skill-stocktake

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

85%

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, highly actionable orchestration document with clear sequencing, validation checkpoints, and real one-level-deep script references. Its only real weakness is conciseness — a few illustrative blocks and repeated paths could be trimmed without losing clarity.

Suggestions

Tighten the 'Reason quality requirements' Bad/Good example pairs to one compact line each, or move the full examples into a reference file, to reduce body length.

Factor the repeated `~/.claude/skills/skill-stocktake/scripts/` path prefix into a defined variable or a single 'Scripts live in …' note to cut repetition.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and instructional — concrete commands, tables, and a JSON schema rather than concept explanations Claude already knows — but the multi-example Bad/Good 'reason quality requirements' block and some repeated path strings could be tightened. Not 3 because not every token earns its place; not 1 because there is no padded background exposition.	2 / 3
Actionability	Provides copy-paste-ready bash commands (scan.sh, quick-diff.sh, save-results.sh invocations), a concrete Agent() prompt template, an explicit `date -u` timestamp command, and a full results.json schema. Not 2 because guidance is fully executable, not pseudocode.	3 / 3
Workflow Clarity	Both flows are explicitly sequenced (Quick Scan 1–7, Full Stocktake Phases 1–4) with a checklist, resume detection as a feedback loop, and an explicit confirmation checkpoint before destructive archive/delete operations. Not 2 because validation checkpoints for batch/destructive work are present and signaled.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview that delegates executable logic to one-level-deep, full-path script references (scan.sh, quick-diff.sh, save-results.sh), all of which exist under ./scripts/, with well-organized sections and easy navigation. Not 2 because references are clearly signaled and shallow, not nested.	3 / 3
	Total	11 / 12 Passed

Description

85%

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, complete, and occupies a distinct niche with an explicit 'Use when' trigger. Its main weakness is trigger-term coverage, which relies on a single verb ('auditing') and omits common synonyms a user might naturally say.

Suggestions

Broaden trigger terms to include natural synonyms users might say, e.g. 'Use when reviewing, auditing, or cleaning up Claude skills and commands'.

Consider mentioning the slash-command invocation ('/skill-stocktake') in the description so users who type the command recognize the match.

Dimension	Reasoning	Score
Specificity	Names the domain ('auditing Claude skills and commands for quality') and multiple concrete capabilities — 'Quick Scan (changed skills only)', 'Full Stocktake modes', 'sequential subagent batch evaluation' — matching the multi-action anchor. Not score 2 because it goes beyond naming a domain plus a single action.	3 / 3
Completeness	Explicit 'Use when auditing...' clause answers when, and 'Supports Quick Scan ... and Full Stocktake modes ...' answers what, satisfying both halves with an explicit trigger. Not 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	Contains relevant keywords ('auditing', 'skills', 'commands', 'quality') but misses common natural variations a user might say ('review', 'check', 'clean up', 'stocktake'). Not 3 because coverage of natural phrasings is thin; not 1 because core trigger terms are present.	2 / 3
Distinctiveness Conflict Risk	Targets a clear meta-niche (auditing skills/commands for quality) with distinct triggers unlikely to fire for ordinary skills. Not 2 because it is not a broad document/code category that would overlap with sibling skills.	3 / 3
	Total	11 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

Reviewed: 4 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.