[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AVJA0DE796EKHGVMY10Q1":3,"skill-same:01M69AVJA0DE796EKHGVMY10Q1":57},{"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":23,"publishedAt":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M69AVJA0DE796EKHGVMY10Q1","skillopt-sleep",null,"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.","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\u002Fclaude-code\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27],"skillopt sleep","review","memory","sessions","2026-11-10 10:12:30",false,"---\nname: skillopt-sleep\ndescription: \"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.\"\n---\n\n# SkillOpt-Sleep: usage-driven self-evolution for a local Claude agent\n\nSkillOpt-Sleep gives the user's agent a **sleep cycle**. On demand or on a\nnightly schedule, it reviews real past Claude Code sessions, re-runs recurring\ntasks through the selected backend, and consolidates what it\nlearns into **memory** (`CLAUDE.md`) and **skills** (`SKILL.md`). With the\ndefault validation gate enabled, it keeps only changes that improve a held-out\nscore. Live files change only through explicit adoption or a user-requested\n`--auto-adopt`. It aims to improve this user's recurring work, while making\neach accepted proposal measurable on the run's held-out tasks,\nwith no model-weight training. It is the deployment-time analogue of training:\nshort-term experience → long-term competence.\n\nIt synthesizes three ideas:\n- **SkillOpt** — the skill\u002Fmemory doc is trainable text; bounded add\u002Fdelete\u002Freplace\n  edits; accepted only through a held-out gate; rejected edits are recorded in\n  the run report for review.\n- **Claude Dreams** — consolidation that reads past sessions and proposes changes\n  inside protected learned blocks; the input is never mutated, and output is\n  reviewed before adoption.\n- **Agent sleep** — periodic background replay turns episodes into durable skill.\n\n## When to use this skill\n\nTrigger when the user wants any of:\n- \"make my agent learn from how I use it\" \u002F \"get better the more I use it\" \u002F \"remember my preferences across sessions\"\n- a nightly\u002Fscheduled or on-demand **offline self-improvement \u002F dream \u002F sleep** run\n- to **review past sessions\u002Ftrajectories** and distill recurring tasks\n- to **consolidate** feedback into `CLAUDE.md` or a managed skill\n- to **schedule** the cycle (cron) or **adopt** a staged proposal\n\n## The cycle (six stages)\n\n1. **Harvest** — read `~\u002F.claude\u002Fprojects\u002F*\u002F\u003Csession>.jsonl` + `~\u002F.claude\u002Fhistory.jsonl` (READ-ONLY) → session digests.\n2. **Mine** — digests → `TaskRecord`s (recurring intents + outcome labels + checkable refs where possible).\n3. **Replay** — re-run tasks through the selected backend under the *current*\n   skill+memory → (hard, soft) scores.\n4. **Consolidate** — reflect on failures → propose bounded edits → **gate** on a held-out slice; with the default gate enabled, accept only if it strictly improves.\n5. **Stage** — write the accepted `proposed_CLAUDE.md` and\u002For\n   `proposed_SKILL.md`, plus `report.md`, `report.json`, `manifest.json`, and\n   `diagnostics.json` into `\u003Cproject>\u002F.skillopt-sleep\u002Fstaging\u002F\u003Ctimestamp>\u002F`.\n   **Nothing live changes.** A rejected run still has a report but no proposed\n   live-file replacement.\n6. **Adopt** — explicit (or opt-in auto): copy staged files over live ones, backing up first.\n\n## How to drive it\n\nPrefer the `\u002Fskillopt-sleep` command. Under the hood it calls the bundled runner:\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" status                       # what's happened\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" dry-run --project \"$(pwd)\"    # no-staging preview\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" run --project \"$(pwd)\"        # full cycle, stages a proposal\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" adopt --project \"$(pwd)\"      # apply staged proposal (with backup)\n```\n\n- Default backend is `mock` (deterministic, **no API spend**) — good for trying the plumbing.\n- Add `--backend claude` or `--backend codex` to spend the user's real budget\n  for model-driven optimization. A held-out gain is run-specific evidence, not\n  a guarantee of broader improvement; results depend on the tasks, model, and\n  checks.\n- Scope defaults to the invoked project; `--scope all` harvests every Claude\n  project into the current run's configured targets.\n- A real backend sends truncated transcript\u002Ftask content to its provider. See\n  the data-boundary rules below before using one with sensitive sessions.\n\n### Scheduling\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" schedule --project \"$(pwd)\" --hour 3 --minute 17\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" unschedule --project \"$(pwd)\"\n```\n\nInstalls a nightly cron entry. `unschedule --all` removes every managed entry.\n\n## Common CLI flags\n\n| Flag | Default | Description |\n|------|---------|-------------|\n| `--project PATH` | cwd | Project directory to evolve |\n| `--scope all\\|invoked` | invoked | Harvest scope |\n| `--backend mock\\|claude\\|codex\\|copilot\\|handoff\\|azure_openai` | mock | Backend (mock = no provider calls) |\n| `--model NAME` | backend default | Override the model used for replay |\n| `--source claude\\|codex\\|auto` | claude | Transcript source |\n| `--lookback-hours N` | 72 | Harvest window |\n| `--max-sessions N` | derived | Cap harvested sessions; defaults to 3 × max tasks (120 with current defaults) |\n| `--max-tasks N` | 40 | Cap mined tasks |\n| `--target-skill-path PATH` | `~\u002F.claude\u002Fskills\u002Fskillopt-sleep-learned\u002FSKILL.md` | Explicit SKILL.md to evolve |\n| `--tasks-file PATH` | — | Reviewed TaskRecord JSON (skip harvest) |\n| `--progress` | off | Print phase progress to stderr |\n| `--auto-adopt` | off | Auto-adopt if gate passes |\n| `--edit-budget N` | 4 | Max bounded edits per night |\n| `--preferences TEXT` | empty | Add house rules to the optimizer's reflection prior |\n| `--json` | off | Machine-readable JSON output |\n\nThe CLI also has source\u002Fruntime path overrides (`--claude-home`, `--codex-home`,\nand `--codex-path`) and action-specific flags. Use\n`python -m skillopt_sleep \u003Caction> --help` as the authoritative surface.\n\n## Config keys (`~\u002F.skillopt-sleep\u002Fconfig.json`)\n\nBeyond the CLI flags, advanced behavior is controlled via config:\n\n- **`preferences`** — free-text house rules injected into the optimizer's reflect step (e.g. \"Always use async\u002Fawait\", \"Answers in `\\boxed{}`\").\n- **`gate_mode`** — `on` (default, validation-gated) or `off` (greedy, accept all edits).\n- **`gate_metric`** — `hard`, `soft`, or `mixed` (default). Controls how the held-out gate scores.\n- **`gate_no_regression`** — `false` by default. Set to `true` to reject a candidate when any validation task's configured gate score decreases.\n- **`dream_rollouts`** — >1 enables multi-rollout contrastive reflection per task.\n- **`recall_k`** — >0 recalls K similar past tasks into the dream (long-term memory).\n- **`evolve_memory`** \u002F **`evolve_skill`** — independently toggle CLAUDE.md vs SKILL.md consolidation.\n\n## Memory consolidation\n\nThe sleep cycle can consolidate both:\n- **SKILL.md** — the managed skill file (bounded edits: add\u002Fdelete\u002Freplace)\n- **CLAUDE.md** — the project memory (same bounded edits)\n\nWith the default gate enabled, both are evaluated by the same held-out score.\nSet `evolve_memory: false` to consolidate only skills, or `evolve_skill: false`\nfor only memory.\n\n## Hard rules\n\n- **Never** hand-edit the user's `CLAUDE.md` \u002F `SKILL.md` as part of this skill.\n  Let the engine's explicit `adopt` or user-requested `--auto-adopt` path apply\n  the staging manifest and back up existing 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, replay, judging, and reflection. The Claude\n  transcript path is not guaranteed to remove every secret before those calls.\n  Review provider policy and session contents first. For sensitive data, use\n  `mock` or run `harvest --output \u003Cfile>`, inspect\u002Fredact the JSON, set\n  `\"reviewed\": true`, and replay it with `--tasks-file`; real backends refuse an\n  unreviewed task file.\n- Always show the user the **held-out baseline → candidate** score and the\n  exact proposed edits before suggesting adoption. Evidence before adoption.\n- If asked to demonstrate the mechanism without provider calls, run\n  `python -m skillopt_sleep.experiments.run_experiment --persona researcher --json`\n  — a deterministic synthetic demo of held-out lift and gate rejection. It\n  validates the mechanism, not effectiveness on the user's own tasks.\n\n## Validate \u002F demo\n\n```bash\n# deterministic synthetic demo (no API): score rises and the gate blocks a regression\npython -m skillopt_sleep.experiments.run_experiment --persona researcher --assert-improves\npython -m skillopt_sleep.experiments.run_experiment --persona programmer  --assert-improves\n```\n\nSee the [SkillOpt-Sleep documentation](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Ftree\u002Fmain\u002Fdocs\u002Fsleep)\nfor recorded results, limitations, and the supported integration surface.\n","# SkillOpt-Sleep: usage-driven self-evolution for a local Claude agent\n\nSkillOpt-Sleep gives the user's agent a **sleep cycle**. On demand or on a\nnightly schedule, it reviews real past Claude Code sessions, re-runs recurring\ntasks through the selected backend, and consolidates what it\nlearns into **memory** (`CLAUDE.md`) and **skills** (`SKILL.md`). With the\ndefault validation gate enabled, it keeps only changes that improve a held-out\nscore. Live files change only through explicit adoption or a user-requested\n`--auto-adopt`. It aims to improve this user's recurring work, while making\neach accepted proposal measurable on the run's held-out tasks,\nwith no model-weight training. It is the deployment-time analogue of training:\nshort-term experience → long-term competence.\n\nIt synthesizes three ideas:\n- **SkillOpt** — the skill\u002Fmemory doc is trainable text; bounded add\u002Fdelete\u002Freplace\n  edits; accepted only through a held-out gate; rejected edits are recorded in\n  the run report for review.\n- **Claude Dreams** — consolidation that reads past sessions and proposes changes\n  inside protected learned blocks; the input is never mutated, and output is\n  reviewed before adoption.\n- **Agent sleep** — periodic background replay turns episodes into durable skill.\n\n## When to use this skill\n\nTrigger when the user wants any of:\n- \"make my agent learn from how I use it\" \u002F \"get better the more I use it\" \u002F \"remember my preferences across sessions\"\n- a nightly\u002Fscheduled or on-demand **offline self-improvement \u002F dream \u002F sleep** run\n- to **review past sessions\u002Ftrajectories** and distill recurring tasks\n- to **consolidate** feedback into `CLAUDE.md` or a managed skill\n- to **schedule** the cycle (cron) or **adopt** a staged proposal\n\n## The cycle (six stages)\n\n1. **Harvest** — read `~\u002F.claude\u002Fprojects\u002F*\u002F\u003Csession>.jsonl` + `~\u002F.claude\u002Fhistory.jsonl` (READ-ONLY) → session digests.\n2. **Mine** — digests → `TaskRecord`s (recurring intents + outcome labels + checkable refs where possible).\n3. **Replay** — re-run tasks through the selected backend under the *current*\n   skill+memory → (hard, soft) scores.\n4. **Consolidate** — reflect on failures → propose bounded edits → **gate** on a held-out slice; with the default gate enabled, accept only if it strictly improves.\n5. **Stage** — write the accepted `proposed_CLAUDE.md` and\u002For\n   `proposed_SKILL.md`, plus `report.md`, `report.json`, `manifest.json`, and\n   `diagnostics.json` into `\u003Cproject>\u002F.skillopt-sleep\u002Fstaging\u002F\u003Ctimestamp>\u002F`.\n   **Nothing live changes.** A rejected run still has a report but no proposed\n   live-file replacement.\n6. **Adopt** — explicit (or opt-in auto): copy staged files over live ones, backing up first.\n\n## How to drive it\n\nPrefer the `\u002Fskillopt-sleep` command. Under the hood it calls the bundled runner:\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" status                       # what's happened\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" dry-run --project \"$(pwd)\"    # no-staging preview\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" run --project \"$(pwd)\"        # full cycle, stages a proposal\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" adopt --project \"$(pwd)\"      # apply staged proposal (with backup)\n```\n\n- Default backend is `mock` (deterministic, **no API spend**) — good for trying the plumbing.\n- Add `--backend claude` or `--backend codex` to spend the user's real budget\n  for model-driven optimization. A held-out gain is run-specific evidence, not\n  a guarantee of broader improvement; results depend on the tasks, model, and\n  checks.\n- Scope defaults to the invoked project; `--scope all` harvests every Claude\n  project into the current run's configured targets.\n- A real backend sends truncated transcript\u002Ftask content to its provider. See\n  the data-boundary rules below before using one with sensitive sessions.\n\n### Scheduling\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" schedule --project \"$(pwd)\" --hour 3 --minute 17\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsleep.sh\" unschedule --project \"$(pwd)\"\n```\n\nInstalls a nightly cron entry. `unschedule --all` removes every managed entry.\n\n## Common CLI flags\n\n| Flag | Default | Description |\n|------|---------|-------------|\n| `--project PATH` | cwd | Project directory to evolve |\n| `--scope all\\|invoked` | invoked | Harvest scope |\n| `--backend mock\\|claude\\|codex\\|copilot\\|handoff\\|azure_openai` | mock | Backend (mock = no provider calls) |\n| `--model NAME` | backend default | Override the model used for replay |\n| `--source claude\\|codex\\|auto` | claude | Transcript source |\n| `--lookback-hours N` | 72 | Harvest window |\n| `--max-sessions N` | derived | Cap harvested sessions; defaults to 3 × max tasks (120 with current defaults) |\n| `--max-tasks N` | 40 | Cap mined tasks |\n| `--target-skill-path PATH` | `~\u002F.claude\u002Fskills\u002Fskillopt-sleep-learned\u002FSKILL.md` | Explicit SKILL.md to evolve |\n| `--tasks-file PATH` | — | Reviewed TaskRecord JSON (skip harvest) |\n| `--progress` | off | Print phase progress to stderr |\n| `--auto-adopt` | off | Auto-adopt if gate passes |\n| `--edit-budget N` | 4 | Max bounded edits per night |\n| `--preferences TEXT` | empty | Add house rules to the optimizer's reflection prior |\n| `--json` | off | Machine-readable JSON output |\n\nThe CLI also has source\u002Fruntime path overrides (`--claude-home`, `--codex-home`,\nand `--codex-path`) and action-specific flags. Use\n`python -m skillopt_sleep \u003Caction> --help` as the authoritative surface.\n\n## Config keys (`~\u002F.skillopt-sleep\u002Fconfig.json`)\n\nBeyond the CLI flags, advanced behavior is controlled via config:\n\n- **`preferences`** — free-text house rules injected into the optimizer's reflect step (e.g. \"Always use async\u002Fawait\", \"Answers in `\\boxed{}`\").\n- **`gate_mode`** — `on` (default, validation-gated) or `off` (greedy, accept all edits).\n- **`gate_metric`** — `hard`, `soft`, or `mixed` (default). Controls how the held-out gate scores.\n- **`gate_no_regression`** — `false` by default. Set to `true` to reject a candidate when any validation task's configured gate score decreases.\n- **`dream_rollouts`** — >1 enables multi-rollout contrastive reflection per task.\n- **`recall_k`** — >0 recalls K similar past tasks into the dream (long-term memory).\n- **`evolve_memory`** \u002F **`evolve_skill`** — independently toggle CLAUDE.md vs SKILL.md consolidation.\n\n## Memory consolidation\n\nThe sleep cycle can consolidate both:\n- **SKILL.md** — the managed skill file (bounded edits: add\u002Fdelete\u002Freplace)\n- **CLAUDE.md** — the project memory (same bounded edits)\n\nWith the default gate enabled, both are evaluated by the same held-out score.\nSet `evolve_memory: false` to consolidate only skills, or `evolve_skill: false`\nfor only memory.\n\n## Hard rules\n\n- **Never** hand-edit the user's `CLAUDE.md` \u002F `SKILL.md` as part of this skill.\n  Let the engine's explicit `adopt` or user-requested `--auto-adopt` path apply\n  the staging manifest and back up existing 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, replay, judging, and reflection. The Claude\n  transcript path is not guaranteed to remove every secret before those calls.\n  Review provider policy and session contents first. For sensitive data, use\n  `mock` or run `harvest --output \u003Cfile>`, inspect\u002Fredact the JSON, set\n  `\"reviewed\": true`, and replay it with `--tasks-file`; real backends refuse an\n  unreviewed task file.\n- Always show the user the **held-out baseline → candidate** score and the\n  exact proposed edits before suggesting adoption. Evidence before adoption.\n- If asked to demonstrate the mechanism without provider calls, run\n  `python -m skillopt_sleep.experiments.run_experiment --persona researcher --json`\n  — a deterministic synthetic demo of held-out lift and gate rejection. It\n  validates the mechanism, not effectiveness on the user's own tasks.\n\n## Validate \u002F demo\n\n```bash\n# deterministic synthetic demo (no API): score rises and the gate blocks a regression\npython -m skillopt_sleep.experiments.run_experiment --persona researcher --assert-improves\npython -m skillopt_sleep.experiments.run_experiment --persona programmer  --assert-improves\n```\n\nSee the [SkillOpt-Sleep documentation](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Ftree\u002Fmain\u002Fdocs\u002Fsleep)\nfor recorded results, limitations, and the supported integration surface.\n",{"name":5,"description":7},"main","bc0a392ef0a7f92840ec673d80204d34ced169d0","plugins\u002Fclaude-code\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":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add microsoft\u002FSkillOpt --skill skillopt-sleep",{"tool":49,"command":50},"bunx","bunx skills add microsoft\u002FSkillOpt --skill skillopt-sleep",{"tool":52,"command":53},"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\u002Fclaude-code\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",true,[],[58,65,75,84],{"skillNo":59,"name":5,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":28},"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",[],[24,64],"openclaw",{"skillNo":66,"name":5,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":74,"publishedAt":28},"01M69AVR9TG4AP9WJE9QYEY79X","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSkillOpt\u002Fblob\u002Fmain\u002Fplugins\u002Fdsh\u002Fskills\u002Fskillopt-sleep\u002FSKILL.md",[70,73],{"categoryNo":71,"categoryName":72,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[24,27,26,25],{"skillNo":76,"name":5,"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":81,"publishedAt":28},"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",[80],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[24,27,82,83,25],"status","cli",{"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":89,"publishedAt":28},"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",[],[24,25,82,27,26,90],"codex"]