Skip to content
SkillScript-led1,053 tokens in use

SkillOpt Sleep OpenClaw Reference

A contributed reference port of SkillOpt-Sleep to OpenClaw with a DeepSeek backend prototype, meant for study and adaptation before any use.

19,169 stars on the repository MIT Licensemicrosoft/SkillOpt · plugins/openclaw

Skill label

measured from its files

What installing SkillOpt Sleep OpenClaw Reference costs

38tokens idle
1,053tokens in use
2,477tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: run_sleep.py, run_sleep_cron.sh, skillopt_sleep_openclaw.py, slash_sleep.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure16/25
  • Examples3/15
  • Output15/15
  • Size13/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    run_sleep_cron.sh, line 11
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    run_sleep_cron.sh, line 16
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    run_sleep_cron.sh, line 43
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    skillopt_sleep_openclaw.py, line 26

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity96
  • Maintenance84
  • Community68
  • Maturity28
  • Momentum40

This folder is a reference adaptation of SkillOpt-Sleep for OpenClaw. It holds a DeepSeek Chat Completions backend prototype, a cycle wrapper, a slash-command helper, a cron runner and a sample configuration.

The skill says it is not a plug-and-play integration. Paths come from the contributor’s machine and parts of the wrapper predate the current engine interfaces, so it lists the porting gaps to close first.

What You Get

  • A DeepSeek backend prototype covering attempt, judge and reflect steps, with an Ollama embedding helper that is not wired in
  • A cycle wrapper, a /sleep style command helper and a category-based cron runner as source material
  • A sample configuration with gate, edit budget and token limits
  • A six-point checklist for turning the reference into a portable integration

Common Use Cases

  • Study how a custom backend plugs into the shared skillopt_sleep engine
  • Use it as a starting point for an OpenClaw or other custom-agent port
  • Review the data boundary of a third-party model backend before adopting one
  • Test SkillOpt-Sleep itself with the shared CLI and the mock backend while the port is unfinished

What Makes It Unique

Most skills in the directory are ready to install. This one is source material: its SKILL.md tells the reader not to run or schedule the files unchanged and points to the shared CLI for anything supported. Its value is the worked example of a non-default backend and the explicit list of what a port must fix.

Under The Hood

The SKILL.md is prose that points the reader at the folder’s README and scripts. The scripts include a Python wrapper that imports the engine from a hard-coded repository path, a backend that sends task, skill, memory and rubric text to a DeepSeek chat endpoint using an API key read from an environment variable or a local env file, a helper that posts text to a local Ollama service, a command helper that can copy a staged skill over a live one and delete staging folders, and a shell runner that loops over task files and writes logs. All paths belong to the contributor’s machine and must be replaced before use.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers