Skillopt Sleep

What it does

When your agent uses it

• The user wants their Claude agent to self-improve from past usage
• Asks about a nightly/offline sleep
• Memory/skill consolidation
• Says things like make my agent better the more I use it

Example prompts

• “cycle, memory/skill consolidation, or says things like”
• “review my past sessions”
• “learn my preferences”
• “/skillopt-sleep”

Requirements

• Python 3

Workflow steps

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

1. 1Harvest — read ~/.claude/projects/*/.jsonl + ~/.claude/history.jsonl (READ-ONLY) → session digests.
2. 2Mine — digests → TaskRecords (recurring intents + outcome labels + checkable refs where possible).
3. 3Replay — re-run tasks offline under the current skill+memory → (hard, soft) scores.
4. 4Consolidate — reflect on failures → propose bounded edits → gate on a held-out slice; accept only if it strictly improves.
5. 5Stage — write proposed_CLAUDE.md, proposed_SKILL.md, a diff, and report.md into /.skillopt-sleep/staging//. Nothing live changes.
6. 6Adopt — explicit (or opt-in auto): copy staged files over live ones, backing up first.

What it can do on your machine

Read from SKILL.md and the folder at commit 19392f7. 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

  Shell commands in SKILL.md call:

  • python

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

• Network

  Links to these hosts (documentation or services it may open):

  • microsoft.github.io

  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 loads about 1.8k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 713 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~140

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

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

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 alirezarezvani/claude-skills at commit 19392f7, republished under its MIT licence (© alirezarezvani). 713 words, ~1,793 tokens.

name

skillopt-sleep

description

Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill 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 offline self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay offline -> consolidate validated CLAUDE.md and SKILL.md behind a held-out gate.

"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" status                       # what's happened
"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" dry-run --project "$(pwd)"    # safe preview
"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" run --project "$(pwd)"        # full cycle, stages a proposal
"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" adopt --project "$(pwd)"      # apply staged proposal (with backup)

"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" schedule --project "$(pwd)" --hour 3 --minute 17
"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" unschedule --project "$(pwd)"

# deterministic proof (no API): held-out score rises, gate blocks regressions
python -m skillopt_sleep.experiments.run_experiment --persona researcher --assert-improves
python -m skillopt_sleep.experiments.run_experiment --persona programmer  --assert-improves

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

Files

Just SKILL.md in engineering/skillopt-sleep/skills/skillopt-sleep of alirezarezvani/claude-skills.

Open the folder on GitHubat commit 19392f7