[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P39C0E4K926T0N0SDX2KYF":3,"skill-same:01M6P39C0E4K926T0N0SDX2KYF":42},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":17,"linkOnly":18,"markdownContent":19,"markdownBody":19,"frontMatter":20,"refName":21,"commitSha":22,"skillDirectory":23,"forksCount":12,"repositoryHtmlUrl":24,"repositoryHomepageUrl":6,"ownerHtmlUrl":25,"ownerBlogUrl":26,"ownerDescription":6,"updatedAt":27,"install":28,"resources":41},"01M6P39C0E4K926T0N0SDX2KYF","regression",null,"dexter-cnx\u002Fagent-engineering-toolkit","dexter-cnx","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F73522389?v=4","01M6K09WYAAXJXMR26H00WJ2AT","01M6P370Z0XCZ7NC67MJ2MRW94",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Foverlays\u002Fagent-karpathy\u002Fskills\u002Fregression\u002FSKILL.md",[],[5],"2026-11-10 10:12:30",false,"# karpathy-regression\n\n## Purpose\nEnforce structural and behavioral guardrails on mutation candidates before any promotion decision is made, hard-failing on any violation.\n\n## Use when\n- You have generated mutation candidates and need to verify none of them break existing behavior, remove required sections, or introduce architecture violations\n- You are running a CI gate and need a hard stop before a potentially broken skill reaches the promotion stage\n- A candidate has an unexpectedly high score and you want to confirm it was not achieved by removing constraints or degrading the output contract\n- You are manually reviewing a candidate before committing it to the repository\n\n## Do NOT use when\n- You are checking the baseline skill before mutation — regression is for candidates only — use a more specific skill instead.\n- You only want a quality score — use `karpathy-evaluation` instead — use a more specific skill instead.\n- The skill is not in SKILL.md format (regression checks assume the 13-section schema) — use a more specific skill instead.\n- You are reviewing policies, templates, or documentation files (not SKILL.md content)\n\n## Inputs required\n- One or more MutationCandidate dicts (output of `karpathy-mutation`)\n- The baseline SKILL.md content (to compare section counts and output contract)\n- The skill_path (to check forbidden file paths)\n\n## Constraints\n- Must hard-fail (exit 1) if ANY of the five checks fail for a candidate\n- Must not modify any file during a check — read-only inspection only\n- Must return a RegressionResult for every candidate, even if some pass and others fail\n- Forbidden mutation paths include: AGENTS.md, AGENTS.overlay.md, docs\u002Fprompt-pipeline.md, evals\u002Frubrics\u002F, evals\u002Fschemas\u002F, .github\u002Fworkflows\u002F\n- A candidate that removes an existing H2 section always fails — no exceptions\n\n## Step-by-step workflow\n1. For each candidate, extract all `## ` section headers and compare to the baseline set — fail if any are missing.\n2. Scan candidate content for architecture violation patterns: direct SDK imports in presentation layer, repository bypass, logic placed directly in a widget.\n3. Check that the skill_path does not match any entry in the forbidden paths list.\n4. Compare the Purpose section between candidate and baseline — fail if candidate's Purpose is empty when baseline's was not.\n5. Compare Output contract bullet count between candidate and baseline — fail if candidate has fewer deliverables.\n6. If all checks pass, set `passed = True` and return an empty `violations` list.\n7. If any check fails, set `passed = False`, populate `violations` with one message per failure, and raise `RegressionViolation`.\n\n## Output contract\n- A RegressionResult dict per candidate: candidate_id, passed (bool), violations (list of strings)\n- A summary dict with: regression_results (list), passing_candidates (list of candidates that passed), regression_failures (list of failing candidate_ids), all_passed (bool)\n- Exit code 1 from `regression_runner.py` if any candidate fails\n\n## Validation checklist\n- Run `python -m runners.regression_runner --skill \u003Cpath> --candidates \u003Cfile>` and confirm exit code 0 for clean candidates\n- Confirm a candidate with a removed section produces `passed: false` and a non-empty `violations` list\n- Confirm the `regression_failures` list matches the set of candidate_ids with `passed: false`\n- Confirm passing candidates are forwarded to the promotion stage without modification\n\n## Related skills\n- `karpathy-mutation` — produces the candidates this skill checks\n- `karpathy-optimizer` — receives only regression-passing candidates\n- `karpathy-evaluation` — runs after regression to score passing candidates\n\n## References\n- [`..\u002F..\u002Fagents\u002Fregression_agent.py`](..\u002F..\u002Fagents\u002Fregression_agent.py)\n- [`..\u002F..\u002Fdocs\u002Fguardrails.md`](..\u002F..\u002Fdocs\u002Fguardrails.md)\n- [`..\u002F..\u002Fevals\u002Ftestcases\u002Fflutter_deeplink\u002F`](..\u002F..\u002Fevals\u002Ftestcases\u002Fflutter_deeplink\u002F)\n\n## Real example\nHistorical static snapshot: the `token_budget` mutation for flutter deep link removes the Constraints section in an aggressive attempt to reduce tokens. The regression check on step 1 immediately detects the missing `## Constraints` header and raises `RegressionViolation(candidate_id='baseline-token_budget', violations=['Missing required section: ## Constraints'])`. This candidate is excluded from the promotion stage.\n\n## Real file output sample\n```text\nmemory\u002Fcandidate_archive.json\nreports\u002Flatest_report.md\n```\n",{},"main","3035171e2986d5fdb445e694b9013fbdf58b3ff6","overlays\u002Fagent-karpathy\u002Fskills\u002Fregression","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit","https:\u002F\u002Fgithub.com\u002Fdexter-cnx","https:\u002F\u002Fdexter-cnx.github.io\u002Fportfolio\u002F","2026-05-26 14:24:27",{"source":7,"skillName":5,"commands":29,"prompt":39,"zipAvailable":40},[30,33,36],{"tool":31,"command":32},"npx","npx skills add dexter-cnx\u002Fagent-engineering-toolkit --skill regression",{"tool":34,"command":35},"bunx","bunx skills add dexter-cnx\u002Fagent-engineering-toolkit --skill regression",{"tool":37,"command":38},"pnpm","pnpm dlx skills add dexter-cnx\u002Fagent-engineering-toolkit --skill regression","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Foverlays\u002Fagent-karpathy\u002Fskills\u002Fregression\u002FSKILL.md",true,[],[43,70,90,99,111,123],{"skillNo":44,"name":45,"nameZh":6,"description":46,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":47,"categories":48,"keywords":49,"publishedAt":17},"01M6P4P9S9017DTSFMRKGA7XW2","toolkit-i18n-operator","Use the toolkit-i18n CLI for repeated Flutter localization workflows with compact outputs, CSV validation, key coverage reporting, generated JSON exports, and safe non-mutating behavior.","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Ftools\u002Ftoolkit-i18n\u002Fskills\u002Ftoolkit-i18n-operator\u002FSKILL.md",[],[50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69],"toolkit i18n operator","i18n","operator","toolkit","flutter localization","cli","safe","workflows","for","validation","with","csv","compact","reporting","json","flutter","behavior","coverage","generated","use",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":86,"publishedAt":17},"01M6P4NREKE3P0XYV3RBBWC987","toolkit-design-operator","Use the toolkit-design CLI for repeated repository workflows.","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Ftools\u002Ftoolkit-design\u002Fskills\u002Ftoolkit-design-operator\u002FSKILL.md",[76,81],{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[87,52,53,88,58,55,57,89,69],"toolkit design operator","design","repository",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":17},"01M6P4NNSQ09QFPYG2PMPWEA94","toolkit-ci-operator","Use the toolkit-ci CLI for repeated repository workflows.","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Ftools\u002Ftoolkit-ci\u002Fskills\u002Ftoolkit-ci-operator\u002FSKILL.md",[],[97,98,52,53,89,55,57,69,58],"toolkit ci operator","ci",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":17},"01M6P4NK636991P6WWQ6X8HDYX","toolkit-arch-operator","Use the toolkit-arch CLI for repeated repository workflows, including Flutter i18n usage scans, layer checks, and localization coverage.","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Ftools\u002Ftoolkit-arch\u002Fskills\u002Ftoolkit-arch-operator\u002FSKILL.md",[],[106,107,53,52,51,108,109,58,69,67,65,110,89,57,55],"toolkit arch operator","arch","usage","layer","localization",{"skillNo":112,"name":113,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":119,"publishedAt":17},"01M6P4NF18XGVSG2NR01E1DX0R","web-testing","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Foverlays\u002Fweb-frontend\u002Fskills\u002Fweb-testing\u002Fskill.md",[116],{"categoryNo":117,"categoryName":118,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000008","测试与质量",[120,121,122],"web testing","web","testing",{"skillNo":124,"name":125,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":17},"01M6P4MVK07EJ75FQTFN54AGPM","web-state","https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Foverlays\u002Fweb-frontend\u002Fskills\u002Fweb-state\u002Fskill.md",[],[121,129,130],"state","web state"]