Official agent skill

SkillOpt-Sleep OpenClaw Reference

by microsoft in microsoft/SkillOpt

“Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.”

— description from SKILL.md by microsoft
OfficialMITAuto-check passedAgent Workflows

Install SkillOpt-Sleep OpenClaw Reference

skills CLI
$ npx skills add microsoft/SkillOpt --skill skillopt-sleep -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microsoft/SkillOpt skillopt-sleep --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microsoft/SkillOpt.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/openclaw .claude/skills/skillopt-sleep && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skillopt-sleep
GitHub stars
18k
Token cost
~1.3k tokens
SKILL.md length
642 words
Files
10
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

  • Works in 6 steps: Replace every absolute workspace,… → Update the custom backend factory to the… → Replace the experimental adoption logic… → …
  • SKILL.md covers What is included, Known porting gaps, Shared-engine features are not… and Data and credential boundary, plus 1 more section
  • Runs Python and Shell scripts from its folder; calls python

About this skill

SkillOpt-Sleep OpenClaw Reference is an official skill in microsoft/SkillOpt (18k stars). Its SKILL.md is about 1.3k tokens, with 9 other files in the folder. Licence: MIT.

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Replace every absolute workspace, repository, state, skill, log, and task
  2. Update the custom backend factory to the current get_backend call contract,
  3. Replace the experimental adoption logic with the current staging manifest
  4. Decide how real OpenClaw transcripts are converted into a supported session
  5. Build scheduling around the adapted wrapper. The shared scheduler launches
  6. Add isolated end-to-end tests for dry-run, accepted/rejected gates, staging,

What it can do on your machine

Read from SKILL.md and the folder at commit 343db22. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

SkillOpt-Sleep OpenClaw Reference loads about 1.3k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 642 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/SkillOpt at commit 343db22, republished under its MIT licence (© microsoft). 642 words, ~1,279 tokens.

Download SKILL.mdSave it as .claude/skills/skillopt-sleep/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
skillopt-sleep
description
Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.

SkillOpt-Sleep OpenClaw reference adaptation

This directory is a contributed reference, not a supported, plug-and-play OpenClaw integration. It illustrates one way to connect the shared skillopt_sleep cycle to a custom DeepSeek Chat Completions backend and a set of environment-specific task fixtures.

Do not run or schedule the files unchanged. Several scripts and the sample configuration preserve assumptions from the contributor's original machine, and parts of the wrapper have not yet been ported to the current shared-engine interfaces. Start with the directory's README.md, which is the authoritative status and adaptation guide.

What is included

  • skillopt_sleep_openclaw.py — a contributed DeepSeek backend prototype. It also contains an Ollama embedding helper, but that helper is not wired into the current shared sleep cycle.
  • run_sleep.py — a custom cycle wrapper with environment-specific paths and a backend-registration shim.
  • slash_sleep.py — an experimental command helper written for an older staging-manifest shape.
  • run_sleep_cron.sh — a machine-specific category runner, not a portable cron installer.
  • config.json — a sample configuration, not a set of guaranteed or enforced runtime limits.
  • tests/*.json — example task fixtures from one environment, not a universal OpenClaw benchmark.

Known porting gaps

Before treating this as an integration, a maintainer must at least:

  1. Replace every absolute workspace, repository, state, skill, log, and task path with explicit user configuration.
  2. Update the custom backend factory to the current get_backend call contract, including the project directory, and update its backend methods and edit records to the current protocol.
  3. Replace the experimental adoption logic with the current staging manifest and skillopt_sleep.staging.adopt behavior. Current staging artifacts use proposed_SKILL.md / proposed_CLAUDE.md, manifest.json, and report files; they do not expose the old manifest.proposed_skill field.
  4. Decide how real OpenClaw transcripts are converted into a supported session format. Pointing claude_home at an arbitrary agent directory does not by itself make its files Claude Code-compatible JSONL.
  5. Build scheduling around the adapted wrapper. The shared scheduler launches the shared CLI; it does not automatically preserve this custom backend or its category task-file flow.
  6. Add isolated end-to-end tests for dry-run, accepted/rejected gates, staging, adoption and backup, credential failure, and scheduled execution.

Until those gaps are resolved, use the supported shared python -m skillopt_sleep CLI with --backend mock to test SkillOpt-Sleep itself, and treat this directory only as source material for a future OpenClaw port.

Show full SKILL.md (269 more words)Show less

Shared-engine features are not wrapper features

At this revision the supported shared CLI backends are mock, claude, codex, copilot, handoff, and azure_openai; the plugin integration reference is the authoritative list. The shared engine can consolidate a selected skill and project CLAUDE.md memory (controlled by evolve_skill and evolve_memory), and its schedule / unschedule actions manage shared-engine cron entries. Those capabilities do not make the custom OpenClaw wrapper portable: the shared scheduler will not invoke the prototype backend or its category fixtures. Use the shared documentation for those features, not this reference SKILL.

Data and credential boundary

The prototype DeepSeek backend sends task, skill, memory, response, rubric, and reflection content to its configured Chat Completions endpoint. Its source also contains a helper that can send text to an Ollama service if a future port wires that helper into the cycle. Neither path should be assumed to remove every secret or private detail.

Before any port is tested with real data:

  • use isolated, synthetic or explicitly reviewed task files;
  • replace sample business names, personal references, URLs, and machine paths;
  • load credentials through the operator's secret-management mechanism;
  • verify TLS and retention policy for every remote endpoint; and
  • inspect all staged artifacts before adoption.

The bundled fixtures are examples only. Their scores and any old cost estimates do not establish effectiveness, safety, or a stable nightly price for another OpenClaw deployment.

Further information

Contributions that turn this reference into a portable integration should add tests and update all three documents together.

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files in plugins/openclaw of microsoft/SkillOpt.

  • SKILL.md
  • README.md
  • config.json
  • run_sleep.py
  • run_sleep_cron.sh
  • skillopt_sleep_openclaw.py
  • slash_sleep.py
  • tests/devops-tasks.json
  • tests/research-cron-tasks.json
  • tests/wiki-tasks.json

Open the folder on GitHubat commit 343db22

Compare with similar skills

SkillOpt-Sleep OpenClaw Reference next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

SkillOpt-Sleep OpenClaw Reference compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SkillOpt-Sleep OpenClaw Reference this skillmicrosoft/SkillOpt18k—~1.3kAutomated safety check: PassMIT
Distilly Person Profile Buildertitanwings/distilly25k—~15kAutomated safety check: NotesMIT
Mindmemos CLImindscale-noah/MindMemOS1k—~3.4kAutomated safety check: PassNone
Spec Driven Developzhu1090093659/deepseek-pp1.9k—~6.9kAutomated safety check: PassApache-2.0
Remember Learningsdyad-sh/dyad22k—~1.1kAutomated safety check: PassCustom licence
Codex Deepseek Subagentoil-oil/codex-deepseek-subagent376—~673Automated safety check: PassMIT

Similar skills

  • Distills source material about a colleague, a relationship or a celebrity into reusable Person Profiles that an agent can later work from, in English or Chinese.

    25k GitHub stars~15k tokensUpdated 15 days ago
    Agent WorkflowsAuto-check: notes
  • Mindmemos CLI

    mindscale-noah/MindMemOS

    Give an AI agent persistent, cross-session long-term memory through MindMemOS.

    1k GitHub stars~3.4k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Spec Driven Develop

    zhu1090093659/deepseek-pp

    Automates pre-development workflow for large-scale complex tasks.

    1.9k GitHub stars~6.9k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Remember Learnings

    dyad-sh/dyad

    Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

    22k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Codex Deepseek Subagent

    oil-oil/codex-deepseek-subagent

    配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent,支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用;普通 API 问题与配置后的日常编码任务不触发。

    376 GitHub stars~673 tokensUpdated 27 days ago
    Agent WorkflowsAuto-check passed
  • OpenGUI Installer for DSH

    Core-Mate/OpenGUI

    Installs and verifies the latest stable OpenGUI release in a DeepSeek Harness web profile on macOS without disturbing existing plugins or settings.

    1.8k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from microsoft/SkillOpt

  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Official

    Runs a nightly or on-demand sleep cycle for a local Codex agent: review past sessions, replay recurring tasks and stage validated skill and memory edits for adoption.

    18k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • SkillOpt-Sleep for Cursor

    microsoft/SkillOpt

    Official

    Mines recurring tasks from recent local Cursor sessions, replays them to test bounded skill edits, and stages validated improvements to a project Cursor skill for review.

    18k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs a usage-driven self-improvement cycle for the dsh agent: harvest past sessions, mine recurring tasks, replay them and stage validated skill edits.

    18k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about SkillOpt-Sleep OpenClaw Reference

How do I install SkillOpt-Sleep OpenClaw Reference in Claude Code?

Run `npx skills add microsoft/SkillOpt --skill skillopt-sleep -a claude-code`. Or copy the skill folder (plugins/openclaw in microsoft/SkillOpt) into .claude/skills/skillopt-sleep in your project. Claude Code loads it when a task matches its description.

How do I install SkillOpt-Sleep OpenClaw Reference in Codex?

Run `npx skills add microsoft/SkillOpt --skill skillopt-sleep -a codex`. Or copy the skill folder (plugins/openclaw in microsoft/SkillOpt) into .agents/skills/skillopt-sleep in your project. Codex loads it when a task matches its description.

Can I use SkillOpt-Sleep OpenClaw Reference in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/SkillOpt --skill skillopt-sleep -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skillopt-sleep, .gemini/skills/skillopt-sleep, .github/skills/skillopt-sleep and .opencode/skills/skillopt-sleep in your project.

What does SkillOpt-Sleep OpenClaw Reference need to run?

Going by SKILL.md and its folder, SkillOpt-Sleep OpenClaw Reference needs Python and a shell for the scripts in its folder and the command-line tools its instructions call (python).

Does SkillOpt-Sleep OpenClaw Reference access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is SkillOpt-Sleep OpenClaw Reference safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does SkillOpt-Sleep OpenClaw Reference use?

SkillOpt-Sleep OpenClaw Reference is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does SkillOpt-Sleep OpenClaw Reference use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to SkillOpt-Sleep OpenClaw Reference?

Skills that share tags, products or a category with SkillOpt-Sleep OpenClaw Reference: Distilly Person Profile Builder (titanwings/distilly, 25k stars), Mindmemos CLI (mindscale-noah/MindMemOS, 1k stars), Spec Driven Develop (zhu1090093659/deepseek-pp, 1.9k stars) and Remember Learnings (dyad-sh/dyad, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SkillOpt-Sleep OpenClaw Reference?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/SkillOpt, which has 18,087 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.

Source: microsoft/SkillOpt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.