[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AEWFM0RFSR0716QS8G73B4":3,"skill-same:01M7AEWFM0RFSR0716QS8G73B4":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7AEWFM0RFSR0716QS8G73B4","outcome-quality-enforcement",null,"Enforce the highest credible quality on a consequential team outcome through reference calibration, observable success contracts, native operation, independent criticism, root-cause revision, and quality-convergence stopping. Use when an accountable lead commissions creative or ambiguous work, judges a major deliverable, sees repeated near-misses, or must decide whether more iteration is warranted. Do not use to turn routine low-risk work into ceremony.","BlueprintLabIO\u002Frestless-core","BlueprintLabIO","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F222796351?v=4","01M7AETKD0TZXRAGH2WAKGNYE6","01M7AETKE63A80017SD5ZWAEF4",12,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Finfra\u002Fcompany-image\u002Fskills\u002Foutcome-quality-enforcement\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: outcome-quality-enforcement\ndescription: Enforce the highest credible quality on a consequential team outcome through reference calibration, observable success contracts, native operation, independent criticism, root-cause revision, and quality-convergence stopping. Use when an accountable lead commissions creative or ambiguous work, judges a major deliverable, sees repeated near-misses, or must decide whether more iteration is warranted. Do not use to turn routine low-risk work into ceremony.\n---\n\n# Outcome quality enforcement\n\nThe accountable lead owns the accepted outcome. Staff own production. A completed Attempt is evidence\nto judge, not proof that the outcome is good.\n\n## Form the quality contract\n\nBefore expensive production, retrieve rather than guess:\n\n- the real product, operating environment, repository, data, and constraints;\n- authoritative product or brand truth;\n- the strongest accepted incumbent or gold-standard reference;\n- prior failures as compact observations, without inheriting rejected solutions; and\n- the specialist skill or evaluator that matches the outcome.\n\nResolve any ambiguity that changes the solution class, cost, authority, or acceptance bar. Otherwise\nmake a reversible assumption and record it. Keep one concise durable contract containing:\n\n1. the observable outcome and whose reality must change;\n2. priorities and explicit trade-offs;\n3. references ordered by authority;\n4. the incumbent or minimum quality floor;\n5. exclusions and authority boundaries;\n6. native evidence required for acceptance;\n7. the independent evaluator and verdict language;\n8. the owner-attention envelope; and\n9. the convergence and blocker conditions.\n\nGive producers the minimum sufficient context: the contract, exact inputs, environment, and relevant\nexamples. Do not replay the full lead conversation or make them reverse-engineer the outcome from a\nchecklist.\n\n## Run the evidence loop\n\nUse the smallest Work graph that preserves real accountability:\n\n1. Commission Staff to produce a coherent end-to-end candidate or one high-information slice.\n2. Operate the exact candidate in its real medium. Capture native evidence before interpreting it.\n3. Commission a fresh-context independent evaluator when judgement matters. Give it the contract,\n   ordered references, exact candidate, and factual evidence—but not producer rationale.\n4. Require a decisive verdict and ranked consequential gaps. Check that the evaluator actually tested\n   the promised outcome; a weak verifier creates false confidence.\n5. Commission the smallest root-cause repair with a credible improvement hypothesis, then evaluate the\n   new exact candidate again.\n\nBudget evidence context deliberately. Keep large screenshot, trace, log, and capture corpora as durable\nlinked outputs; give the evaluator compact manifests, representative native views, and commands or\nlocators for retrieving the rest. When capture and judgement together would saturate one session,\nseparate evidence production from a fresh synthesis pass rather than carrying an ever-growing\ntranscript. Verification commands must be non-interactive and must not install packages, rewrite lock\nfiles, or otherwise change the candidate they purport to judge.\n\nContinue while a consequential gap and credible improvement path remain. Attempt limits bound local\nexecution failure; they do not lower the team outcome. Create sparse revision or replacement Work as\nneeded. After the same important failure twice, change the approach, context, skill, model, evaluator,\nor team seam. Use a clean reset when the trajectory is anchored to rejected assumptions or form.\n\nPrefer one coherent root fix over accumulated patches. Complexity must buy observable quality,\nreliability, or future reasoning leverage. Convert repeated failures into a reusable skill, test,\nevaluation, tool, or compact durable observation.\n\n## Converge honestly\n\nAccept only when:\n\n- the contract is proven against the exact native artifact;\n- the result clears the stated floor and ordered references;\n- independent review accepts it when required;\n- the verifier and evidence are themselves credible;\n- no consequential unresolved gap remains; and\n- the owner is asked only for authority or irreducible judgement, with a ready-to-use review target.\n\nDo not stop because a build is green, a producer is confident, an arbitrary loop count elapsed, or the\nlead is tired of iterating. Stop when quality converges or when a concrete external constraint makes\nfurther machine progress impossible. State residual uncertainty and disagreement plainly.\n","# Outcome quality enforcement\n\nThe accountable lead owns the accepted outcome. Staff own production. A completed Attempt is evidence\nto judge, not proof that the outcome is good.\n\n## Form the quality contract\n\nBefore expensive production, retrieve rather than guess:\n\n- the real product, operating environment, repository, data, and constraints;\n- authoritative product or brand truth;\n- the strongest accepted incumbent or gold-standard reference;\n- prior failures as compact observations, without inheriting rejected solutions; and\n- the specialist skill or evaluator that matches the outcome.\n\nResolve any ambiguity that changes the solution class, cost, authority, or acceptance bar. Otherwise\nmake a reversible assumption and record it. Keep one concise durable contract containing:\n\n1. the observable outcome and whose reality must change;\n2. priorities and explicit trade-offs;\n3. references ordered by authority;\n4. the incumbent or minimum quality floor;\n5. exclusions and authority boundaries;\n6. native evidence required for acceptance;\n7. the independent evaluator and verdict language;\n8. the owner-attention envelope; and\n9. the convergence and blocker conditions.\n\nGive producers the minimum sufficient context: the contract, exact inputs, environment, and relevant\nexamples. Do not replay the full lead conversation or make them reverse-engineer the outcome from a\nchecklist.\n\n## Run the evidence loop\n\nUse the smallest Work graph that preserves real accountability:\n\n1. Commission Staff to produce a coherent end-to-end candidate or one high-information slice.\n2. Operate the exact candidate in its real medium. Capture native evidence before interpreting it.\n3. Commission a fresh-context independent evaluator when judgement matters. Give it the contract,\n   ordered references, exact candidate, and factual evidence—but not producer rationale.\n4. Require a decisive verdict and ranked consequential gaps. Check that the evaluator actually tested\n   the promised outcome; a weak verifier creates false confidence.\n5. Commission the smallest root-cause repair with a credible improvement hypothesis, then evaluate the\n   new exact candidate again.\n\nBudget evidence context deliberately. Keep large screenshot, trace, log, and capture corpora as durable\nlinked outputs; give the evaluator compact manifests, representative native views, and commands or\nlocators for retrieving the rest. When capture and judgement together would saturate one session,\nseparate evidence production from a fresh synthesis pass rather than carrying an ever-growing\ntranscript. Verification commands must be non-interactive and must not install packages, rewrite lock\nfiles, or otherwise change the candidate they purport to judge.\n\nContinue while a consequential gap and credible improvement path remain. Attempt limits bound local\nexecution failure; they do not lower the team outcome. Create sparse revision or replacement Work as\nneeded. After the same important failure twice, change the approach, context, skill, model, evaluator,\nor team seam. Use a clean reset when the trajectory is anchored to rejected assumptions or form.\n\nPrefer one coherent root fix over accumulated patches. Complexity must buy observable quality,\nreliability, or future reasoning leverage. Convert repeated failures into a reusable skill, test,\nevaluation, tool, or compact durable observation.\n\n## Converge honestly\n\nAccept only when:\n\n- the contract is proven against the exact native artifact;\n- the result clears the stated floor and ordered references;\n- independent review accepts it when required;\n- the verifier and evidence are themselves credible;\n- no consequential unresolved gap remains; and\n- the owner is asked only for authority or irreducible judgement, with a ready-to-use review target.\n\nDo not stop because a build is green, a producer is confident, an arbitrary loop count elapsed, or the\nlead is tired of iterating. Stop when quality converges or when a concrete external constraint makes\nfurther machine progress impossible. State residual uncertainty and disagreement plainly.\n",{"name":5,"description":7},"main","74448c875ccc3d826c90b46381cc63698ba769aa","infra\u002Fcompany-image\u002Fskills\u002Foutcome-quality-enforcement",1,"https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core","https:\u002F\u002Frestless.run","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO","2026-11-14 10:29:34",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add BlueprintLabIO\u002Frestless-core --skill outcome-quality-enforcement",{"tool":37,"command":38},"bunx","bunx skills add BlueprintLabIO\u002Frestless-core --skill outcome-quality-enforcement",{"tool":40,"command":41},"pnpm","pnpm dlx skills add BlueprintLabIO\u002Frestless-core --skill outcome-quality-enforcement","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Finfra\u002Fcompany-image\u002Fskills\u002Foutcome-quality-enforcement\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7AEXHE6CPB3TMHWKEMDWYM7","fixture-note-etiquette","How the company writes a Fixture Notes message. Used only by the connections smoke.","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Ftools\u002Ffixture-mcp-provider\u002Ffixtures\u002Fplugin\u002Fskills\u002Ffixture-note-etiquette\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7AEXC9H7TTENFY1S87TQZF5","web-native-review","Prepare or independently review a rendered website against its outcome contract and a mature ground-truth reference. Use for landing pages, product sites, blogs, documentation sites, or other browser-native outcomes; do not use to judge source code alone or turn mechanical layout facts into a taste score.","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Finfra\u002Fcompany-image\u002Fskills\u002Fweb-native-review\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7AEX8KTGCGTDHKMKRMV25AS","scenario-evidence","Run a versioned Runtime scenario, probe its real capabilities, preserve compact evidence, and prepare its native review target. Use for a project outcome that benefits from repeatable setup\u002Frun\u002Fassertion\u002Fevidence—not to choose a plan, team, or business verdict.","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Finfra\u002Fcompany-image\u002Fskills\u002Fscenario-evidence\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7AEX433AM2YZ08ST66G3FF5","research","Answer a question the company needs to decide on with a sourced brief - market facts, a technology, a regulation, an audience, a price, a supplier. Use when an answer must be found and checked on the web or in documents before acting; do not use for a quick lookup a single source settles, or for competitor landscapes (use competitor-research).","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Finfra\u002Fcompany-image\u002Fskills\u002Fresearch\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7AEWYCTNC5VF57C9PQF1X4W","reference-led-reset","Reset a rejected or repeatedly drifting outcome into a genuinely fresh Work Attempt grounded in ordered authoritative references. Use when the owner asks to start over, when qualitative defects survive revision, or when a mechanically valid result conflicts with the product or brand source of truth. Do not use for an ordinary bounded repair that should preserve the current candidate.","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Finfra\u002Fcompany-image\u002Fskills\u002Freference-led-reset\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7AEWV2KP5JM50T3S7VD7HR9","publish-git","Safely reconcile, verify, and publish Git refs through the governed Restless effect path. Use for pushes or deployments driven by a Git push; do not use for read-only fetches, local Git work, or provider API administration.","https:\u002F\u002Fgithub.com\u002FBlueprintLabIO\u002Frestless-core\u002Fblob\u002Fmain\u002Finfra\u002Fcompany-image\u002Fskills\u002Fpublish-git\u002FSKILL.md",[],[]]