source-command-audit-prose

Add descriptive prose to bare sections in whitepapers (FR + EN) using 9 parallel agents

Quality

64%

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-audit-prose/SKILL.md

Quality

Content

75%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 highly actionable with concrete templates, mapping tables, and verification commands, and the workflow is clearly sequenced with validation. The main gap is duplicated rule/definition text between the main body and the embedded agent prompt.

Suggestions

De-duplicate the strict rules and bare-section definition: state them once in the body and have the agent prompt reference them rather than restating them verbatim.

Turn the post-enrichment verification into an explicit feedback loop (check -> if fail, fix -> re-run) to push workflow_clarity to 5.

If the per-WP budget table and agent prompt grow further, consider moving them into a reference file referenced one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but the strict rules and the "bare section" definition are restated nearly verbatim inside the agent prompt block (steps and rules duplicated from the earlier "Règles Strictes" section), which could be tightened by referencing the canonical rules once.	3 / 5
Actionability	Usage examples with arguments, a full WP mapping table, a copy-paste-ready agent prompt template, concrete post-enrichment bash verification, and per-WP line budgets give fully executable, copy-paste-ready guidance covering the common cases.	5 / 5
Workflow Clarity	The multi-step process is clearly sequenced (sources, mapping, conditional single-vs-9-agent execution, agent steps 1-8, reporting, shutdown, verification) with validation checkpoints (grep/wc checks), but the post-enrichment verification lists checks without an explicit fix-and-retry feedback loop, leaving it just below the level-5 anchor.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so all content is inline; however it is well-organized into clearly headed sections with signaled workspace input paths (reference.yaml, ultimate-guide.md), fitting the good-structure anchor rather than the one-level-deep-reference level 5 which requires separate files.	4 / 5
	Total	16 / 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 states a clear, specific capability but omits any explicit trigger guidance, which is the main weakness. It is reasonably distinct from other skills but lacks natural user-facing keywords.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to enrich, fill in, or add intro prose to bare whitepaper sections, or mentions /audit-prose.'

Include natural synonyms users would say (e.g. 'intro paragraphs', 'descriptive text', '.qmd whitepapers') alongside 'bare sections'.

Reframe in third-person action voice and consider listing the key sub-actions (identify bare sections, add 2-4 sentence prose, verify Typst constraints) to lift specificity.

Dimension	Reasoning	Score
Specificity	"Add descriptive prose to bare sections in whitepapers (FR + EN) using 9 parallel agents" names the domain and one concrete action with modifiers (FR+EN, 9 agents), but does not list several distinct specific actions, matching the anchor for naming domain with 1-2 concrete actions rather than the several-action anchor at 4.	3 / 5
Completeness	The "what" is clear (add descriptive prose to bare sections in FR/EN whitepapers via 9 agents) but there is no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords like "whitepapers", "prose", and "bare sections" are relevant but somewhat technical; common natural synonyms a user would actually say (e.g. "fill in", "intro paragraphs", ".qmd") are missing, fitting the anchor for some relevant keywords lacking common variations.	3 / 5
Distinctiveness Conflict Risk	"Bare sections in whitepapers (FR + EN)" carves a specific niche unlikely to trigger for unrelated skills, fitting the mostly-distinct anchor with only minor overlap risk; it is not quite the minimal-conflict level 5 because trigger phrasing is thin.	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-audit-prose/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.