[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVGE076BNB3J7JDBGAKD2T":3,"skill-same:01M7AVGE076BNB3J7JDBGAKD2T":54},{"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":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M7AVGE076BNB3J7JDBGAKD2T","verification-before-completion",null,"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","MinhDuyDEV\u002Fmd-pikit","MinhDuyDEV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F94704296?v=4","01M7AVDRJB5JM5VG5B6K49X0EZ","Nguyễn Viết Minh Duy","01M7AVDRKDB3JPGHFE4HGK1Z5M",0,"MIT","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: verification-before-completion\ndescription: 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\nversion: 1.0.0\ntags: [workflow, code-quality]\ndependencies: []\nagent_types: [planner, worker, reviewer]\ntools: []\n---\n\n# Verification Before Completion\n\n## The Iron Law\n\n\u003CEXTREMELY-IMPORTANT>\n**No completion claim without evidence.** \"Done\" means the named verification command ran, exited 0, and its output was inspected. Not \"should work\", \"looks right\", or \"tested locally\". **Evidence before assertion, always.**\n\u003C\u002FEXTREMELY-IMPORTANT>\n\n## Use\n\nApply before any \"done\", \"fixed\", \"passing\", \"works\", or \"ready to merge\" claim; commit, push, PR, or after non-trivial edits. For pure prose or a directly observable artifact, cite the diff or artifact instead.\n\n## Evidence\n\n| Claim | Required evidence |\n| --- | --- |\n| Test, typecheck, lint, or build passes | Named command, exit 0, inspected output |\n| Behavior is X | Reproduction plus observed output |\n| Code matches spec | Diff or path + line range |\n| Bug is fixed | Regression fails without, passes with |\n| Shipped | All above plus commit or PR link |\n\nProse and code review are inspection, not verification.\n\n## Workflow\n\n1. Name the check before editing.\n2. Run it and show the relevant output; do not paraphrase.\n3. Inspect the exit code: non-zero makes the claim false. \"0 tests\", skipped tests, or hidden warnings do not pass.\n4. Cite the command, output, path, line range, SHA, or test artifact.\n5. If it fails, fix it or report the work as blocked; do not claim completion.\n\n## Red Flags and Rationalizations\n\n\"It should work\", \"I've tested it\", \"tests pass\", \"LGTM\", \"one-line change\", \"existing tests cover it\", \"CI will catch it\", \"I'm in a hurry\", and \"it's obvious\" are not evidence. Run the check again.\n\n## Report\n\nReport verification in normal, concise prose; do not emit a mandatory XML\u002FJSON wrapper. Match detail to the claim:\n\n- **Result:** say whether the requested result is verified, partial, blocked, or unverified.\n- **Evidence:** name the exact command or probe, exit status, relevant output, and path\u002FSHA when applicable.\n- **Limits:** state skipped checks, remaining risks, or unavailable review; do not imply stronger proof than the evidence supports.\n\nA one-line change may need only a diff review and focused command. A code change needs the relevant test\u002Ftypecheck output. Research needs cited sources and a clear separation of fact, inference, and uncertainty. If no check ran, name the exact intended command and say why; urgency or small scope does not waive verification. Do not claim completion from inspection alone.\n","# Verification Before Completion\n\n## The Iron Law\n\n\u003CEXTREMELY-IMPORTANT>\n**No completion claim without evidence.** \"Done\" means the named verification command ran, exited 0, and its output was inspected. Not \"should work\", \"looks right\", or \"tested locally\". **Evidence before assertion, always.**\n\u003C\u002FEXTREMELY-IMPORTANT>\n\n## Use\n\nApply before any \"done\", \"fixed\", \"passing\", \"works\", or \"ready to merge\" claim; commit, push, PR, or after non-trivial edits. For pure prose or a directly observable artifact, cite the diff or artifact instead.\n\n## Evidence\n\n| Claim | Required evidence |\n| --- | --- |\n| Test, typecheck, lint, or build passes | Named command, exit 0, inspected output |\n| Behavior is X | Reproduction plus observed output |\n| Code matches spec | Diff or path + line range |\n| Bug is fixed | Regression fails without, passes with |\n| Shipped | All above plus commit or PR link |\n\nProse and code review are inspection, not verification.\n\n## Workflow\n\n1. Name the check before editing.\n2. Run it and show the relevant output; do not paraphrase.\n3. Inspect the exit code: non-zero makes the claim false. \"0 tests\", skipped tests, or hidden warnings do not pass.\n4. Cite the command, output, path, line range, SHA, or test artifact.\n5. If it fails, fix it or report the work as blocked; do not claim completion.\n\n## Red Flags and Rationalizations\n\n\"It should work\", \"I've tested it\", \"tests pass\", \"LGTM\", \"one-line change\", \"existing tests cover it\", \"CI will catch it\", \"I'm in a hurry\", and \"it's obvious\" are not evidence. Run the check again.\n\n## Report\n\nReport verification in normal, concise prose; do not emit a mandatory XML\u002FJSON wrapper. Match detail to the claim:\n\n- **Result:** say whether the requested result is verified, partial, blocked, or unverified.\n- **Evidence:** name the exact command or probe, exit status, relevant output, and path\u002FSHA when applicable.\n- **Limits:** state skipped checks, remaining risks, or unavailable review; do not imply stronger proof than the evidence supports.\n\nA one-line change may need only a diff review and focused command. A code change needs the relevant test\u002Ftypecheck output. Research needs cited sources and a clear separation of fact, inference, and uncertainty. If no check ran, name the exact intended command and say why; urgency or small scope does not waive verification. Do not claim completion from inspection alone.\n",{"name":5,"tags":24,"tools":27,"version":28,"agent_types":29,"description":7,"dependencies":33},[25,26],"workflow","code-quality",[],"1.0.0",[30,31,32],"planner","worker","reviewer",[],"main","01207a96514af9f9c4d7d6cb594b936c6a9ddb10",".pi\u002Fskills\u002Fverification-before-completion","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV","2026-08-20 02:00:33",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add MinhDuyDEV\u002Fmd-pikit --skill verification-before-completion",{"tool":46,"command":47},"bunx","bunx skills add MinhDuyDEV\u002Fmd-pikit --skill verification-before-completion",{"tool":49,"command":50},"pnpm","pnpm dlx skills add MinhDuyDEV\u002Fmd-pikit --skill verification-before-completion","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",true,[],[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AVGJR1RSRVA3VJT8ZW4Y27","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization. Includes complete pressure testing methodology.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AVGAYJ6APXRB9QWBG7482S","typescript-coding-standards","Use when writing, refactoring, or reviewing TypeScript code that needs strong domain modeling, typed errors, schema parsing, safe adapters, test seams, or maintainable module boundaries.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Ftypescript-coding-standards\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7AVG8CE5BTR2CRFPHHVJCJZ","test-driven-development","Use when implementing a feature, bugfix, or behavior-changing refactor — require a failing behavior test before production code, then make the smallest change that passes.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"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":82,"publishedAt":19},"01M7AVG5FJH3WTG9XR2G0608ND","source-driven-development","Use when unfamiliar libraries, dependency internals, external APIs, framework behavior, migrations, or current ecosystem guidance require official documentation, version-matched source, read the tests, and cited evidence.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fsource-driven-development\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AVG37PZ77CF35KAR6E93ZJ","security-and-hardening","Use when auditing security, implementing authentication or authorization, handling secrets, or validating data across external trust boundaries.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fsecurity-and-hardening\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AVG0HSKDA2Q23AEWDT8TNS","prototype","Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says \"prototype this\", \"let me play with it\", \"try a few designs\".","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fprototype\u002FSKILL.md",[],[]]