written-consent

Draft a unanimous written consent of the board or a committee in house format, with precedent search from the consents repository. Handles multi-resolution consents, director conflict flags, state-law notice requirements, and signatory tracking, with a built-in scope warning for major one-off actions. Use when user says "written consent", "unanimous consent", "board consent", "consent in lieu", "UWC", or describes an action needing board approval without a meeting.

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.

The body is highly actionable with a clear, gated workflow, but it is long and repetitive for its token budget and keeps content inline that would benefit from being split into referenced files.

Suggestions

Deduplicate the professional-regulator referral paragraph (currently repeated in the major-action gate, the consequential-action gate, and the no-precedent block) into a single referenced snippet or a shared note.

Extract the full consent template and the routine/review-flag classification tables into reference files (e.g., references/consent-template.md, references/action-classification.md) and link to them from SKILL.md to improve progressive disclosure.

Tighten the long quoted stop/gate blocks to their trigger conditions and the two forward paths, trimming explanatory prose that restates the same one-way-door rationale.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but it is padded by repetition — the professional-regulator referral boilerplate appears verbatim three times — and several long quoted stop/gate blocks could be tightened.	2 / 3
Actionability	Provides a complete, copy-paste-ready consent template, concrete action-classification lists, specific intake questions, and explicit output checklists — fully actionable guidance rather than abstract direction.	3 / 3
Workflow Clarity	A clear Step 1–5 sequence is paired with explicit validation gates (no-precedent hard stop, major-action-plus-urgency stop, consequential-action gate) that act as feedback loops before drafting and output.	3 / 3
Progressive Disclosure	The skill is a well-sectioned single file but runs ~310 lines with no bundle files, and substantial content (the full consent template, classification tables) that could be split into one-level-deep references remains inline.	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.

The description is specific, trigger-rich, and complete with a clear what-and-when structure, all in third-person voice. It is a strong model description with no obvious weaknesses.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — drafting unanimous written consents, precedent search, multi-resolution handling, director conflict flags, state-law notice requirements, and signatory tracking — rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what ("Draft a unanimous written consent…") and when ("Use when user says…"), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Covers the natural phrasings a user would say — "written consent", "unanimous consent", "board consent", "consent in lieu", "UWC" — plus a plain-language description of the triggering situation.	3 / 3
Distinctiveness Conflict Risk	Targets a clearly distinct legal niche (board written consents) with specific triggers, making overlap with other skills unlikely.	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: corporate-legal/skills/written-consent/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.