of a release workflow.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F03-advanced\u002Flesson-08-plugins-and-distribution\u002Fexamples\u002Frelease-plugin\u002Fskills\u002Ftag-version\u002FSKILL.md",[],[93,94,95,96,97,98,99,100,101],"tag version","workflow","create","release","git","push","npm","package","publish",{"skillNo":103,"name":96,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":25},"01M6ADNCNHCXNHVAW43ZV43ZC8","Run the complete release workflow: changelog entry, version bump, git tag, and GitHub release. Invokes changelog-entry, tag-version, and publish in sequence. Use when releasing a new version of the project.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F03-advanced\u002Flesson-08-plugins-and-distribution\u002Fexamples\u002Frelease-plugin\u002Fskills\u002Frelease\u002FSKILL.md",[],[96,97,108,99,109,110,101,111,112,94],"changelog","changelog entry","run","status","github",{"skillNo":114,"name":101,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":25},"01M6ADNAWDDDDX4CS69E1D496X","Push the current branch and all tags to origin, then create a GitHub release using the latest tag and its CHANGELOG.md entry. Use after tag-version to complete a release.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F03-advanced\u002Flesson-08-plugins-and-distribution\u002Fexamples\u002Frelease-plugin\u002Fskills\u002Fpublish\u002FSKILL.md",[],[101,98,112,95,96,97,108],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":25},"01M6ADN9MP0ASQ6SX14NEPP5XE","changelog-entry","Draft the changelog entry for all unreleased commits in Keep a Changelog format. Groups commits into Added, Changed, Fixed, Removed, and Security. Use before releasing a new version or when updating CHANGELOG.md.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F03-advanced\u002Flesson-08-plugins-and-distribution\u002Fexamples\u002Frelease-plugin\u002Fskills\u002Fchangelog-entry\u002FSKILL.md",[],[109,108,21,97],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":25},"01M6ADN8243TD9X8FH7FCQ608R","auto-format-on-edit","Automatically format code files after every edit using Prettier and ESLint. Active in the background whenever Claude edits a file. Formatting is silent — no prompts, no output unless a formatter fails. Use when you want consistent formatting enforced automatically during a coding session.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F03-advanced\u002Flesson-07-hooks-in-skills\u002Fexamples\u002Fauto-format-on-edit\u002FSKILL.md",[],[133,134,135],"auto format on edit","code","file",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":147,"publishedAt":25},"01M6ADN5VVNV7Y2WPYQA13M4ZQ","code-quality-audit","Run a comprehensive code quality audit covering security, performance, and maintainability. Use for quarterly audits, pre-release reviews, or when onboarding to a large codebase.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-with-skills\u002Fblob\u002Fmain\u002Fsrc\u002Fcontent\u002Fdocs\u002F03-advanced\u002Flesson-06-context-window-mastery\u002Fexamples\u002Flightweight-orchestrator\u002FSKILL.md",[142],{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[148,149,134,150,151,110,96,152,21],"code quality audit","audit","code quality","performance","onboarding"]