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

86%

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.

A thorough, highly actionable slash-command skill with concrete commands, a clear phased workflow, and proper validation/confirmation gates for destructive operations. Its main weakness is mild verbosity and inline-heavy structure that could move some detailed guidance into reference files.

Suggestions

Move the 'Reason quality requirements' Bad/Good example pairs into a reference file (e.g. references/verdict-reasons.md) and summarize the rules inline, trimming conciseness padding.

Tighten the Phase 4 Consolidation prose into a numbered checklist mirroring the Phase 1/2 style for consistency and token efficiency.

Consider extracting the results.json schema block into references/results-schema.md and linking to it, improving progressive disclosure for what is currently an inline-heavy body.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — tables, copy-paste bash commands, an Agent prompt template, and a JSON schema — with only minor over-explanation in the Bad/Good reason-quality examples; it does not pad with concepts Claude already knows, so it sits above the 3 anchor but not at the every-token-earns-its-place 5 anchor.	4 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands (scan.sh, quick-diff.sh, save-results.sh), a concrete Agent invocation with a prompt template, an explicit results JSON schema, and a verdict criteria table covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (Quick Scan 1–7, Full Stocktake Phases 1–4) with a checklist, resume detection feedback loop, chunk-based saving, and explicit user-confirmation gates for destructive retire/merge/delete operations, satisfying the validation requirement for batch/destructive workflows.	5 / 5
Progressive Disclosure	Well-organized into clear sections with the three scripts referenced by real, one-level-deep paths, but most detailed judgment guidance (verdict criteria, reason-quality examples, schema) is inlined rather than split into reference files, leaving minor organization gaps versus the cleanly-split 5 anchor.	4 / 5
	Total	18 / 20 Passed

Description

83%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 well-crafted description that clearly states both purpose and trigger, names two distinct operating modes, and uses natural, distinctive vocabulary. Minor room to add synonyms and tighten the 'what' to concrete audit actions.

Dimension	Reasoning	Score
Specificity	Names the domain (auditing Claude skills and commands) and several concrete capabilities — Quick Scan, Full Stocktake, and sequential subagent batch evaluation — with only minor coverage gaps, fitting the 'lists several specific actions' anchor better than the '1-2 concrete actions' anchor.	4 / 5
Completeness	Explicitly answers both 'what' (audits skills/commands for quality via two named modes) and 'when' with a concrete trigger phrase ('Use when auditing Claude skills and commands for quality'), matching the top anchor rather than the 'when could be more explicit' anchor at 4.	5 / 5
Trigger Term Quality	Includes natural terms a user managing skills would say ('auditing Claude skills and commands', 'quality', 'Quick Scan', 'Full Stocktake'), giving good keyword coverage, though a few common synonyms like 'review' or 'clean up' are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (skill/command auditing) with distinctive terms ('stocktake', 'Quick Scan', 'Full Stocktake'), but carries minor overlap risk with other skill-review or quality-checking skills rather than the minimal conflict risk of the 5 anchor.	4 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/skill-stocktake/SKILL.md
Commit: 07756ce

Reviewed: 2 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.