source-command-ccguide-refresh-docs

Re-fetch official Anthropic Codex docs and update current snapshot (baseline unchanged)

Quality

66%

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 ./.agents/skills/source-command-ccguide-refresh-docs/SKILL.md

Quality

Content

78%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 lean, well-structured simple skill that names the exact tool and follow-up actions without padding. The main gap is the lack of an explicit invocation signature and an explicit error-handling feedback loop around the tool call.

Suggestions

Add the exact invocation for the refresh_official_docs MCP tool (parameters/signature) so the call is copy-paste ready.

Add an explicit error path: what to do if the fetch fails or the tool returns no diff, to turn the implicit 'After success' gate into a real validation checkpoint.

Drop or tighten the 'migrated source command' framing, which adds context without aiding execution.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence — it names the tool and post-steps without explaining what an MCP tool or a snapshot is. Not a 5 because the 'migrated source command' framing and the '~1.2MB (takes ~5s)' detail are mildly trimmable; not a 3 because there is no padded explanation of concepts Claude already knows.	4 / 5
Actionability	Gives the concrete tool to call ('refresh_official_docs' MCP tool) and a concrete follow-up command ('/ccguide:diff-docs') plus post-success actions. Not a 5 because no exact invocation signature or example call is provided; not a 3 because the guidance is executable, not pseudocode or vague direction.	4 / 5
Workflow Clarity	The single action (run the tool) is unambiguous with a clear post-success sequence (show the returned diff preview, remind user to run /ccguide:diff-docs); the destructive/batch cap does not apply since the baseline is never touched. Not a 5 because the success check is implicit ('After success') with no explicit error-handling feedback loop; not a 3 because the sequence and success gate are clear.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references, organized under a clear 'Command Template' section — meeting the rubric's simple-skill exception for a top score. Not lower because the structure is well-organized and there are no nested or buried references.	5 / 5
	Total	17 / 20 Passed

Description

53%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 a clear, distinct niche with two concrete actions, but it omits any 'Use when...' trigger guidance and misses the natural term 'refresh'. Addressing the missing trigger clause and matching the user-facing command name would lift the two lowest dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to refresh or re-fetch the Codex docs snapshot.'

Include the natural trigger term 'refresh' (matching the command name) alongside 'Re-fetch' so users' actual phrasing is covered.

Briefly contrast with sibling skills (e.g. note this only updates the 'current' snapshot, unlike init_official_docs which sets the baseline) to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain (Anthropic Codex docs) and two concrete actions ('Re-fetch ... docs and update current snapshot'), but coverage is not comprehensive beyond those two actions. Not a 4 because only two actions are listed with no further specifics; not a 2 because the actions are concrete rather than generic.	3 / 5
Completeness	Clearly states what the skill does ('Re-fetch ... docs and update current snapshot (baseline unchanged)') but has no 'Use when...' clause or explicit trigger guidance, capping completeness at 3 per the rubric. Not a 4 because 'when' is entirely absent rather than weakly implied; not a 2 because the 'what' is clear, not vague.	3 / 5
Trigger Term Quality	Contains relevant keywords ('Re-fetch', 'official Anthropic Codex docs', 'update ... snapshot') but omits the natural user-facing term 'refresh' that matches the command name. Not a 4 because a common natural variation ('refresh the docs') is missing; not a 2 because several relevant keywords are present rather than just one generic term.	3 / 5
Distinctiveness Conflict Risk	Targets a narrow niche (refreshing the Codex docs 'current' snapshot) and the '(baseline unchanged)' clause distinguishes it from sibling init/diff skills, leaving only minor overlap risk. Not a 5 because the description does not explicitly contrast with the related init_official_docs / diff-docs skills; not a 3 because it is more specific than 'works with document files'.	4 / 5
	Total	13 / 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: FlorianBruniaux/claude-code-ultimate-guide
Path: .agents/skills/source-command-ccguide-refresh-docs/SKILL.md
Commit: e828d7f

Reviewed: 3 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.