nap

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

Quality

65%

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

72%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 tight, well-organized body that specifies concrete invocation commands and quantified usage triggers. Its main gaps are the absence of any validate-then-execute workflow for what is a destructive batch operation, and minor token duplication between the frontmatter, blockquote, and Confidence section.

Suggestions

Add a validation sequence, e.g., 'Run `squad nap --dry-run` first, review the affected files, then run without --dry-run'.

Remove the duplicate description blockquote and the Confidence section, which restate frontmatter metadata.

Include a short example of the command output and what a successful run should report.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations and specific thresholds ("history.md files exceed 15KB", "total size exceeds 1MB"), but the opening blockquote duplicates the frontmatter description and the Confidence section ('medium — Confirmed by team vote (4-1)') is execution-irrelevant metadata that could be trimmed. This matches 'efficient; minor instances that could be trimmed' rather than the every-token-earns-its-place level 5.	4 / 5
Actionability	The Invocation section gives concrete, executable commands with flag variants (`squad nap --deep`, `squad nap --dry-run`, `/nap`), fitting 'mostly executable guidance with minor gaps'. Not 5, because there is no example output, no guidance on interpreting results, and no direction on which flags to use when.	4 / 5
Workflow Clarity	The skill performs destructive batch operations (pruning old logs, cleaning orphaned inbox files, archiving decisions), and the body contains no validation or verification step — a safety-relevant `--dry-run` flag is listed but never sequenced into a check-then-run workflow. Per the rubric's cap this cannot exceed 3 even for a single-purpose skill; it is not 2 because the single action itself is unambiguously specified.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no external references needed, and the content is organized into clean, well-labeled sections (What It Does, When To Use, Invocation, Confidence). Per the rubric's simple-skill guidance this earns a 5 with no bundle files required.	5 / 5
	Total	16 / 20 Passed

Description

58%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 concise and names concrete actions against a specific target, but it omits any 'Use when...' trigger guidance and lacks the natural phrasings a user would say when they need this skill. It describes a distinct niche yet reads more like a terse label than a triggerable capability statement.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the context window is tight, before large fan-outs, or when .squad/ grows large'.

State the objects of each action (compress agent histories, prune old logs, archive stale decisions, clean orphaned inbox files) so the coverage is comprehensive.

Include natural user phrasings and synonyms such as 'free up context', 'clean up .squad', or 'reclaim context budget'.

Dimension	Reasoning	Score
Specificity	The description lists three concrete actions ("compress, prune, archive") with a specific target (".squad/ state"), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because the objects of each action (histories, logs, decisions, inbox files) are not stated, and below 3 because it names the domain plus three actions rather than only 1-2.	4 / 5
Completeness	It clearly answers 'what' ("compress, prune, archive .squad/ state") but there is no 'when' clause at all, which caps completeness at 3 per the judging guidelines. It is not 2, since the 'what' is concrete rather than vague, and cannot be 4+ without explicit trigger guidance.	3 / 5
Trigger Term Quality	Relevant keywords are present ("context hygiene", "compress", "archive", ".squad/") but common natural phrases a user would actually say (e.g., "free up context", "clean up .squad", "context window is full") and their synonyms are missing. Not 2, because the terms are domain-relevant and include a concrete path rather than purely generic words like "Works with files"; not 4, because coverage of natural user phrasings is thin.	3 / 5
Distinctiveness Conflict Risk	The ".squad/ state" scope carves out a clear niche with low overlap against generic skills, fitting 'mostly distinct; minor overlap risk'. Not 5, because "context hygiene" is a broad concept and the description carries no distinct trigger phrases to disambiguate it from other cleanup/maintenance skills.	4 / 5
	Total	14 / 20 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: 29e69f5

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.