demand-intake

Pre-drafting context gathering for a demand letter — parties, facts, basis, leverage, BATNA, and privilege filters — written to a structured intake.md the demand-draft skill reads. Use when the user wants to prep a demand letter, run intake before drafting, or capture context for a payment demand, breach/cure notice, cease-and-desist, employment separation, or preservation demand.

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 highly actionable, well-sequenced intake workflow with a complete output template and explicit decision checkpoints. Its weaknesses are rhetorical padding that slightly inflates the token budget and the absence of any reference-file split for a body of this length.

Suggestions

Trim motivational/editorial prose (e.g., the Purpose paragraph's "worse than no letter" framing and scattered rhetorical asides) so every line carries procedural guidance.

Consider moving the full intake.md template or the strategic-block guidance into a one-level-deep reference file (e.g., references/intake-template.md) referenced from the body, to shorten the SKILL.md overview and add progressive disclosure.

Add a brief completeness check before writing (e.g., confirm all Posture fields are non-blank, since the skill already warns against falling back to defaults) to strengthen the confirm-before-save checkpoint into a hard validation gate.

Dimension	Reasoning	Score
Conciseness	Mostly substantive and domain-specific, but opens with motivational prose ("A demand letter sent without thinking about those is worse than no letter") and sprinkles rhetorical asides that could be trimmed without losing guidance.	2 / 3
Actionability	Provides a complete intake.md template with field-by-field placeholders, exact slug format, explicit file paths, and verbatim confirmation/handoff prompts — copy-paste ready guidance for an instruction skill.	3 / 3
Workflow Clarity	A clear 6-step sequence plus an ordered intake (Posture first, core 8, then strategic block) with explicit decision gates: a materiality heuristic, an explicit skip option, and a confirm-before-save checkpoint that flags thin spots.	3 / 3
Progressive Disclosure	Well-organized into clear sections with no nested references, but at ~265 lines it is entirely self-contained — the full template and strategic block are inline rather than offloaded to one-level-deep reference files.	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 dense, third-person description that names concrete deliverables and components, carries an explicit "Use when" trigger covering multiple demand types, and cleanly distinguishes itself from the sibling drafting skill. It hits the top anchor on all four dimensions.

Dimension	Reasoning	Score
Specificity	Enumerates concrete components gathered ("parties, facts, basis, leverage, BATNA, and privilege filters") and concrete actions ("written to a structured intake.md the demand-draft skill reads"), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what (pre-drafting context gathering written to a structured intake.md) and an explicit "Use when" trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	The "Use when" clause lists natural phrasings a user would say — "prep a demand letter," "payment demand," "cease-and-desist," "employment separation," "preservation demand" — with good coverage and common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (pre-draft intake) explicitly separated from "the demand-draft skill," with distinct per-demand-type triggers unlikely to collide with other 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/demand-intake/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.