Name: skillopt-sleep
Rating: 74.4 (1 reviews)
Author: microsoft

skillopt-sleep

Use when the user wants the dsh agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, skill/memory 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.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

The body is a well-structured, actionable guide: a sequenced six-stage workflow with a real validation gate, executable tool commands, and clear safety boundaries around the destructive adopt step. It is mostly concise and uses external docs for deeper material rather than inlining everything.

Suggestions

Tighten the opening paragraph ('SkillOpt-Sleep is Microsoft's SkillOpt deployment-time companion engine: it reviews...') since the 'When to use' and cycle sections already convey the same information more concretely.

Move the advanced engine config keys (gate_mode, gate_metric, dream_rollouts, recall_k, etc.) into a short referenced section or table so the main flow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence (tool table, params table, tight hard-rules list), with only minor introductory prose ('SkillOpt-Sleep is Microsoft's SkillOpt deployment-time companion engine...') that could be trimmed, fitting the 'efficient; minor instances of over-explanation' anchor rather than the maximally lean 5.	4 / 5
Actionability	Provides copy-paste-ready commands with realistic arguments ('skillopt_run project=<dir> backend=<codex\|claude\|...> preferences=...', 'skillopt_adopt project=<dir>'), a full tool-behavior table, a parameters table, and a YAML config patch, covering the common cases fully executably.	5 / 5
Workflow Clarity	The six-stage cycle is clearly sequenced with an explicit validation checkpoint (held-out slice, 'accept only on strict improvement'), a backup-before-adopt live-change boundary, and an 'evidence before adoption' hard rule; the destructive/batch cap does not apply because validation is present.	5 / 5
Progressive Disclosure	No bundle files exist, but the body is well-sectioned with clear headers and a one-level-deep external docs link; advanced engine keys are kept inline only briefly. This fits 'good structure; most content appropriately placed; minor organization gaps' rather than the ideal split-over-files 5.	4 / 5
	Total	18 / 20 Passed

Description

95%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.

The description is strong: it opens with an explicit 'Use when' clause packed with natural trigger phrases, then states the concrete four-stage pipeline the skill drives. Voice is third person and there is no vague fluff or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('harvest past sessions', 'mine recurring tasks', 'replay via a selected backend', 'consolidate validated skills behind a held-out gate'), with only minor coverage gaps, matching the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both 'what' (drives the engine: harvest -> mine -> replay -> consolidate) and 'when' via a clear 'Use when...' clause with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers users would actually say ('make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', 'sleep/dream cycle', 'schedule background self-optimization'), including synonyms, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skillopt_sleep engine / dsh offline self-evolution) with distinctive triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	19 / 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: microsoft/SkillOpt
Path: plugins/dsh/skills/skillopt-sleep/SKILL.md
Commit: 79124b3

Reviewed: 5 days 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.