briefing-critique

Compare generated draft pages against the source briefing to catch copy errors, missing content, wrong block types, and structural mismatches. Use when "critique drafts", "check briefing compliance", "verify content fidelity", "QA against briefing", or "validate draft pages".

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

81%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 highly actionable, well-sequenced audit skill with strong validation and copy-paste scripts. The main weakness is length and some duplicated guidance between steps and troubleshooting.

Suggestions

Deduplicate the CDN-reachability check: define it once in Step 6 and have Step 8 reference it rather than re-listing the same curl loop and severity.

Extract the two large Python diff scripts into a scripts/ bundle file, keeping only a short invocation snippet in SKILL.md to reduce the inline wall of code.

Trim the Troubleshooting table to entries that add information beyond the corresponding step (e.g., drop rows that merely point back to a step already stating the rule).

Dimension	Reasoning	Score
Conciseness	Mostly efficient and concrete, but ~680 lines with redundancy: the CDN-reachability check appears in both Step 6 and Step 8, and the Troubleshooting table restates guidance already covered in the steps.	3 / 5
Actionability	Fully executable, copy-paste-ready Python diff scripts plus exact curl/grep commands and concrete file paths with clearly marked {sitename} placeholders covering the common cases.	5 / 5
Workflow Clarity	Eleven clearly sequenced steps with mechanical script-based validation, per-page continue-on-failure logic, an explicit cross-page checklist, and defined verdict/severity criteria.	5 / 5
Progressive Disclosure	References (critique-overlay.js, report-template.html) are real, one-level-deep, and well-signaled, but the two large templated Python scripts are inlined rather than split into a scripts/ bundle.	4 / 5
	Total	17 / 20 Passed

Description

88%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 well-crafted description that clearly answers what the skill does and when to use it, with multiple natural trigger phrases. Minor room to add file-extension triggers and sharpen distinctiveness from sibling audit skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete detection actions — 'catch copy errors, missing content, wrong block types, and structural mismatches' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly states both the 'what' (compare drafts against briefing to catch errors) and the 'when' via a concrete 'Use when ...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Strong natural-language triggers ('critique drafts', 'check briefing compliance', 'verify content fidelity', 'QA against briefing', 'validate draft pages') with good synonym coverage, but no file extensions such as .plain.html are included.	4 / 5
Distinctiveness Conflict Risk	Has a clear briefing-fidelity niche with distinct triggers, but some overlap risk with broader QA/site-auditor skills referenced in Cross-References.	4 / 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
skill_md_line_count	SKILL.md is long (684 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: paolomoz/skills
Path: skills/briefing-critique/SKILL.md
Commit: 5a6bbfe

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.