[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BV0B7ST36ERTZCB8HQ6NHV":3,"skill-same:01M6BV0B7ST36ERTZCB8HQ6NHV":83},{"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":23,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":76},"01M6BV0B7ST36ERTZCB8HQ6NHV","deploy-audit",null,"Audit every commit pending between a base branch and a deployed branch\u002Ftag for deploy risk (migrations, config\u002Fsecret wiring completeness, feature-flag defaults, schema parity), then open the GitHub compare diff. Use when asked to audit pending commits, check deploy risk, review what is about to ship, or before opening a deploy PR or shipping to production.","drn\u002Fdots","drn","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F885841?v=4","01M6BTZJR7B1RVQRJKP0S70DQS","Darren Cheng","01M6BTZJWXCK41P3Z50BV8KWD9",23,"MIT","https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Fdeploy-audit\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"deploy","audit","deploy audit","commits","when","pending","wiring","for","true","compare","feature","schema","diff","use","branch","review","open","ship","risk","Production","shipping","pr","config","commit","github","2026-11-10 10:12:30",false,"---\nname: deploy-audit\ndescription: Audit every commit pending between a base branch and a deployed branch\u002Ftag for deploy risk (migrations, config\u002Fsecret wiring completeness, feature-flag defaults, schema parity), then open the GitHub compare diff. Use when asked to audit pending commits, check deploy risk, review what is about to ship, or before opening a deploy PR or shipping to production.\ndisable-model-invocation: true\n---\n\n# Pre-Deploy Risk Audit\n\nAudit the commits pending between a base branch and a deployed branch\u002Ftag,\nassess the risk of each change, and open the GitHub compare diff for human\nreview. This is an informational audit — it does not block or change anything\non its own.\n\n## Arguments\n\n- `$ARGUMENTS` - Optional: `\u003Cbase>..\u003Cdeployed>` (e.g. `master..production`), or\n  just the deployed ref if the base is the repo's default branch. If omitted,\n  detect candidates from context below and ask the user to confirm.\n\n## Context\n\n- Remote: !`git remote get-url origin 2>\u002Fdev\u002Fnull | head -1`\n- Default branch: !`git branch -r 2>\u002Fdev\u002Fnull | grep -oE 'origin\u002F(main|master)' | head -1`\n- Remote branches: !`git branch -r 2>\u002Fdev\u002Fnull | grep -viE 'HEAD|dependabot' | head -30`\n- Recent tags: !`git tag --sort=-creatordate 2>\u002Fdev\u002Fnull | head -10`\n\n## Instructions\n\nWork through the following steps in order, gathering enough evidence at each\none to give the final risk report real teeth rather than a generic checklist.\n\n### Step 1: Determine the two refs\n\nParse `$ARGUMENTS` for `\u003Cbase>..\u003Cdeployed>`. If only one ref is given, treat it\nas the deployed ref and use the detected default branch as base. If nothing is\ngiven, look at the remote branches\u002Ftags in Context above for likely\ncandidates (a `production`\u002F`release`\u002F`deploy` branch, or the most recent tag)\nand ask the user to confirm the base and deployed refs before proceeding.\n\nRefs and the org\u002Frepo derived from the remote URL are treated as untrusted\ninput for shell purposes: if either contains characters outside\n`[A-Za-z0-9._\u002F-]`, do not interpolate it directly into a shell command —\nquote it and confirm with the user first.\n\nRun `git fetch origin` for both refs to ensure they are current.\n\n### Step 2: Enumerate pending commits\n\n```\ngit log --oneline \u003Cdeployed>..\u003Cbase>\ngit diff --stat \u003Cdeployed>..\u003Cbase>\n```\n\nIf this returns nothing, report \"Nothing pending — `\u003Cdeployed>` and `\u003Cbase>`\nare in sync\" and stop.\n\nRead full commit messages for risk signal:\n\n```\ngit log --format='%H %s%n%b%n---' \u003Cdeployed>..\u003Cbase>\n```\n\nCommit bodies often carry the actual risk context (design rationale, what a\nmigration does, why a flag was added) that the subject line does not.\n\n### Step 3: Assess migration safety\n\nIf the diff touches migration files (schema migrations, database migration\ndirectories — detect the project's convention rather than assuming one path),\nread each new migration and classify it:\n\n- **Additive\u002Fsafe**: new nullable column, new table, new index created\n  concurrently\u002Fonline\n- **Requires care**: backfill needed, column made non-nullable, default value\n  added to an existing large table\n- **Destructive**: column\u002Ftable drop, rename, type change without a\n  compatibility shim\n\nFlag anything in the latter two categories explicitly.\n\n### Step 4: Check schema parity\n\nIf the project maintains more than one copy of a schema file (a canonical\nschema plus mirrored\u002Fgenerated copies used by other services or packages —\ncheck the project's own docs\u002Frules for this convention, or search for\nmultiple files with the same schema filename), diff the canonical version\nagainst every mirror. Flag any mismatch in version or content.\n\nIf the project has no such mirrored-schema convention, skip this step and\nsay so.\n\n### Step 5: Trace config and secret wiring\n\nFor every new environment variable or secret introduced by the diff, trace it\nthrough the **full chain** the project uses to get a value from\ninfrastructure config into a running process — for example: an IaC variable\ndeclaration, through any module wiring, into the per-environment secret\ndefinitions, into the actual task\u002Fservice\u002Fcontainer definition that reads it.\n\nA secret or parameter existing in a vault\u002Fparameter store is not the same as\nit being wired anywhere a running process reads it — check for a reference at\nevery layer, not just that the value was provisioned. This is the single\nhighest-value check in this audit: a half-wired chain (defined but never\nreferenced downstream) will not be caught by `terraform plan` or similar and\nfails silently in production.\n\nIf the project has no IaC\u002Fconfig-chain convention to trace, skip this step\nand say so.\n\n### Step 6: Check feature-flag defaults\n\nIf the diff introduces calls to a feature-flag SDK for a new flag key, look up\nthat flag's default\u002Ftargeting state in whatever flag-management tooling the\nproject has available (search with ToolSearch for a feature-flag MCP tool, or\ncheck for a flag-provider CLI). Confirm new flags default to **off**, or note\nexplicitly if a new flag is live-by-default and why.\n\nIf no flag-management tooling is discoverable, skip this step and say so.\n\n### Step 7: Open the compare diff\n\nDerive `\u003Corg>\u002F\u003Crepo>` from the remote URL in Context and open:\n\n```\nhttps:\u002F\u002Fgithub.com\u002F\u003Corg>\u002F\u003Crepo>\u002Fcompare\u002F\u003Cdeployed>...\u003Cbase>\n```\n\nOn macOS use `open \"\u003Curl>\"`; on Linux use `xdg-open \"\u003Curl>\"`; otherwise print\nthe URL for the user to open manually.\n\n### Step 8: Report\n\nSummarize per pending change (or per logical group of changes) with a\nlow\u002Fmoderate\u002Fhigh risk rating, and call out explicitly:\n\n- Any destructive or backfill-requiring migrations\n- Any schema mirror mismatches\n- Any half-wired or unverified config\u002Fsecret chains\n- Any new flags that are live-by-default rather than off\n- Any risk category that was skipped because no tooling was available to\n  verify it\n\nDo not silently drop a skipped category from the summary — an unverified\ncheck is different from a verified-safe one.\n","# Pre-Deploy Risk Audit\n\nAudit the commits pending between a base branch and a deployed branch\u002Ftag,\nassess the risk of each change, and open the GitHub compare diff for human\nreview. This is an informational audit — it does not block or change anything\non its own.\n\n## Arguments\n\n- `$ARGUMENTS` - Optional: `\u003Cbase>..\u003Cdeployed>` (e.g. `master..production`), or\n  just the deployed ref if the base is the repo's default branch. If omitted,\n  detect candidates from context below and ask the user to confirm.\n\n## Context\n\n- Remote: !`git remote get-url origin 2>\u002Fdev\u002Fnull | head -1`\n- Default branch: !`git branch -r 2>\u002Fdev\u002Fnull | grep -oE 'origin\u002F(main|master)' | head -1`\n- Remote branches: !`git branch -r 2>\u002Fdev\u002Fnull | grep -viE 'HEAD|dependabot' | head -30`\n- Recent tags: !`git tag --sort=-creatordate 2>\u002Fdev\u002Fnull | head -10`\n\n## Instructions\n\nWork through the following steps in order, gathering enough evidence at each\none to give the final risk report real teeth rather than a generic checklist.\n\n### Step 1: Determine the two refs\n\nParse `$ARGUMENTS` for `\u003Cbase>..\u003Cdeployed>`. If only one ref is given, treat it\nas the deployed ref and use the detected default branch as base. If nothing is\ngiven, look at the remote branches\u002Ftags in Context above for likely\ncandidates (a `production`\u002F`release`\u002F`deploy` branch, or the most recent tag)\nand ask the user to confirm the base and deployed refs before proceeding.\n\nRefs and the org\u002Frepo derived from the remote URL are treated as untrusted\ninput for shell purposes: if either contains characters outside\n`[A-Za-z0-9._\u002F-]`, do not interpolate it directly into a shell command —\nquote it and confirm with the user first.\n\nRun `git fetch origin` for both refs to ensure they are current.\n\n### Step 2: Enumerate pending commits\n\n```\ngit log --oneline \u003Cdeployed>..\u003Cbase>\ngit diff --stat \u003Cdeployed>..\u003Cbase>\n```\n\nIf this returns nothing, report \"Nothing pending — `\u003Cdeployed>` and `\u003Cbase>`\nare in sync\" and stop.\n\nRead full commit messages for risk signal:\n\n```\ngit log --format='%H %s%n%b%n---' \u003Cdeployed>..\u003Cbase>\n```\n\nCommit bodies often carry the actual risk context (design rationale, what a\nmigration does, why a flag was added) that the subject line does not.\n\n### Step 3: Assess migration safety\n\nIf the diff touches migration files (schema migrations, database migration\ndirectories — detect the project's convention rather than assuming one path),\nread each new migration and classify it:\n\n- **Additive\u002Fsafe**: new nullable column, new table, new index created\n  concurrently\u002Fonline\n- **Requires care**: backfill needed, column made non-nullable, default value\n  added to an existing large table\n- **Destructive**: column\u002Ftable drop, rename, type change without a\n  compatibility shim\n\nFlag anything in the latter two categories explicitly.\n\n### Step 4: Check schema parity\n\nIf the project maintains more than one copy of a schema file (a canonical\nschema plus mirrored\u002Fgenerated copies used by other services or packages —\ncheck the project's own docs\u002Frules for this convention, or search for\nmultiple files with the same schema filename), diff the canonical version\nagainst every mirror. Flag any mismatch in version or content.\n\nIf the project has no such mirrored-schema convention, skip this step and\nsay so.\n\n### Step 5: Trace config and secret wiring\n\nFor every new environment variable or secret introduced by the diff, trace it\nthrough the **full chain** the project uses to get a value from\ninfrastructure config into a running process — for example: an IaC variable\ndeclaration, through any module wiring, into the per-environment secret\ndefinitions, into the actual task\u002Fservice\u002Fcontainer definition that reads it.\n\nA secret or parameter existing in a vault\u002Fparameter store is not the same as\nit being wired anywhere a running process reads it — check for a reference at\nevery layer, not just that the value was provisioned. This is the single\nhighest-value check in this audit: a half-wired chain (defined but never\nreferenced downstream) will not be caught by `terraform plan` or similar and\nfails silently in production.\n\nIf the project has no IaC\u002Fconfig-chain convention to trace, skip this step\nand say so.\n\n### Step 6: Check feature-flag defaults\n\nIf the diff introduces calls to a feature-flag SDK for a new flag key, look up\nthat flag's default\u002Ftargeting state in whatever flag-management tooling the\nproject has available (search with ToolSearch for a feature-flag MCP tool, or\ncheck for a flag-provider CLI). Confirm new flags default to **off**, or note\nexplicitly if a new flag is live-by-default and why.\n\nIf no flag-management tooling is discoverable, skip this step and say so.\n\n### Step 7: Open the compare diff\n\nDerive `\u003Corg>\u002F\u003Crepo>` from the remote URL in Context and open:\n\n```\nhttps:\u002F\u002Fgithub.com\u002F\u003Corg>\u002F\u003Crepo>\u002Fcompare\u002F\u003Cdeployed>...\u003Cbase>\n```\n\nOn macOS use `open \"\u003Curl>\"`; on Linux use `xdg-open \"\u003Curl>\"`; otherwise print\nthe URL for the user to open manually.\n\n### Step 8: Report\n\nSummarize per pending change (or per logical group of changes) with a\nlow\u002Fmoderate\u002Fhigh risk rating, and call out explicitly:\n\n- Any destructive or backfill-requiring migrations\n- Any schema mirror mismatches\n- Any half-wired or unverified config\u002Fsecret chains\n- Any new flags that are live-by-default rather than off\n- Any risk category that was skipped because no tooling was available to\n  verify it\n\nDo not silently drop a skipped category from the summary — an unverified\ncheck is different from a verified-safe one.\n",{"name":5,"description":7,"disable-model-invocation":54},true,"master","427f62a9fc82624977516767979411f885161ac5","agents\u002Fskills\u002Fdeploy-audit",4,"https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots","https:\u002F\u002Fgithub.com\u002Fdrn","https:\u002F\u002Fdrn.dev","CTO & Co-Founder @thanx","2026-11-12 16:13:13",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":54},[66,69,72],{"tool":67,"command":68},"npx","npx skills add drn\u002Fdots --skill deploy-audit",{"tool":70,"command":71},"bunx","bunx skills add drn\u002Fdots --skill deploy-audit",{"tool":73,"command":74},"pnpm","pnpm dlx skills add drn\u002Fdots --skill deploy-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Fdeploy-audit\u002FSKILL.md",[77],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fpatterns.md","REFERENCE","参考文档",21263,"https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002F10x-swe\u002Fskills\u002Fpython-performance-optimization\u002Freferences\u002Fpatterns.md",[84,111,131,142,166,184],{"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":93,"publishedAt":49},"01M70KJSG2P5Y3N95MGSGKJ8VA","batch-pr-review","Review a batch of pull requests together, describe every change in plain language, and build a private Claude artifact that eases human review, with a severity-tagged and verified findings list. Use when asked to review several PRs, a stack of PRs, PRs listed in a Slack thread or message, or to summarize a batch of PRs for a reviewer.","https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Fbatch-pr-review\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通",[94,95,45,96,39,97,28,98,99,100,101,102,103,104,105,106,107,108,109,110],"batch pr review","batch","pr review","reviewer","parse","scripts","human","artifact","message","write","read","stack","gh pr","Bash","change","pull requests","slack",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":120,"publishedAt":49},"01M6BV2G3ZAS76C40S3YBY6R61","plannotator-setup-goal","Create reviewed Codex goal setup packages for long-running \u002Fgoal work. Use when the user wants to turn an idea, backlog, project mission, or vague objective into durable goal files under a project goals slug folder, with Plannotator review gates for brief, narrative plan with acceptance criteria, verification, blockers, and the final \u002Fgoal prompt.","https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Fplannotator-setup-goal\u002FSKILL.md",[117],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[121,122,123,124,125,126,127,128,129,130,39],"plannotator setup goal","setup","verification","plan","plannotator review","brief","acceptance","create","packages","codex",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":49},"01M6BV26Y6GTDMQZYXFRWKEC08","plannotator-annotate","Open Plannotator's annotation UI for a markdown file, converted HTML file, URL, or folder and then respond to the returned annotations.","https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Fplannotator-annotate\u002FSKILL.md",[],[138,139,40,140,141],"plannotator annotate","markdown","ui","file",{"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":149,"publishedAt":49},"01M6BV44RGGTRRFGWMYCR3BQ1P","write-skill","Create or improve a Claude Code skill\u002Fslash command with best practices for structure, dynamic context, and safety. Use for creating new skills, improving existing ones, or learning skill authoring.","https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Fwrite-skill\u002FSKILL.md",[148],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},[103,150,151,152,153,154,31,155,156,37,157,158,159,160,161,162,163,164,165,128],"write skill","with","authoring","code skill","code","structure","claude code skill","context","command","improve","learning","Safety","best practices","Existing","new","skill authoring",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":49},"01M6BV4390BFK30F1T51SAJPAV","wrapup","End-of-session checklist that detects loose ends — uncommitted changes, unmerged branches, learnings to capture, handoffs needed — and routes to the right skills. Use for session closeout, wrapping up, end of day, or \"anything else to capture\".","https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Fwrapup\u002FSKILL.md",[],[168,173,174,175,31,176,177,178,179,180,37,181,182,183],"session closeout","up","changes","end of day","end","branches","learnings","checklist","session","closeout","capture",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":49},"01M6BV41ZZ051JX2B3CB5WARZM","tts","Read text aloud using text-to-speech. Use when the user says \"speak to me\", \"read to me\", \"read this aloud\", \"say this\", \"speak the summary\", or asks to hear something spoken.","https:\u002F\u002Fgithub.com\u002Fdrn\u002Fdots\u002Fblob\u002Fmaster\u002Fagents\u002Fskills\u002Ftts\u002FSKILL.md",[],[186,37,191,104,192,193,194,195,28,196,197,198],"user","speak","text","speech","say","text-to-speech","me","summary"]