[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79XV99AM1651BWD83RRAMMB":3,"skill-same:01M79XV99AM1651BWD83RRAMMB":48},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M79XV99AM1651BWD83RRAMMB","plan-verifying-execution",null,"Guides judging whether completed execution actually did what the plan said, by checking claims against the repository rather than against the checklist.","wahidyankf\u002Fbeaver-nest","wahidyankf","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10843406?v=4","01M79XPZPDMM2D076E49HRJT8A","Wahidyan Kresna Fridayoka","01M79XPZQGDA87TNY0HYDREYDP",2,"MIT","https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fplan-verifying-execution\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: plan-verifying-execution\ndescription: >-\n  Guides judging whether completed execution actually did what the plan said, by checking claims against the repository\n  rather than against the checklist.\nwhen_to_use: >-\n  Use when auditing finished plan execution before archival, or when extending an execution checker's methodology.\ncompatibility: Requires read access to the repository and the ability to re-run its checks.\n---\n\n# Verifying Plan Execution\n\nThe temporal sibling of validating a draft. The same domains, asked after the fact, against the repository instead of\nagainst the text.\n\n## Verify Against the Repository, Not the Checklist\n\nA ticked box is a claim. The entire value of this audit is testing claims against what the repository now contains.\n\nDoes the file exist at the path the item named? Does the command still pass when re-run? Does the evidence establish the\ncriterion it is filed under, or merely sit next to it?\n\nAn audit that reads only `delivery.md` establishes that the plan is internally consistent — which was never in doubt,\nand which a plan can be while describing work that did not happen.\n\n## The Two Silent Failures\n\n**Scope drift.** Work added quietly because it seemed necessary, or dropped quietly because it turned out not to be.\nBoth are invisible in a checklist where every box is ticked. Compare what was delivered against what `prd.md` said, not\nagainst what `delivery.md` recorded.\n\n**Evidence that does not establish its claim.** A passing test filed under a criterion it does not exercise. A\nscreenshot filed as proof of a behaviour it does not show. These pass a glance and fail on reading.\n\n## Gates Must Have Actually Run\n\nA declared gate that never ran is not a passing gate. Check for the evidence record — command, commit, timestamp, result\n— rather than for the absence of complaints.\n\nA gate that returned findings and was then repaired is fine, and is a different thing from a gate nobody invoked.\n\n## Cleanup Is Proven, Not Assumed\n\nRe-list the paths the plan said would be removed. \"Cleanup ran\" is a claim of the same kind as a ticked box.\n\n## Knowledge Capture Is Part of Execution\n\nEvery learning must reach a durable owner or be discarded with a reason. An unrouted `learnings.md` blocks archival —\nthis is the step most often waived, and the one whose omission costs the most later, because the discovery is lost at\nexactly the moment it was cheapest to keep.\n\n## Blocking Is the Default\n\nReport what is unresolved plainly rather than passing with a caveat. A caveat in a verdict is read as a pass by everyone\nwho skims it.\n","# Verifying Plan Execution\n\nThe temporal sibling of validating a draft. The same domains, asked after the fact, against the repository instead of\nagainst the text.\n\n## Verify Against the Repository, Not the Checklist\n\nA ticked box is a claim. The entire value of this audit is testing claims against what the repository now contains.\n\nDoes the file exist at the path the item named? Does the command still pass when re-run? Does the evidence establish the\ncriterion it is filed under, or merely sit next to it?\n\nAn audit that reads only `delivery.md` establishes that the plan is internally consistent — which was never in doubt,\nand which a plan can be while describing work that did not happen.\n\n## The Two Silent Failures\n\n**Scope drift.** Work added quietly because it seemed necessary, or dropped quietly because it turned out not to be.\nBoth are invisible in a checklist where every box is ticked. Compare what was delivered against what `prd.md` said, not\nagainst what `delivery.md` recorded.\n\n**Evidence that does not establish its claim.** A passing test filed under a criterion it does not exercise. A\nscreenshot filed as proof of a behaviour it does not show. These pass a glance and fail on reading.\n\n## Gates Must Have Actually Run\n\nA declared gate that never ran is not a passing gate. Check for the evidence record — command, commit, timestamp, result\n— rather than for the absence of complaints.\n\nA gate that returned findings and was then repaired is fine, and is a different thing from a gate nobody invoked.\n\n## Cleanup Is Proven, Not Assumed\n\nRe-list the paths the plan said would be removed. \"Cleanup ran\" is a claim of the same kind as a ticked box.\n\n## Knowledge Capture Is Part of Execution\n\nEvery learning must reach a durable owner or be discarded with a reason. An unrouted `learnings.md` blocks archival —\nthis is the step most often waived, and the one whose omission costs the most later, because the discovery is lost at\nexactly the moment it was cheapest to keep.\n\n## Blocking Is the Default\n\nReport what is unresolved plainly rather than passing with a caveat. A caveat in a verdict is read as a pass by everyone\nwho skims it.\n",{"name":5,"description":7,"when_to_use":24,"compatibility":25},"Use when auditing finished plan execution before archival, or when extending an execution checker's methodology.","Requires read access to the repository and the ability to re-run its checks.","main","e6a21f0c020e81a73b28f6923bd898af898f17e4",".agents\u002Fskills\u002Fplan-verifying-execution",0,"https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest","https:\u002F\u002Fgithub.com\u002Fwahidyankf","Software Engineer","2026-11-15 04:32:43",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add wahidyankf\u002Fbeaver-nest --skill plan-verifying-execution",{"tool":40,"command":41},"bunx","bunx skills add wahidyankf\u002Fbeaver-nest --skill plan-verifying-execution",{"tool":43,"command":44},"pnpm","pnpm dlx skills add wahidyankf\u002Fbeaver-nest --skill plan-verifying-execution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fplan-verifying-execution\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M79Y04GAQQJXY8N9BD749WDJ","writing-browser-e2e-tests","Guides writing browser end-to-end tests that find elements as users do, wait on what the action produced, keep page knowledge in page objects, organize one feature per file, and run scenario-backed suites from generated specs.","https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-browser-e2e-tests\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M79Y0001QFQM6ZZQMG91MMN6","usability-heuristic-evaluation","Guides judging a running interface as a first-time user would, without its specifications: citing a named principle for every finding, walking each task step, reading labels and addresses for scent, and rating severity.","https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fusability-heuristic-evaluation\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M79XZX1AF54RXJRYZZ5KRA3Z","tooling-nx","Guides Nx workspace work under the Nx standard: selecting projects by the graph, adding a target only where a capability exists, tracing a stale cached pass to its missing input, and answering a module-boundary finding.","https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftooling-nx\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M79XZT0D49C6D7DHBE0960H6","programming-typescript","Guides the procedure for writing or changing TypeScript: loading the TypeScript standard first, driving each increment test-first, finding which rule a decision falls under, and confirming the gates before handing off.","https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fprogramming-typescript\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79XZPYGRRJ4CK2EGA3P5RYP","programming-shell","Guides shell work under the shell standards: checking the declared dialect first, deciding whether logic belongs in shell at all, tracing where exit-on-error does not reach, and testing the script as its callers run it.","https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fprogramming-shell\u002FSKILL.md",[],[],{"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":90,"publishedAt":19},"01M79XZKN2R9RR0MX66DEM5W2Z","programming-javascript","Guides JavaScript work under the JavaScript standard: confirming the file is type-checked, typing through JSDoc, validating input the checker cannot see, and noticing floating promises and swallowed errors before handing off.","https:\u002F\u002Fgithub.com\u002Fwahidyankf\u002Fbeaver-nest\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fprogramming-javascript\u002FSKILL.md",[],[]]