[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AVR9TG4AP9WJE9QYEY79X":3,"skill-same:01M69AVR9TG4AP9WJE9QYEY79X":60},{"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":26,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M69AVR9TG4AP9WJE9QYEY79X","skillopt-sleep",null,"Use when the user wants the dsh agent to self-improve from past usage, asks about a nightly\u002Foffline 'sleep' or 'dream' cycle, skill\u002Fmemory consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine through the skillopt_* tools: harvest past sessions -> mine recurring tasks -> replay via a selected backend -> consolidate validated skills behind a held-out gate.","microsoft\u002FSkillOpt","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AVF76KYARHPEXXWV3G0QZ",19078,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Fblob\u002Fmain\u002Fplugins\u002Fdsh\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30],"skillopt sleep","review","memory","sessions","2026-11-10 10:12:30",false,"---\nname: skillopt-sleep\ndescription: \"Use when the user wants the dsh agent to self-improve from past usage, asks about a nightly\u002Foffline 'sleep' or 'dream' cycle, skill\u002Fmemory consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine through the skillopt_* tools: harvest past sessions -> mine recurring tasks -> replay via a selected backend -> consolidate validated skills behind a held-out gate.\"\n---\n\n# SkillOpt-Sleep: usage-driven self-evolution for the dsh agent\n\nSkillOpt-Sleep is Microsoft's [SkillOpt](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt)\ndeployment-time companion engine: it reviews your past sessions (harvest), mines\nrecurring tasks (mine), replays them through a selected backend (replay), and\nconsolidates what it learns into skill documents behind a **held-out validation\ngate** (consolidate).\n\nThis skill drives the engine through the 7 `skillopt_*` tools exposed by the\ndsh-skillopt plugin. The default `mock` backend makes no model calls, which is\nuseful for verifying the plumbing; a real backend consumes your API budget.\n\n## When to use\n\n- \"make my agent better the more I use it\" \u002F \"learn my preferences across sessions\"\n- a one-off **offline self-evolution \u002F sleep \u002F dream** run (immediate or scheduled)\n- review past sessions\u002Ftrajectories and distill recurring tasks\n- consolidate feedback into `AGENTS.md` \u002F `SKILL.md` \u002F managed skills\n- schedule (cron) the cycle, or adopt a staged proposal\n\n## The cycle (six stages)\n\n1. **Harvest** — read-only scan of supported local session records → digests\n2. **Mine** — digests → recurring task records (intent + outcome labels + checkable refs)\n3. **Replay** — re-run tasks under the current skill+memory with the selected backend → (hard, soft) scores\n4. **Consolidate** — reflect on failures → propose bounded edits → **validation gate** on a held-out slice (default: accept only on strict improvement)\n5. **Stage** — write accepted proposals to `\u003Cproject>\u002F.skillopt-sleep\u002Fstaging\u002F\u003Ctimestamp>\u002F`. **Live files are unchanged.** A rejected run still has a report but no proposal files.\n6. **Adopt** — explicit (or operator-configured `--auto-adopt`) copies staged files over live ones, backing up first.\n\n## Driving it\n\nPrefer the tools over hand-editing files:\n\n| Tool | Behavior |\n|---|---|\n| `skillopt_status` | state, engine availability, latest staged proposal & report |\n| `skillopt_dry_run` | full preview (harvest+mine+replay), stages nothing |\n| `skillopt_run` | full cycle, stages a proposal (live files unchanged by default) |\n| `skillopt_adopt` | apply latest staged proposal (with backup) — the live-change boundary |\n| `skillopt_harvest` | read-only show\u002Fexport of mined tasks |\n| `skillopt_schedule` \u002F `skillopt_unschedule` | install\u002Fremove the nightly cron entry for this project |\n\nTypical flow:\n\n```text\n# 1. check state (default mock backend, zero cost)\nskillopt_status\n\n# 2. preview the cycle\nskillopt_dry_run project=\u003Cdir> source=\u003Cclaude|codex|…>\n\n# 3. real run (consumes the selected backend's API budget)\nskillopt_run project=\u003Cdir> backend=\u003Ccodex|claude|…> preferences=\"Prefer pytest; keep commits imperative.\"\n\n# 4. review the report, then adopt\nskillopt_adopt project=\u003Cdir>\n\n# 5. schedule nightly at 03:17\nskillopt_schedule project=\u003Cdir> hour=3 minute=17 backend=\u003Ccodex>\n```\n\n## Parameters\n\n| Parameter | Default | Meaning |\n|---|---|---|\n| `project` | config or cwd | project directory to evolve |\n| `backend` | `mock` | `mock\\|claude\\|codex\\|copilot\\|cursor\\|pi\\|opencode\\|handoff\\|azure_openai` (mock = no model calls) |\n| `source` | config | transcript source: `claude\\|codex\\|copilot\\|cursor\\|pi\\|opencode\\|auto` |\n| `model` | backend default | replay model override |\n| `maxTasks` | 40 | mined-task cap |\n| `preferences` | empty | house rules for the reflection prior (e.g. \"always use async\u002Fawait\") |\n\n## Configuration (cordis.yml \u002F bundle patch)\n\n```yaml\n- insert:\n    - id: skillopt\n      name: '.\u002Fsrc\u002Findex.js'\n      config:\n        backend: codex\n        project: \u002Fpath\u002Fto\u002Fproject\n        preferences: 'Always use async\u002Fawait'\n        # auto-adopt is OPERATOR-ONLY — the model cannot set it\n        autoAdopt: false\n```\n\nAdvanced engine keys go in `~\u002F.skillopt-sleep\u002Fconfig.json`:\n`gate_mode` (on\u002Foff), `gate_metric` (hard\u002Fsoft\u002Fmixed), `gate_no_regression`,\n`dream_rollouts`, `recall_k`, `evolve_memory` \u002F `evolve_skill`.\n\n## Hard rules\n\n- **Never** hand-edit `AGENTS.md` \u002F `SKILL.md` around `skillopt_adopt`; let the\n  engine's explicit adopt (or operator-configured `--auto-adopt`) apply the\n  staging manifest, backing up live files first.\n- Harvest is read-only; `mock` replay has no side effects.\n- Real backends send truncated transcript excerpts and derived tasks to the\n  selected provider for mining\u002Freplay\u002Fjudging\u002Freflection. For sensitive\n  sessions, export tasks first (`skillopt_harvest output=\u003Cfile>`), redact, set\n  the top-level `\"reviewed\"` to `true`, then replay with `--tasks-file`; real\n  backends refuse unreviewed task files.\n- Show the user the **held-out baseline → candidate** score and the exact\n  proposed edits before suggesting adoption. Evidence before adoption.\n\n## Validate \u002F demo (no API spend)\n\n```bash\npip install skillopt\npython -m skillopt_sleep.experiments.run_experiment --persona researcher --assert-improves\n```\n\nDeterministic synthetic demo: the score rises and the gate blocks a regression.\nIt validates the mechanism, not effectiveness on your own tasks.\n\nSee the [SkillOpt-Sleep docs](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Ftree\u002Fmain\u002Fdocs\u002Fsleep)\nfor recorded results and limitations.\n","# SkillOpt-Sleep: usage-driven self-evolution for the dsh agent\n\nSkillOpt-Sleep is Microsoft's [SkillOpt](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt)\ndeployment-time companion engine: it reviews your past sessions (harvest), mines\nrecurring tasks (mine), replays them through a selected backend (replay), and\nconsolidates what it learns into skill documents behind a **held-out validation\ngate** (consolidate).\n\nThis skill drives the engine through the 7 `skillopt_*` tools exposed by the\ndsh-skillopt plugin. The default `mock` backend makes no model calls, which is\nuseful for verifying the plumbing; a real backend consumes your API budget.\n\n## When to use\n\n- \"make my agent better the more I use it\" \u002F \"learn my preferences across sessions\"\n- a one-off **offline self-evolution \u002F sleep \u002F dream** run (immediate or scheduled)\n- review past sessions\u002Ftrajectories and distill recurring tasks\n- consolidate feedback into `AGENTS.md` \u002F `SKILL.md` \u002F managed skills\n- schedule (cron) the cycle, or adopt a staged proposal\n\n## The cycle (six stages)\n\n1. **Harvest** — read-only scan of supported local session records → digests\n2. **Mine** — digests → recurring task records (intent + outcome labels + checkable refs)\n3. **Replay** — re-run tasks under the current skill+memory with the selected backend → (hard, soft) scores\n4. **Consolidate** — reflect on failures → propose bounded edits → **validation gate** on a held-out slice (default: accept only on strict improvement)\n5. **Stage** — write accepted proposals to `\u003Cproject>\u002F.skillopt-sleep\u002Fstaging\u002F\u003Ctimestamp>\u002F`. **Live files are unchanged.** A rejected run still has a report but no proposal files.\n6. **Adopt** — explicit (or operator-configured `--auto-adopt`) copies staged files over live ones, backing up first.\n\n## Driving it\n\nPrefer the tools over hand-editing files:\n\n| Tool | Behavior |\n|---|---|\n| `skillopt_status` | state, engine availability, latest staged proposal & report |\n| `skillopt_dry_run` | full preview (harvest+mine+replay), stages nothing |\n| `skillopt_run` | full cycle, stages a proposal (live files unchanged by default) |\n| `skillopt_adopt` | apply latest staged proposal (with backup) — the live-change boundary |\n| `skillopt_harvest` | read-only show\u002Fexport of mined tasks |\n| `skillopt_schedule` \u002F `skillopt_unschedule` | install\u002Fremove the nightly cron entry for this project |\n\nTypical flow:\n\n```text\n# 1. check state (default mock backend, zero cost)\nskillopt_status\n\n# 2. preview the cycle\nskillopt_dry_run project=\u003Cdir> source=\u003Cclaude|codex|…>\n\n# 3. real run (consumes the selected backend's API budget)\nskillopt_run project=\u003Cdir> backend=\u003Ccodex|claude|…> preferences=\"Prefer pytest; keep commits imperative.\"\n\n# 4. review the report, then adopt\nskillopt_adopt project=\u003Cdir>\n\n# 5. schedule nightly at 03:17\nskillopt_schedule project=\u003Cdir> hour=3 minute=17 backend=\u003Ccodex>\n```\n\n## Parameters\n\n| Parameter | Default | Meaning |\n|---|---|---|\n| `project` | config or cwd | project directory to evolve |\n| `backend` | `mock` | `mock\\|claude\\|codex\\|copilot\\|cursor\\|pi\\|opencode\\|handoff\\|azure_openai` (mock = no model calls) |\n| `source` | config | transcript source: `claude\\|codex\\|copilot\\|cursor\\|pi\\|opencode\\|auto` |\n| `model` | backend default | replay model override |\n| `maxTasks` | 40 | mined-task cap |\n| `preferences` | empty | house rules for the reflection prior (e.g. \"always use async\u002Fawait\") |\n\n## Configuration (cordis.yml \u002F bundle patch)\n\n```yaml\n- insert:\n    - id: skillopt\n      name: '.\u002Fsrc\u002Findex.js'\n      config:\n        backend: codex\n        project: \u002Fpath\u002Fto\u002Fproject\n        preferences: 'Always use async\u002Fawait'\n        # auto-adopt is OPERATOR-ONLY — the model cannot set it\n        autoAdopt: false\n```\n\nAdvanced engine keys go in `~\u002F.skillopt-sleep\u002Fconfig.json`:\n`gate_mode` (on\u002Foff), `gate_metric` (hard\u002Fsoft\u002Fmixed), `gate_no_regression`,\n`dream_rollouts`, `recall_k`, `evolve_memory` \u002F `evolve_skill`.\n\n## Hard rules\n\n- **Never** hand-edit `AGENTS.md` \u002F `SKILL.md` around `skillopt_adopt`; let the\n  engine's explicit adopt (or operator-configured `--auto-adopt`) apply the\n  staging manifest, backing up live files first.\n- Harvest is read-only; `mock` replay has no side effects.\n- Real backends send truncated transcript excerpts and derived tasks to the\n  selected provider for mining\u002Freplay\u002Fjudging\u002Freflection. For sensitive\n  sessions, export tasks first (`skillopt_harvest output=\u003Cfile>`), redact, set\n  the top-level `\"reviewed\"` to `true`, then replay with `--tasks-file`; real\n  backends refuse unreviewed task files.\n- Show the user the **held-out baseline → candidate** score and the exact\n  proposed edits before suggesting adoption. Evidence before adoption.\n\n## Validate \u002F demo (no API spend)\n\n```bash\npip install skillopt\npython -m skillopt_sleep.experiments.run_experiment --persona researcher --assert-improves\n```\n\nDeterministic synthetic demo: the score rises and the gate blocks a regression.\nIt validates the mechanism, not effectiveness on your own tasks.\n\nSee the [SkillOpt-Sleep docs](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Ftree\u002Fmain\u002Fdocs\u002Fsleep)\nfor recorded results and limitations.\n",{"name":5,"description":7},"main","bc0a392ef0a7f92840ec673d80204d34ced169d0","plugins\u002Fdsh\u002Fskills\u002Fskillopt-sleep",1830,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt","https:\u002F\u002Faka.ms\u002Fskillopt","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-11 04:10:50",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add microsoft\u002FSkillOpt --skill skillopt-sleep",{"tool":52,"command":53},"bunx","bunx skills add microsoft\u002FSkillOpt --skill skillopt-sleep",{"tool":55,"command":56},"pnpm","pnpm dlx skills add microsoft\u002FSkillOpt --skill skillopt-sleep","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Fblob\u002Fmain\u002Fplugins\u002Fdsh\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",true,[],[61,68,77,84],{"skillNo":62,"name":5,"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":31},"01M69AVT3C6TRVF93BQ4T5MJFS","Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Fblob\u002Fmain\u002Fplugins\u002Fopenclaw\u002FSKILL.md",[],[27,67],"openclaw",{"skillNo":69,"name":5,"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":74,"publishedAt":31},"01M69AVPDW8T7960QBW29F3ZEW","Use when the user wants Cursor to learn from recent local sessions, asks for an offline sleep or dream cycle, wants to consolidate recurring work into a Cursor skill, or requests SkillOpt-Sleep status, harvest, dry-run, run, scheduling, review, or adoption. Drives the validation-gated skillopt_sleep engine with Cursor transcripts and the optional Cursor Agent CLI backend.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Fblob\u002Fmain\u002Fplugins\u002Fcursor\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",[73],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[27,75,30,76,28],"status","cli",{"skillNo":78,"name":5,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":31},"01M69AVMGBV7KJX0NF043FPDQ6","Use when the user wants Codex to self-improve from past usage, asks about a nightly\u002Foffline 'sleep' or 'dream' cycle, wants Codex to review past sessions, learn preferences, consolidate memory\u002Fskills, run dry-run\u002Frun\u002Fadopt\u002Fstatus for SkillOpt-Sleep, or schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated memory + skills behind a held-out gate.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",[],[27,75,30,29,83,28],"codex",{"skillNo":85,"name":5,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":90,"publishedAt":31},"01M69AVJA0DE796EKHGVMY10Q1","Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly\u002Foffline 'sleep' or 'dream' cycle, memory\u002Fskill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated CLAUDE.md\u002FSKILL.md behind a held-out gate.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",[89],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[27,28,30,29]]