nap

Context hygiene — compress, prune, archive .squad/ state

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.squad-templates/skills/nap/SKILL.md

Quality

Content

87%

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

The body is concise, well-structured, and gives executable invocation guidance, but it lacks an explicit validation/safety workflow for its destructive operations. Adding a dry-run-then-confirm checkpoint would close the main gap.

Suggestions

Add a short workflow note: run with --dry-run first, review what would be pruned/archived, then run the real command — giving an explicit validation checkpoint for the destructive operations.

Briefly document what --deep and --dry-run do so the actionable guidance is complete rather than relying on flag names alone.

Clarify whether Claude should verify .squad/ size or history.md thresholds before invoking, turning the "When To Use" triggers into a check-then-act sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean (~25 lines) with no explaining of concepts Claude already knows; each section (What It Does, When To Use, Invocation, Confidence) earns its place.	3 / 3
Actionability	Provides concrete, copy-paste-ready commands for both surfaces ("squad nap", "squad nap --deep", "squad nap --dry-run" and the REPL equivalents), matching the executable-guidance anchor.	3 / 3
Workflow Clarity	Prune/archive/clean are destructive batch operations, yet no validation checkpoint or validate→fix→retry loop is described beyond listing a --dry-run flag, so workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	Under 50 lines with no need for external references and clearly organized sections, satisfying the simple-skill allowance for a top progressive-disclosure score.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 specific and action-oriented but misses explicit trigger guidance and leans on coined terminology a user would not naturally say. Adding a "Use when…" clause with natural-language triggers would raise both completeness and trigger-term quality.

Suggestions

Append a "Use when…" clause with natural triggers, e.g. before fan-out work, when .squad/ grows large, or after long sessions, to satisfy the completeness requirement.

Replace or supplement the coined term "context hygiene" with phrases users actually say (e.g. "clean up .squad/ state", "free up context window") to improve trigger-term quality.

Add a distinguishing cue (mention of .squad/ logs, histories, decisions, or inbox files) to reduce overlap with generic cleanup skills.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions — "compress, prune, archive" — matching the anchor for multiple specific concrete actions rather than just naming a domain.	3 / 3
Completeness	Clearly states what the skill does but includes no "Use when…" trigger clause, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	"Context hygiene" is a coined phrase rather than something a user would naturally say, and the action verbs are relevant but lack common natural variations a user would utter.	2 / 3
Distinctiveness Conflict Risk	The ".squad/ state" scope gives it a niche, but "context hygiene" could overlap with generic cleanup skills and the triggers are not explicit enough to be clearly distinct.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .squad-templates/skills/nap/SKILL.md
Commit: e23dd92

Reviewed: 1 day 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.