demand-draft

Draft a demand letter from a completed intake, gated on a privilege / FRE 408 / waiver / admission checklist, with a .docx output, post-send checklist, and an offer to create a matter. Use when the user says "draft the demand", "write the [type] letter", or has a finished demand intake ready to turn into a sendable draft.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 genuinely expert legal-drafting skill with excellent actionability and a rigorous, validated workflow. Its main weaknesses are conciseness (repetition and long blockquotes) and progressive disclosure (a monolithic body with no reference files split out).

Suggestions

Move the five demand-type skeleton templates (payment, breach/cure, cease & desist, employment separation, preservation) into a single references/TEMPLATES.md linked once from the Template selection section to reduce inline bulk.

Extract the full post-send checklist markdown block into a references/CHECKLIST.md and reference it by path, keeping only the field semantics inline.

De-duplicate the record-fidelity / verbatim-quote guidance that is self-described as 'repeated here' from the plugin CLAUDE.md, keeping a single concise restatement plus the pinpoint-cite addition.

Dimension	Reasoning	Score
Conciseness	The ~345-line body is mostly necessary domain-specific doctrine (FRE 408, UCC § 2-612 installment contracts, privilege-waiver doctrine) Claude does not already know, so it avoids the score-1 'explains concepts Claude knows' anchor — but it is padded with self-acknowledged repetition ('repeated here' from CLAUDE.md) and long blockquotes that could be tightened.	2 / 3
Actionability	Gives concrete executable guidance — exact file paths, precise placeholder formats ([CITE:___], [VERIFY:___], [SME VERIFY]), per-tone consequence phrases, and numbered template skeletons — so an instruction-only skill earns 3 rather than the score-2 'pseudocode / missing key details'.	3 / 3
Workflow Clarity	A clearly sequenced 1–9 flow with a pre-draft gate checklist, explicit per-item validation ('Do not proceed until each is engaged'), a citation-verification feedback loop, and a post-send checklist — matching the score-3 'clear sequence with explicit validation steps and feedback loops'.	3 / 3
Progressive Disclosure	No bundle files exist and the body is a monolithic 345-line wall of text with five demand-type skeletons and a full checklist template inline that could be split into one-level-deep reference files; sections are well-headed, but content that should be separate is inline, matching the score-2 rather than the score-3 'well-signaled one-level-deep references'.	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 strong: third-person voice, concrete capabilities, explicit 'Use when' triggers, and a distinct niche that minimizes conflict risk. It reads as a high-quality model skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Draft a demand letter', 'gated on a privilege / FRE 408 / waiver / admission checklist', '.docx output', 'post-send checklist', and 'offer to create a matter' — matching the score-3 anchor of several specific concrete actions rather than the score-2 'names domain and some actions'.	3 / 3
Completeness	Explicitly states what it does (draft from intake, gated checklist, .docx output, post-send checklist, matter offer) and when to use it via an explicit 'Use when...' clause, satisfying both halves; not score-2 where 'when' is only implied.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say — 'draft the demand', 'write the [type] letter', 'finished demand intake ready to turn into a sendable draft' — giving good coverage; not the score-2 anchor of only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	A clear demand-letter niche with distinct triggers ('draft the demand', 'write the [type] letter') unlikely to fire for unrelated skills; not the score-2 anchor where overlap with similar skills remains.	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/demand-draft/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.