[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79EMYJ4GMSAP6QB5SHH8P3B":3,"skill-same:01M79EMYJ4GMSAP6QB5SHH8P3B":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79EMYJ4GMSAP6QB5SHH8P3B","behavioral-evidence",null,"Independently verify an accepted objective with real evidence (computer use, browser, the repository's verification CLI) and confirm the change adds no automated tests.","AO-HyS\u002Fdevelopment-system","AO-HyS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286554351?v=4","01M79DCXZGC6076EH5QATNXCY2","AO HyS","01M79DCY06TSBCJ946VP0BT0RG",0,"MIT","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.3.0\u002Fskills\u002Finternal\u002Fbehavioral-evidence\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: behavioral-evidence\ndescription: Independently verify an accepted objective with real evidence (computer use, browser, the repository's verification CLI) and confirm the change adds no automated tests.\n---\n\n# Behavioral evidence\n\nReal verification is the evidence. Computer use, the browser and the\nrepository's verification CLI and feature map observe the accepted behavior\nthrough its public interface; a green check, count or coverage percentage never\noverrides the accepted objective.\n\n## No automated tests\n\nThe change adds no automated tests, test runner configuration, test scripts,\ntest dependencies or CI test steps. Run\n`development-system check-no-tests --root \u003Crepository> --json` and report its\nfindings; automated tests found in the change are deleted, not kept or\nstrengthened. Report the actual missing behavior and the smallest real\nobservation that would prove it instead of proposing a test.\n\n## Independent verification\n\nThe implementer's own checks are never the only evidence. A context-isolated\nreviewer derives the oracle from the accepted objective and public interface,\nobserves the behavior for real (computer use, the browser, the repository's\nverification CLI), rejects narrowed or unsupported runs, and reports the verdict\nagainst every acceptance criterion, including unproven items. Independent\nreview returns the actual evidence gap; it does not invent a check per form or\nfeature.\n\n## Web flows: QuickE2E with Jev (2.3.0)\n\nDrive web flows with QuickE2E on its documented Jev engine. Jev is prepaid\n(TypeSafe key at `~\u002F.config\u002Fjevgrep\u002Fcredentials.json`), so cost bans on hosted\ninference do not apply to it; data limits still do. QuickE2E calls Jev through\nOpenRouter, so load the Development System preload that sends the same request\nto TypeSafe.\n\nQuickE2E is an external tool, not shipped in this release. Install it once,\npinned, outside any repository; skip this when\n`node ~\u002F.development-system\u002Ftools\u002Fquicke2e\u002Fbin\u002Fquicke2e.mjs --help` already\nworks and `git -C ~\u002F.development-system\u002Ftools\u002Fquicke2e rev-parse HEAD` shows\nthat commit. The same commands move an existing clone to the pin:\n\n```bash\n[ -d ~\u002F.development-system\u002Ftools\u002Fquicke2e\u002F.git ] || git clone https:\u002F\u002Fgithub.com\u002Fdmoka\u002Fquicke2e ~\u002F.development-system\u002Ftools\u002Fquicke2e\ngit -C ~\u002F.development-system\u002Ftools\u002Fquicke2e fetch origin\ngit -C ~\u002F.development-system\u002Ftools\u002Fquicke2e checkout 98f74b6ceb44e8eb68c0bc176e522983639b9521   # 0.5.0\n(cd ~\u002F.development-system\u002Ftools\u002Fquicke2e && npm ci && npx playwright install chromium)\n```\n\nThen run a flow:\n\n```bash\nOPENROUTER_API_KEY=via-typesafe node --import \"$HOME\u002F.codex\u002Fdevelopment-system\u002Fruntime\u002Fquicke2e\u002Ftypesafe-jev.mjs\" \\\n  \"$HOME\u002F.development-system\u002Ftools\u002Fquicke2e\u002Fbin\u002Fquicke2e.mjs\" run \u003Cflow.mjs> --base \u003Curl> --engine jev --trace \u003Cprivate-dir> --video \u003Cprivate-dir>\n```\n\n- Log in with the repository's test accounts (names from its env files, never\n  printed) and pass a Playwright `storageState`. Wait for `networkidle` before\n  the first click on dev servers that hydrate late.\n- Keep the flow file under `$HOME\u002F.development-system\u002Fprivate\u002Fverification\u002F\u003Crun-id>\u002F`,\n  never in the repository. Do not pass `--emit`: no replay spec is kept, so this\n  is live verification, not an automated test (operator decision 2026-10-13);\n  keeping a replay spec needs an operator test grant. A failed flow is re-run\n  live, so renamed labels need no maintenance.\n- Prove permissions both ways: the allowed role reaches the end state and a\n  role without the permission is observed refused.\n- Assert side effects (rows, emails, payments in test mode), not just text.\n- Clean up the records the flow created and stop every server you started.\n\nThe T3 browser remains the tool for visual judgment and exploration without a\ndefined flow.\n\nLines of code, file counts, identifier length and minified formatting are not\nquality targets. Complexity signals may inform diagnosis but cannot fail a run.\n\n## Output\n\nReturn the check-no-tests result, each acceptance criterion with its real\nevidence (passed, failed or not reached), the independent verdict, every\nself-grading finding and any unproven behavior. This skill is read-only and\nnever edits.\n\n## Authorized Claude Code account recovery (1.39.0)\n\nFor Claude Code review and computer use, the operator explicitly authorizes the\nlocal Codex credential-home sequence followed by a fresh native Claude role.\nRun codex-review once; it discovers existing profiles without copying credentials\nand records at most two sequential profile attempts. Read receipt.json as well as findings.\nWhen status is fallback_required and fallback.eligible is true, immediately\ndispatch reviewer (plan, diff or security), visual-reviewer (image review) or\nbrowser-qa (computer use) through the native Agent tool with the original packet.\nCopy fallback.prompt verbatim from the receipt; it contains the original packet\nand Codex fallback:, Codex fallback receipt: and Codex fallback packet: lines.\nThe guard verifies the full dispatched packet, hash, root, mode and Task-Id and\nrejects resume so the native agent stays fresh. Computer-use fallback receipts\nare admitted once only; a consumed receipt requires reconciliation, not replay.\nDo not let a failed Codex attempt silently omit the independent review or absorb\nit into the coordinator. Preserve the endpoint and actual capability requirements.\nCancellation, safety refusal and uncertain computer-use effects are not fallback\npermission: reconcile observed state before more actions. If the native role lacks\nvision or an authorized browser, retain the gap and continue independent work.\nReport the provider change and actual or unknown identity. This explicit Claude\nexception does not change restricted Codex-only tasks or Headroom's same-account\nper-invocation contract. HOME installation does not prove live host loading.\n","# Behavioral evidence\n\nReal verification is the evidence. Computer use, the browser and the\nrepository's verification CLI and feature map observe the accepted behavior\nthrough its public interface; a green check, count or coverage percentage never\noverrides the accepted objective.\n\n## No automated tests\n\nThe change adds no automated tests, test runner configuration, test scripts,\ntest dependencies or CI test steps. Run\n`development-system check-no-tests --root \u003Crepository> --json` and report its\nfindings; automated tests found in the change are deleted, not kept or\nstrengthened. Report the actual missing behavior and the smallest real\nobservation that would prove it instead of proposing a test.\n\n## Independent verification\n\nThe implementer's own checks are never the only evidence. A context-isolated\nreviewer derives the oracle from the accepted objective and public interface,\nobserves the behavior for real (computer use, the browser, the repository's\nverification CLI), rejects narrowed or unsupported runs, and reports the verdict\nagainst every acceptance criterion, including unproven items. Independent\nreview returns the actual evidence gap; it does not invent a check per form or\nfeature.\n\n## Web flows: QuickE2E with Jev (2.3.0)\n\nDrive web flows with QuickE2E on its documented Jev engine. Jev is prepaid\n(TypeSafe key at `~\u002F.config\u002Fjevgrep\u002Fcredentials.json`), so cost bans on hosted\ninference do not apply to it; data limits still do. QuickE2E calls Jev through\nOpenRouter, so load the Development System preload that sends the same request\nto TypeSafe.\n\nQuickE2E is an external tool, not shipped in this release. Install it once,\npinned, outside any repository; skip this when\n`node ~\u002F.development-system\u002Ftools\u002Fquicke2e\u002Fbin\u002Fquicke2e.mjs --help` already\nworks and `git -C ~\u002F.development-system\u002Ftools\u002Fquicke2e rev-parse HEAD` shows\nthat commit. The same commands move an existing clone to the pin:\n\n```bash\n[ -d ~\u002F.development-system\u002Ftools\u002Fquicke2e\u002F.git ] || git clone https:\u002F\u002Fgithub.com\u002Fdmoka\u002Fquicke2e ~\u002F.development-system\u002Ftools\u002Fquicke2e\ngit -C ~\u002F.development-system\u002Ftools\u002Fquicke2e fetch origin\ngit -C ~\u002F.development-system\u002Ftools\u002Fquicke2e checkout 98f74b6ceb44e8eb68c0bc176e522983639b9521   # 0.5.0\n(cd ~\u002F.development-system\u002Ftools\u002Fquicke2e && npm ci && npx playwright install chromium)\n```\n\nThen run a flow:\n\n```bash\nOPENROUTER_API_KEY=via-typesafe node --import \"$HOME\u002F.codex\u002Fdevelopment-system\u002Fruntime\u002Fquicke2e\u002Ftypesafe-jev.mjs\" \\\n  \"$HOME\u002F.development-system\u002Ftools\u002Fquicke2e\u002Fbin\u002Fquicke2e.mjs\" run \u003Cflow.mjs> --base \u003Curl> --engine jev --trace \u003Cprivate-dir> --video \u003Cprivate-dir>\n```\n\n- Log in with the repository's test accounts (names from its env files, never\n  printed) and pass a Playwright `storageState`. Wait for `networkidle` before\n  the first click on dev servers that hydrate late.\n- Keep the flow file under `$HOME\u002F.development-system\u002Fprivate\u002Fverification\u002F\u003Crun-id>\u002F`,\n  never in the repository. Do not pass `--emit`: no replay spec is kept, so this\n  is live verification, not an automated test (operator decision 2026-10-13);\n  keeping a replay spec needs an operator test grant. A failed flow is re-run\n  live, so renamed labels need no maintenance.\n- Prove permissions both ways: the allowed role reaches the end state and a\n  role without the permission is observed refused.\n- Assert side effects (rows, emails, payments in test mode), not just text.\n- Clean up the records the flow created and stop every server you started.\n\nThe T3 browser remains the tool for visual judgment and exploration without a\ndefined flow.\n\nLines of code, file counts, identifier length and minified formatting are not\nquality targets. Complexity signals may inform diagnosis but cannot fail a run.\n\n## Output\n\nReturn the check-no-tests result, each acceptance criterion with its real\nevidence (passed, failed or not reached), the independent verdict, every\nself-grading finding and any unproven behavior. This skill is read-only and\nnever edits.\n\n## Authorized Claude Code account recovery (1.39.0)\n\nFor Claude Code review and computer use, the operator explicitly authorizes the\nlocal Codex credential-home sequence followed by a fresh native Claude role.\nRun codex-review once; it discovers existing profiles without copying credentials\nand records at most two sequential profile attempts. Read receipt.json as well as findings.\nWhen status is fallback_required and fallback.eligible is true, immediately\ndispatch reviewer (plan, diff or security), visual-reviewer (image review) or\nbrowser-qa (computer use) through the native Agent tool with the original packet.\nCopy fallback.prompt verbatim from the receipt; it contains the original packet\nand Codex fallback:, Codex fallback receipt: and Codex fallback packet: lines.\nThe guard verifies the full dispatched packet, hash, root, mode and Task-Id and\nrejects resume so the native agent stays fresh. Computer-use fallback receipts\nare admitted once only; a consumed receipt requires reconciliation, not replay.\nDo not let a failed Codex attempt silently omit the independent review or absorb\nit into the coordinator. Preserve the endpoint and actual capability requirements.\nCancellation, safety refusal and uncertain computer-use effects are not fallback\npermission: reconcile observed state before more actions. If the native role lacks\nvision or an authorized browser, retain the gap and continue independent work.\nReport the provider change and actual or unknown identity. This explicit Claude\nexception does not change restricted Codex-only tasks or Headroom's same-account\nper-invocation contract. HOME installation does not prove live host loading.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F2.3.0\u002Fskills\u002Finternal\u002Fbehavioral-evidence","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system","https:\u002F\u002Fgithub.com\u002FAO-HyS","https:\u002F\u002Faohys.net\u002F","Software Boutique, we make your projects come true live. ","2026-11-14 03:17:27",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add AO-HyS\u002Fdevelopment-system --skill behavioral-evidence",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill behavioral-evidence",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill behavioral-evidence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.3.0\u002Fskills\u002Finternal\u002Fbehavioral-evidence\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M79EQ4BPYQTX8RWN1Y1J2K1F","working-backwards","Define a software feature through PRFAQ and staged documents when the user requests working backwards before coding.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fworking-backwards\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M79EQ2E8P85Y1Y7VNJZMNEJE","flow-implement","Implement a requested software change through verification, corrections, and its authorized delivery endpoint.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fflow-implement\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M79EQ0PNMKHPJ78F8WMNX06P","development-steward","Run the scheduled, read-only weekly maintenance review for the six explicitly opted-in repositories and prepare one concise private report for Check-in.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fdevelopment-steward\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79EPXJ56MX7955GWP1HD4B0","grill-with-docs","Run one recoverable interview for functional, visual, or mixed software grills; reuse equivalent answers and offer the shared HTML questionnaire.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fgrill-with-docs\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79EPTFPHYEV40ZG52Z0GVS2","global-agent-guardrails","Install, audit, test, or update the Development System's global destructive-command guard for Codex, Claude Code and T3 Code. Use when configuring agent safety hooks or investigating whether dangerous shell operations are blocked.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fglobal-agent-guardrails\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79EPR0KPHKAFN7V6CEEDR0Y","impeccable","Design or refine frontend UI using project context and a focused design playbook; also handles visual critique and polish.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FSKILL.md",[],[]]