artefact-logger

Log access to Claude configuration artefacts (CLAUDE.md, rules, skills, commands, agents). This skill should be invoked automatically after reading configuration files to track usage.

Quality

75%

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 ./.claude/skills/artefact-logger/SKILL.md

Quality

Content

87%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 concise, actionable, and well-structured with a verified script reference and copy-paste examples. The only meaningful gap is the absence of validation or a feedback loop for what is effectively a batch logging operation, which caps workflow clarity.

Suggestions

Add a verification checkpoint after logging (e.g. confirm the new entry exists in .claude/artefacts.yaml) to satisfy the batch-operation validation expectation.

Have the script guard the appended YAML against malformed or duplicate entries, or note in the body that duplicates are expected, to address the validation gap.

Add brief examples for the 'command' and 'agent' types so all documented valid types have a copy-paste reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no padding or explanation of concepts Claude already knows; every section (When to Use, How to Log, Arguments, Examples, Notes) earns its place, matching the 'lean and efficient, every token earns its place' anchor.	5 / 5
Actionability	It gives a fully executable command with the real script path, an argument table with valid type values, and three copy-paste-ready examples covering the common cases, matching the 'fully executable, copy-paste ready, common cases covered' anchor.	5 / 5
Workflow Clarity	Although the single logging action is unambiguous, this is a batch/automated operation whose script appends raw YAML with no validation that the entry was written or that artefacts.yaml stays well-formed, so the missing-validation cap for batch operations applies, capping it at the 'steps present but validation gaps' anchor.	3 / 5
Progressive Disclosure	As a sub-50-line simple skill it is organized into clear sections with a single one-level-deep, real script reference (scripts/log-artefact.sh, which exists) and no nested references, matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	18 / 20 Passed

Description

62%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 clearly states what the skill does and when it should fire, with a concrete niche and enumerated artefact types. Its main weaknesses are a single-action specificity, file-type keywords rather than natural user phrases, and a slightly broad 'after reading configuration files' trigger.

Suggestions

Broaden the action vocabulary beyond 'Log access' (e.g. 'Tracks and records access') to lift specificity toward a comprehensive action list.

Add natural trigger phrasing a user would say (e.g. 'Use after reading or loading CLAUDE.md, rules, skills, commands, or custom agents') instead of relying solely on artefact file-type labels.

Tighten the 'when' clause by naming the concrete reading events that should trigger logging, reducing overlap risk with general config-handling skills.

Dimension	Reasoning	Score
Specificity	Names the domain (configuration artefacts) and one concrete action ('Log access to') with enumerated types, but does not list several specific actions; matches the 'domain plus 1-2 concrete actions' anchor rather than the broader coverage of 4.	3 / 5
Completeness	Both 'what' (log access to configuration artefacts to track usage) and 'when' (after reading configuration files) are explicit, but the 'when' trigger could be more specific with concrete user-facing phrases, placing it at the 'both present, when could be more explicit' anchor rather than 5.	4 / 5
Trigger Term Quality	Relevant artefact-name keywords (CLAUDE.md, rules, skills, commands, agents) are present, but these are file-type labels rather than natural phrases a user would say, and common synonyms or variations are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The logging niche is narrowly distinct from other skills, but the 'after reading configuration files' trigger is broad enough to risk minor overlap with related config-handling skills, matching the 'mostly distinct, minor overlap risk' anchor rather than the minimal-conflict 5.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cteyton/packmind
Path: .claude/skills/artefact-logger/SKILL.md
Commit: e198635

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.