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

78%

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 ./skills/skill-stocktake/SKILL.md

Quality

Content

82%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 content is a well-structured, highly actionable orchestration skill with explicit multi-phase workflows, validation checkpoints, and externalized scripts. It loses points only on minor conciseness padding and a lack of explicit error-recovery loops during subagent evaluation.

Suggestions

Add an explicit feedback loop for subagent evaluation failures (e.g., retry/escalation if a subagent returns invalid JSON), which would lift workflow_clarity to the top anchor.

Trim the Notes section and consolidate redundant statements about verdict-branching origin to tighten conciseness.

Consider moving the lengthy Phase 2 good/bad reason-quality examples into a referenced reference file to reduce inline bulk and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational — exact script paths, bash commands, an Agent invocation, a JSON schema, and verdict criteria with good/bad pairs — with only minor over-explanation (e.g., the Notes section restates 'no verdict branching by origin' and the guiding-dimensions list is slightly explanatory), fitting 'efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean anchor 5.	4 / 5
Actionability	It provides copy-paste-ready, executable guidance throughout: exact `bash ~/.claude/skills/skill-stocktake/scripts/scan.sh` commands, a concrete `Agent(subagent_type="general-purpose", ...)` invocation, a results.json schema, and a `date -u +%Y-%m-%dT%H:%M:%SZ` command, matching 'fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	The Quick Scan flow (numbered steps 1–7) and Full Stocktake phases (1–4) are clearly sequenced with validation checkpoints — the `[]` early-stop, resume detection on 'in_progress', intermediate chunk saves, and user-confirmation gates on destructive archive/delete operations — but there is no explicit error-recovery loop during subagent evaluation itself, leaving a minor gap below anchor 5.	4 / 5
Progressive Disclosure	Operational bash logic is correctly split into external scripts (quick-diff.sh, save-results.sh, scan.sh — all real files referenced by exact one-level-deep paths) while orchestration stays inline, with clear section headers throughout; the body is fairly long and the Phase 2 good/bad example pairs are sizable inline content that could arguably live in a reference, placing it at 'good structure; minor organization gaps' rather than anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

75%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 clear, third-person, and explicitly trigger-gated with a 'Use when' clause, covering both what the skill does and when to invoke it. It is strong but stops short of the top anchor because the 'when' condition largely restates the 'what' and omits common trigger synonyms.

Suggestions

Differentiate the 'when' clause from the 'what' by adding concrete trigger phrasing users would actually say, e.g. 'Use when reviewing, cleaning up, or taking stock of your Claude skills and commands.'

Add common synonyms/variants (review, check, clean up, prune) to broaden natural trigger coverage.

Consider mentioning the results cache or resume behavior in the description to further distinguish the skill from a generic audit.

Dimension	Reasoning	Score
Specificity	Names the domain ('auditing Claude skills and commands for quality') and lists several concrete capabilities — 'Quick Scan (changed skills only)', 'Full Stocktake modes', 'sequential subagent batch evaluation' — with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the less comprehensive anchor 3.	4 / 5
Completeness	It explicitly answers both what (audits skills/commands for quality via two modes plus batch evaluation) and when ('Use when auditing...'), but the 'when' largely restates the 'what' rather than enumerating distinct concrete trigger conditions, so it falls short of the anchor-5 example.	4 / 5
Trigger Term Quality	The 'Use when auditing Claude skills and commands for quality' clause surfaces natural keywords (auditing, skills, commands, quality) a user would say, but common synonyms like 'review', 'check', or 'clean up' are missing, fitting the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The 'Claude skills and commands' qualifier carves a clear niche with mostly distinct triggers, though 'auditing for quality' is broad enough to risk minor overlap with general review skills, placing it at 'mostly distinct; minor overlap risk' rather than the fully distinct anchor 5.	4 / 5
	Total	16 / 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: d8409a4

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.