[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JK3X78N586FEP9ZX5YH5H":3,"skill-same:01M71JK3X78N586FEP9ZX5YH5H":75},{"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":24,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":5,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M71JK3X78N586FEP9ZX5YH5H","maintain-verification-skill",null,"Audit and repair a project verification skill and its feature map against current source and live behavior. Use whenever the user asks to maintain, refresh, or audit a verify skill, its harness, or its user-facing feature coverage.","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fmaintain-verification-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fmaintain-verification-skill\u002FSKILL.md",[19],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"maintain verification skill","maintain","verification","user","source","live","use","map","behavior","verify skill","project","audit","feature","verify","repair","refresh","harness","coverage","2026-11-10 10:12:30",false,"---\nname: maintain-verification-skill\ndescription: Audit and repair a project verification skill and its feature map against current source and live behavior. Use whenever the user asks to maintain, refresh, or audit a verify skill, its harness, or its user-facing feature coverage.\n---\n\n# Maintain a verification skill\n\nKeep a project-local verification skill honest as the product changes. The unit of rigor is one feature: every mapped feature receives source coverage and a live drive.\n\n## Outcomes\n\n- **clean:** every feature received source and live coverage; no correction is needed.\n- **changed:** proven corrections are ready locally, or published when the user authorized publication.\n- **blocked:** coverage or a safe correction could not finish; name the exact blocker.\n\n## Locate and bound the target\n\nSearch established project roots, including `.agents\u002Fskills\u002Fverify-*`, `.claude\u002Fskills\u002Fverify-*`, and `.cursor\u002Fskills\u002Fverify-*`. Resolve symlinks and edit only the canonical directory. If several canonical candidates remain, ask which one. If none exists, route to `create-verification-skill`.\n\nOnly edit the verification skill's `SKILL.md`, `features\u002F`, and owned harness helpers. Never alter product code during a maintenance pass. Product regressions are findings, not documentation fixes.\n\n| Capability | Preferred route | Fallback |\n|---|---|---|\n| Source wave | One authorized read-only worker per feature, launched within harness limits | Partition or read features sequentially with the same return schema |\n| Live drive | The target skill's declared browser, PTY, API, or platform harness | Mark the feature blocked or verified-unreachable with the attempted route and missing capability |\n| Publication | Create one PR only when the user's request authorizes external publication | Leave a verified local diff and report it |\n\n## Pass\n\n1. **Index hygiene.** Compare the feature index with sibling files. Fix missing, extra, duplicate, and dead entries.\n2. **Source wave.** For every feature file, explain current user-visible behavior from source, cite entry points, flag likely drift, and return one concise live recipe. Workers never drive or edit. Only delegate when current policy permits it.\n3. **Reconcile.** Account for every feature result, spot-check cited drift, combine recipes into the fewest safe app states, and sweep recent source churn for missing user-facing surfaces. Require a concrete source path before adding one.\n4. **Live pass.** Follow the verification skill's launch model: one owned long-lived instance for a server\u002FUI, or a fresh isolated session per short-lived CLI drive. Exercise every feature at least once.\n5. **Triage.** Wrong user-facing instructions are doc drift. Working behavior the harness cannot drive is a harness gap. Broken product behavior is a product gap to report outside this edit scope.\n6. **Re-prove corrections.** Re-drive any changed harness or recipe. Re-read every changed file.\n7. **Ship or stop.** Produce at most one authorized PR. For clean, locally changed, or blocked outcomes, do not create external state without authorization.\n\n## Live invariants\n\n- Doctor before the first drive, each fresh session, and after surprising behavior or failed drives.\n- Reset or relaunch a wedged user state even when process health looks normal.\n- Preserve evidence through every cleanup and verify it still exists.\n- Clean residue from failed drives; stop only instances the run owns.\n- Report an unreachable feature only with the concrete prerequisite and attempted route.\n- Tear down after the final drive and any re-proofs; retain evidence.\n\nReturn feature coverage, confirmed drift, changes, product gaps, proof paths, cleanup status, and one outcome label.\n\n\u003C!-- Adapted from poteto\u002Fpstack maintain-verification-skill, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n","# Maintain a verification skill\n\nKeep a project-local verification skill honest as the product changes. The unit of rigor is one feature: every mapped feature receives source coverage and a live drive.\n\n## Outcomes\n\n- **clean:** every feature received source and live coverage; no correction is needed.\n- **changed:** proven corrections are ready locally, or published when the user authorized publication.\n- **blocked:** coverage or a safe correction could not finish; name the exact blocker.\n\n## Locate and bound the target\n\nSearch established project roots, including `.agents\u002Fskills\u002Fverify-*`, `.claude\u002Fskills\u002Fverify-*`, and `.cursor\u002Fskills\u002Fverify-*`. Resolve symlinks and edit only the canonical directory. If several canonical candidates remain, ask which one. If none exists, route to `create-verification-skill`.\n\nOnly edit the verification skill's `SKILL.md`, `features\u002F`, and owned harness helpers. Never alter product code during a maintenance pass. Product regressions are findings, not documentation fixes.\n\n| Capability | Preferred route | Fallback |\n|---|---|---|\n| Source wave | One authorized read-only worker per feature, launched within harness limits | Partition or read features sequentially with the same return schema |\n| Live drive | The target skill's declared browser, PTY, API, or platform harness | Mark the feature blocked or verified-unreachable with the attempted route and missing capability |\n| Publication | Create one PR only when the user's request authorizes external publication | Leave a verified local diff and report it |\n\n## Pass\n\n1. **Index hygiene.** Compare the feature index with sibling files. Fix missing, extra, duplicate, and dead entries.\n2. **Source wave.** For every feature file, explain current user-visible behavior from source, cite entry points, flag likely drift, and return one concise live recipe. Workers never drive or edit. Only delegate when current policy permits it.\n3. **Reconcile.** Account for every feature result, spot-check cited drift, combine recipes into the fewest safe app states, and sweep recent source churn for missing user-facing surfaces. Require a concrete source path before adding one.\n4. **Live pass.** Follow the verification skill's launch model: one owned long-lived instance for a server\u002FUI, or a fresh isolated session per short-lived CLI drive. Exercise every feature at least once.\n5. **Triage.** Wrong user-facing instructions are doc drift. Working behavior the harness cannot drive is a harness gap. Broken product behavior is a product gap to report outside this edit scope.\n6. **Re-prove corrections.** Re-drive any changed harness or recipe. Re-read every changed file.\n7. **Ship or stop.** Produce at most one authorized PR. For clean, locally changed, or blocked outcomes, do not create external state without authorization.\n\n## Live invariants\n\n- Doctor before the first drive, each fresh session, and after surprising behavior or failed drives.\n- Reset or relaunch a wedged user state even when process health looks normal.\n- Preserve evidence through every cleanup and verify it still exists.\n- Clean residue from failed drives; stop only instances the run owns.\n- Report an unreachable feature only with the concrete prerequisite and attempted route.\n- Tear down after the final drive and any re-proofs; retain evidence.\n\nReturn feature coverage, confirmed drift, changes, product gaps, proof paths, cleanup status, and one outcome label.\n\n\u003C!-- Adapted from poteto\u002Fpstack maintain-verification-skill, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n",{"name":5,"description":7},"main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add caezium\u002Fskills --skill maintain-verification-skill",{"tool":63,"command":64},"bunx","bunx skills add caezium\u002Fskills --skill maintain-verification-skill",{"tool":66,"command":67},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill maintain-verification-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fmaintain-verification-skill\u002FSKILL.md",true,[71],{"path":72,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":16},"LICENSE","许可证",1067,[76,97,125,143,164,185],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":90,"publishedAt":43},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[82,85],{"categoryNo":83,"categoryName":84,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[91,92,93,94,31,95,96],"writing for agents","for","writing","editing","documents","when",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":106,"publishedAt":43},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000010","后端与接口",[99,107,108,109,110,111,112,113,114,115,116,117,118,92,119,120,121,122,123,124],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","workers","best practices","store",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":43},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[132,122,123,133,134,135,92,107,136,109,137,99,93,121,96,138,139,140,141,142],"workers best practices","observability","reviews","promises","worker","new","code","common","streaming","state","anti-patterns",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":43},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[145,118,150,92,151,152,153,154,31,155,96,156,157,158,159,160,161,162,163,112],"setting","up","ci","provisioning infrastructure","only","invoke","Bash","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":168,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":43},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[166,172,173,174,175,92,176,177,31,178,179,180,33,181,182,183,184],"sources","thresholds","evidence","relevant","runtime","design","decisions","work","how","read","data","rationale","returns",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":43},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[191],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},[193,194,195,196,197,92,198,199,200,201,31,156,202,203,204,162,205,181,206,207],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","tasks","with","slack","calendar","flags","grep"]