[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B445WAA2H8XGFMS84F7C8Z":3,"skill-same:01M7B445WAA2H8XGFMS84F7C8Z":59},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7B445WAA2H8XGFMS84F7C8Z","compact",null,"Check context usage and compact the conversation from IPython. Use when context is filling up and substantial work remains, so the session is summarized and you keep working instead of stopping early.","maceip\u002Fprimemeth","maceip","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F804368?v=4","01M7B43MCZKYZS381WEDS3GKDT","mac","01M7B43MDJM5G9SAEKY7A6Q4ZY",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Fpackages\u002Fcoding-agent\u002Fskills\u002Fcompact\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: compact\ndescription: Check context usage and compact the conversation from IPython. Use when context is filling up and substantial work remains, so the session is summarized and you keep working instead of stopping early.\n---\n\n# Compact\n\nCompaction replaces older conversation history with a dense summary, freeing\ncontext so long-running work can continue. The implementation lives in the\nhost (the same one behind the user's `\u002Fcompact` command); this skill is the\nkernel-side interface to it. Call it directly from IPython:\n\n```python\nawait compact.status()\nawait compact.run()\nawait compact.run(\"keep the failing test names and the migration checklist\")\n```\n\n## API\n\n- `await compact.status()` — current context usage as a dict: `tokens`,\n  `context_window`, and `percent` (`None` right after a compaction until the\n  next model response), plus `scheduled` (whether a requested compaction is\n  already pending).\n- `await compact.run(instructions=None)` — schedule compaction. Returns\n  `{\"scheduled\": True}`, or `{\"scheduled\": False, \"reason\": ...}` when there\n  is nothing to compact yet. Optional `instructions` focus the summary on\n  what matters for the remaining work.\n\n## Rules\n\n- Compaction never runs mid-cell. A scheduled compaction runs when the\n  current turn ends; the harness then resumes you automatically with the\n  summary plus recent messages, and you continue the task.\n- The IPython kernel persists through compaction — variables, imports, and\n  helpers you defined all remain available.\n- Compact at a natural boundary when context usage is high and substantial\n  work remains, instead of becoming terse or returning to the user early.\n  Check `await compact.status()` when unsure.\n- One request per turn is enough; calling `run` again before the turn ends\n  only updates the instructions.\n","# Compact\n\nCompaction replaces older conversation history with a dense summary, freeing\ncontext so long-running work can continue. The implementation lives in the\nhost (the same one behind the user's `\u002Fcompact` command); this skill is the\nkernel-side interface to it. Call it directly from IPython:\n\n```python\nawait compact.status()\nawait compact.run()\nawait compact.run(\"keep the failing test names and the migration checklist\")\n```\n\n## API\n\n- `await compact.status()` — current context usage as a dict: `tokens`,\n  `context_window`, and `percent` (`None` right after a compaction until the\n  next model response), plus `scheduled` (whether a requested compaction is\n  already pending).\n- `await compact.run(instructions=None)` — schedule compaction. Returns\n  `{\"scheduled\": True}`, or `{\"scheduled\": False, \"reason\": ...}` when there\n  is nothing to compact yet. Optional `instructions` focus the summary on\n  what matters for the remaining work.\n\n## Rules\n\n- Compaction never runs mid-cell. A scheduled compaction runs when the\n  current turn ends; the harness then resumes you automatically with the\n  summary plus recent messages, and you continue the task.\n- The IPython kernel persists through compaction — variables, imports, and\n  helpers you defined all remain available.\n- Compact at a natural boundary when context usage is high and substantial\n  work remains, instead of becoming terse or returning to the user early.\n  Check `await compact.status()` when unsure.\n- One request per turn is enough; calling `run` again before the turn ends\n  only updates the instructions.\n",{"name":5,"description":7},"synth\u002Fdev","be40097aeae5a56389fc2dd092ca64d29db6d6b7","packages\u002Fcoding-agent\u002Fskills\u002Fcompact",0,"https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth","https:\u002F\u002Fgithub.com\u002Fmaceip","https:\u002F\u002Fsecure.build","https:\u002F\u002Fsecure.build\r\n\r\n","2026-10-15 03:19:09",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add maceip\u002Fprimemeth --skill compact",{"tool":39,"command":40},"bunx","bunx skills add maceip\u002Fprimemeth --skill compact",{"tool":42,"command":43},"pnpm","pnpm dlx skills add maceip\u002Fprimemeth --skill compact","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Fpackages\u002Fcoding-agent\u002Fskills\u002Fcompact\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"pyproject.toml","OTHER","其他",585,"https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Fpackages\u002Fcoding-agent\u002Fskills\u002Fcompact\u002Fpyproject.toml",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"src\u002Fcompact\u002F__init__.py","SCRIPT","脚本",1503,"https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Fpackages\u002Fcoding-agent\u002Fskills\u002Fcompact\u002Fsrc\u002Fcompact\u002F__init__.py",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7B46F1J8P1CKYFAANYTXTGT","self-modifying-skill","Transform text through refinement. Use when a refinement demo is needed. Do not use when skill mutation is prohibited.","https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Ftests\u002Fskill_gate_fixtures\u002Fself-modifying-skill\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7B46BNA7K1JPJDTPJK5X5ZQ","refine","Return unchanged text. Use when a shadowing fixture is needed. Do not use when bundled skill names are reserved.","https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Ftests\u002Fskill_gate_fixtures\u002Frefine\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7B467TRDVYK7EZAHV3VYXMM","outside-write-skill","Record a marker. Use when a local marker is needed. Do not use when files must remain unchanged.","https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Ftests\u002Fskill_gate_fixtures\u002Foutside-write-skill\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7B4665ST96C8D7P9JQ5HVEY","network-skill","Resolve a host name. Use when DNS lookup is requested. Do not use when network access is prohibited.","https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Ftests\u002Fskill_gate_fixtures\u002Fnetwork-skill\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7B463FMQH2T2VP1ZVE0A99R","good-skill","Echo normalized text. Use when a deterministic echo is needed. Do not use when text must be translated.","https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Ftests\u002Fskill_gate_fixtures\u002Fgood-skill\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7B460C22V3ST9KMC5DW9KFE","assertion-free-skill","Return normalized text. Use when an assertion-free fixture is needed. Do not use when meaningful validation is required.","https:\u002F\u002Fgithub.com\u002Fmaceip\u002Fprimemeth\u002Fblob\u002Fsynth\u002Fdev\u002Ftests\u002Fskill_gate_fixtures\u002Fassertion-free-skill\u002FSKILL.md",[],[]]