skillopt-sleep

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.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body with a clear validated workflow and concrete commands. The main weakness is mild verbosity in the conceptual intro and trigger-list redundancy with the description.

Suggestions

Trim the 'synthesizes three ideas' and 'deployment-time analogue of training' prose, or move it to a reference file, since the six-stage cycle already conveys the design.

Collapse the 'When to use this skill' trigger list or replace it with a one-line pointer to the description to avoid restating the same trigger phrases twice.

Consider moving the full CLI flags table and config-keys detail into a reference file, leaving SKILL.md as a lean overview with the most-used commands.

Dimension	Reasoning	Score
Conciseness	The bulk is efficient CLI/config reference content, but the introductory prose ('deployment-time analogue of training') and the 'synthesizes three ideas' block add explanatory padding, and 'When to use this skill' restates trigger phrases already in the description. Not a 3 because the core content still earns its tokens.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands (sleep.sh status/dry-run/run/adopt, schedule), a complete flags table with defaults, config keys, and a deterministic demo command — covering the common cases concretely.	5 / 5
Workflow Clarity	The six-stage cycle is clearly sequenced with an explicit validation checkpoint (held-out gate that 'accept only if it strictly improves'), plus dry-run, backup-before-adopt, and an assert-improves feedback loop for a destructive/batch operation.	5 / 5
Progressive Disclosure	A single well-organized SKILL.md with clear section headers and no nested/buried bundle references (references/, scripts/, assets/ are empty), and external pointers (upstream guide URL, README) are clearly signaled. Not a 5 because some reference-style detail (flags/config) is inlined rather than split out.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both capability and trigger conditions with many natural user phrases. It avoids vague language and is highly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions ('harvest past sessions -> mine recurring tasks -> replay offline -> consolidate validated CLAUDE.md and SKILL.md'), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (drives the skillopt_sleep engine through the harvest→mine→replay→consolidate pipeline) and 'when' via concrete 'Use when the user wants...' trigger phrases.	5 / 5
Trigger Term Quality	Includes a comprehensive set of natural user phrases ('make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle') plus synonyms like sleep/dream.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (offline self-improvement sleep cycle for a local Claude agent) with distinctive triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/skillopt-sleep/skills/skillopt-sleep/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.