policy-redraft

Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff. A first draft for internal review — not for direct application to approved policy documents. Use when the user says "redraft the policy", "draft the policy fix", "mark up the policy", or when gap-surfacer hands off a gap for drafting.

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 content is highly actionable with a clear, well-validated workflow and concrete templates, but it is verbose due to guardrail repetition and monolithic (no progressive disclosure via bundle files). Tightening redundancy and optionally offloading the memo template to a reference would raise the weaker dimensions.

Suggestions

Consolidate the PROPOSAL-not-edit / never-close-the-gap / smallest-possible-edit guardrails into a single authoritative section and reference it rather than restating in five places, to improve conciseness.

Consider extracting the Policy Redraft Memo template (Step 4) and/or the hard guardrails into a references/ file linked once from the body, giving the skill a one-level-deep progressive-disclosure structure.

Trim the restated redline-granularity bullets that appear in both the top workflow and Step 3, keeping them in only the most instructional location.

Dimension	Reasoning	Score
Conciseness	The ~200-line body restates the "PROPOSAL not edit" / "never close the gap" / "smallest-possible edit" guardrails across the top summary, Hard guardrails, Step 3, Filename, Interactions, and "What this skill does not do" — mostly efficient but padded with redundancy.	2 / 3
Actionability	Provides a copy-pasteable memo template, exact filename pattern, exact banner text to emit, an example change-summary table, and verbatim decline phrasings — fully concrete and executable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	Clear 4-step sequence (Gather → Verify rule → Produce redraft → Output memo) with explicit validation checkpoints (rule-status red flags, ⚠️ banner), feedback loops ("If you cannot verify..."), and a "Before applying" checklist for a high-stakes operation.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a monolithic inline document with no external references; the memo template and guardrails could be split into reference files, and several sections that should be one level deep are 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 third-person, specific, and explicitly answers both what the skill does and when to use it, with natural quoted trigger phrases and a clearly scoped niche. It is an exemplar of the rubric's good examples.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Produce a proposed marked-up policy redraft that closes a gap" with its source commands — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Clearly states what it does and provides an explicit "Use when the user says..." clause with triggers, satisfying both what and when.	3 / 3
Trigger Term Quality	Quotes natural phrases a user would actually say ("redraft the policy", "draft the policy fix", "mark up the policy") plus a handoff condition, giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Clear niche (gap → redraft as a proposal, not an edit) distinct from upstream gaps/policy-diff, with scoped triggers unlikely to fire for the wrong skill.	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: regulatory-legal/skills/policy-redraft/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.