[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P38P3DHAZG7C07Z7V9HGC6":3,"skill-same:01M6P38P3DHAZG7C07Z7V9HGC6":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},"01M6P38P3DHAZG7C07Z7V9HGC6","mutation",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\u002Fmutation\u002FSKILL.md",[],[5],"2026-11-10 10:12:30",false,"# karpathy-mutation\n\n## Purpose\nGenerate controlled single-dimension mutation candidates from a baseline SKILL.md, producing one variant per mutation type so that each can be independently evaluated.\n\n## Use when\n- You have a baseline EvalResult and want to explore whether targeted changes improve the score\n- The baseline scores below 0.85 on at least one dimension and you have identified the lowest-scoring dimensions\n- You are running a full optimization cycle and need the mutation stage to produce candidates\n- You want to test whether decomposing compound steps or tightening wording improves correctness or simplicity scores\n\n## Do NOT use when\n- The baseline final_score is already above 0.90 — the improvement margin is unlikely to justify the cycle cost — use a more specific skill instead.\n- You want to change multiple dimensions at once — that violates the one-dimension constraint and makes it impossible to isolate the cause of any score change — use a more specific skill instead.\n- You have not yet run `karpathy-evaluation` on the baseline — you need a baseline score before mutating — use a more specific skill instead.\n- The skill has failing binary checks — fix structural issues before running mutations — use a more specific skill instead.\n\n## Inputs required\n- Full baseline SKILL.md content\n- A stable `skill_id` and `parent_id` (use `\"baseline\"` for unmodified content)\n- The desired number of candidates (1–6, default 5)\n- The baseline EvalResult (to know which dimensions to prioritise)\n\n## Constraints\n- Each candidate must change exactly ONE mutation dimension\n- All 13 required SKILL.md sections must be present in every candidate\n- The Purpose and Output contract sections must not be emptied or materially degraded\n- Mutation must not introduce forbidden strings (TODO, TBD, FIXME, {{}})\n- Each candidate_id must be stable: `\u003Cparent_id>-\u003Cmutation_type>`\n\n## Step-by-step workflow\n1. Confirm the baseline content has all 13 required sections and no placeholder text.\n2. For each selected mutation type (up to n), apply exactly the one-dimension transformation described in `docs\u002Fmutation-system.md`.\n3. After each mutation, verify that the section count in the candidate equals the section count in the baseline.\n4. Count tokens for each candidate: `ceil(word_count × 1.3)`.\n5. Assemble each MutationCandidate dict with: candidate_id, parent_id, mutation_type, mutation_description, content, token_count.\n6. Return the list of candidates for downstream regression and evaluation.\n\n## Output contract\n- A list of MutationCandidate dicts, each matching `evals\u002Fschemas\u002Frun_report.schema.json#\u002Fdefinitions\u002FMutationCandidate`\n- Each dict includes: candidate_id, parent_id, mutation_type, mutation_description, content, token_count\n- At most 6 candidates per run (one per mutation type)\n- The list is appended to `memory\u002Fcandidate_archive.json`\n\n## Validation checklist\n- Confirm each candidate has exactly 12 `## ` section headers (matching the baseline count)\n- Confirm each candidate_id follows the pattern `\u003Cparent_id>-\u003Cmutation_type>`\n- Confirm no candidate content contains TODO, TBD, FIXME, or `{{`\n- Run `python -m runners.mutation_runner --skill \u003Cpath> --n 3` and confirm valid JSON returned\n- Confirm the `mutation_description` accurately describes what changed in one sentence\n\n## Related skills\n- `karpathy-evaluation` — must be run on baseline before calling this skill\n- `karpathy-regression` — must be run on every candidate output from this skill\n- `karpathy-optimizer` — selects the best candidate from this skill's output\n\n## References\n- [`..\u002F..\u002Fdocs\u002Fmutation-system.md`](..\u002F..\u002Fdocs\u002Fmutation-system.md)\n- [`..\u002F..\u002Fagents\u002Fmutation_agent.py`](..\u002F..\u002Fagents\u002Fmutation_agent.py)\n- [`..\u002F..\u002Fevals\u002Ftestcases\u002Fflutter_deeplink\u002F`](..\u002F..\u002Fevals\u002Ftestcases\u002Fflutter_deeplink\u002F)\n\n## Real example\nHistorical static snapshot: given the flutter deep link baseline, the `decomposition_steps` mutation finds the compound step \"Configure the route and register it in the router\" and splits it into \"Configure the route in `app_router.dart`\" and \"Keep the route definition in `app_router.dart` in sync with the router configuration.\" The `simplicity` dimension improves because each step is now independently executable.\n\n## Real file output sample\n```text\nmemory\u002Fcandidate_archive.json\n```\n",{},"main","3035171e2986d5fdb445e694b9013fbdf58b3ff6","overlays\u002Fagent-karpathy\u002Fskills\u002Fmutation","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 mutation",{"tool":34,"command":35},"bunx","bunx skills add dexter-cnx\u002Fagent-engineering-toolkit --skill mutation",{"tool":37,"command":38},"pnpm","pnpm dlx skills add dexter-cnx\u002Fagent-engineering-toolkit --skill mutation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdexter-cnx\u002Fagent-engineering-toolkit\u002Fblob\u002Fmain\u002Foverlays\u002Fagent-karpathy\u002Fskills\u002Fmutation\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"]