brief-section-drafter

Draft a brief section in house style, consistent with the case theory — every fact cited, every case checked, every argument tied to the theory. Use when the user says "draft the [section]", "write the statement of facts", "argument section on [issue]", or needs a first draft of a brief section.

Quality

88%

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

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable brief-drafter body with strong workflow gating and validation. Its main weakness is conciseness — discursive prose and some self-repetition inflate the token budget — and the absence of in-skill reference files for material that could be deferred.

Suggestions

Tighten the discursive passages (e.g., 'Record fidelity', 'Echo vs repeat', 'Candor about weak arguments') by stripping rhetorical asides and keeping only the operational rule, since the rubric penalizes verbosity even when accurate.

Move the verbatim preface/markdown template and the multi-step citation-extraction procedure into a reference file (e.g., references/drafting-templates.md) referenced one level deep, improving both conciseness and progressive disclosure.

Remove content duplicated from the plugin CLAUDE.md (flagged as 'repeated here because...') or compress it to a one-line pointer plus the skill-specific application, to avoid maintaining the same rule in two places.

Dimension	Reasoning	Score
Conciseness	The ~185-line body is mostly specialized procedural discipline rather than concepts Claude already knows, but contains real rhetorical padding and self-repetition (e.g., 'The canonical statement lives in the plugin's CLAUDE.md... repeated here because...', 'A tribunal remembers the first two minutes and the last two') that could be tightened.	2 / 3
Actionability	Highly actionable: explicit marker taxonomy ([VERIFY], [UNCERTAIN], [CITE NEEDED]), exact file paths to load, ready-to-use refusal scripts, source-attribution tags, and a copy-paste preface template — all concrete and executable guidance.	3 / 3
Workflow Clarity	Clear 5-step sequence (Which section → Theory check → Draft → Cite → Output) with explicit validation gates: conflicts gate before drafting, theory-contradiction stop condition, cite-check coverage procedure, and a non-lawyer filing gate.	3 / 3
Progressive Disclosure	Well-organized into sections and signals the plugin CLAUDE.md as the canonical one-level-deep source, but there are no in-skill reference files and substantial inline material (the preface template, citation-extraction procedure) could be split into a reference file to lighten SKILL.md.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, specific description with explicit 'Use when' triggers, third-person voice, and multiple concrete capabilities. It clearly answers what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Draft a brief section in house style', 'every fact cited, every case checked, every argument tied to the theory' — using third person, matching the top anchor.	3 / 3
Completeness	Explicitly answers both what ('Draft a brief section in house style...') and when ('Use when the user says...') with concrete trigger clauses, hitting the top anchor.	3 / 3
Trigger Term Quality	Provides natural phrasings a user would say — 'draft the [section]', 'write the statement of facts', 'argument section on [issue]', 'first draft of a brief section' — with good coverage and variation.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear legal-brief-drafting niche with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: litigation-legal/skills/brief-section-drafter/SKILL.md
Commit: 4a6c651

Reviewed: 6 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.