guide-recap

Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate ready-to-post content from guide updates.

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 findings from the security scan

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.

A well-structured, actionable skill body with concrete commands, a precise scoring algorithm, and clean progressive disclosure into reference files. The main weaknesses are two dangling example-file references and validation handled by external checklist reference rather than inline feedback loops.

Suggestions

Create the missing examples/version-output.md and examples/week-output.md files (or remove those two lines from the Reference Files section) so every cited path resolves.

Inline a brief validate-then-fix checkpoint in Step 6 (e.g., 're-check tone-guidelines DO list; if a DON'T is present, revise before output') instead of only referencing the external checklist.

Trim the Reference Files section to entries not already named inline, or remove the inline re-citations, to reduce duplication.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-organized with tables, flag tables, and a concrete scoring formula rather than padded prose, though the 'Reference Files' section partially duplicates paths already cited inline and the Output example block is somewhat long.	4 / 5
Actionability	Provides copy-paste-ready commands (`/guide-recap latest`, `week 2026-01-27`), an explicit numeric scoring formula, exact file paths, hard-coded URLs, and per-format link targets — concrete and executable guidance covering the common cases.	5 / 5
Workflow Clarity	Seven clearly sequenced steps with an error-handling table giving recovery suggestions and a score-threshold gate in Step 5, but validation is largely delegated to external checklists (tone-guidelines DO/DON'T) rather than an explicit inline validate->fix->retry loop.	4 / 5
Progressive Disclosure	Good one-level-deep structure: details split into references/ and assets/ with a dedicated 'Reference Files' index, and all references/ and assets/ files exist — but the body cites examples/version-output.md and examples/week-output.md whose examples/ directory does not exist, leaving two broken navigation paths.	4 / 5
	Total	17 / 20 Passed

Description

87%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 strong, concrete description that states what it does, when to use it, and the specific output formats and languages, with minimal conflict risk. The only minor gap is a slightly limited action verb set and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Transform CHANGELOG entries into social content') and enumerates concrete output targets across four formats (LinkedIn, Twitter/X, Newsletter, Slack) and two languages (FR + EN), giving broad coverage though the verb set is limited to transform/generate.	4 / 5
Completeness	Explicitly answers both what ('Transform CHANGELOG entries into social content ... in FR + EN') and when ('Use after releases or weekly to generate ready-to-post content from guide updates') with a concrete trigger clause.	5 / 5
Trigger Term Quality	Strong natural keywords a user would actually say — 'CHANGELOG entries', 'social content', 'LinkedIn', 'Twitter/X', 'Newsletter', 'Slack', 'releases', 'weekly' — including the Twitter/X synonym pair, but omits common variants like 'social media posts' or 'announce a release'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (CHANGELOG-to-social-content for guide updates) with distinct platform triggers unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Path: .agents/skills/guide-recap/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.