claim-chart

Build or review an element chart — a patent claim chart (infringement, invalidity, or review) or a civil element chart for any cause of action or defense — with every cell pin-cited and gap detection as the priority output. Use when the user asks for a claim chart, element chart, proof chart, infringement or invalidity contention, element-by-element mapping, or asks "what are we missing to prove [claim]".

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 a strongly actionable, well-sequenced legal workflow with concrete templates, state enums, and validation checkpoints. Its main weaknesses are repetition of framing mantras with some teaching of known concepts, and a monolithic structure that keeps reference-grade tables inline despite having a clean external template file.

Suggestions

Collapse the repeated 'execute, don't gesture' and 'draft, not a contention' mantras into a single stated-once rule referenced where needed, to cut token cost without losing the guidance.

Move the jurisdiction-specific formulations table and the structural-term cognate families into a reference file (parallel to element-templates.md) so SKILL.md stays an overview with one-level-deep references.

Trim the educational prose around CSV formula injection and DOE function-way-result to the procedural rule (apostrophe-prefix the listed leading characters; produce a paired DOE row with the listed fields), trusting Claude's existing knowledge of the concepts.

Dimension	Reasoning	Score
Conciseness	Mostly efficient specialized guidance, but it repeats mantras ('Execute, don't gesture' appears across Steps 4, 4.5 and the dependent-claim section; 'a chart is a draft, not a contention' recurs multiple times) and teaches some concepts Claude already knows (the CSV formula-injection explainer, DOE function-way-result). It is not level 1 because the bulk is genuine domain specificity (case cites, jurisdiction divergences), and not level 3 because the repetition and teaching could be tightened.	2 / 3
Actionability	Highly actionable for an instruction-only skill: concrete markdown row templates with realistic data, fixed state enums ('mapped' / 'needs-evidence' / 'construction-dependent'), explicit file-naming conventions, and defined sheet schemas ('_elements', '_gaps', '_claim-parse', '_constructions') — copy-paste ready rather than the pseudocode or incomplete guidance at level 2.	3 / 3
Workflow Clarity	Clear sequenced workflow (top-level 1–11, then per-mode Steps 1–7 patent and 1–6 civil) with explicit validation checkpoints ('Show the parse to the user. Confirm before mapping. A wrong parse poisons every row below it.') and a closing 'Shared guardrails — checklist', matching the level-3 anchor with checkpoints and checklists rather than the checkpoint-missing level 2.	3 / 3
Progressive Disclosure	The one external reference is real and well-signaled one level deep ('consult references/element-templates.md in the skill directory'), but the body is a ~470-line monolith with large inline tables (jurisdiction-specific formulations, structural-term cognate families) that could be split into reference files — fitting the level-2 anchor where content that should be separate is inline, rather than the cleanly split level 3.	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, cleanly stating both what the skill produces and when to invoke it. It is highly distinctive within a legal-tooling suite and unlikely to conflict with sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build or review an element chart — a patent claim chart (infringement, invalidity, or review) or a civil element chart ... with every cell pin-cited and gap detection as the priority output' — matching the anchor for several specific concrete actions, not the level below which only names a domain and some actions.	3 / 3
Completeness	Explicitly answers both what (build/review patent or civil element charts, pin-cited cells, gap detection) and when via an explicit 'Use when the user asks for ...' clause, satisfying the level-3 anchor; it is not the level-2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Covers natural terms a legal user would say — 'claim chart, element chart, proof chart, infringement or invalidity contention, element-by-element mapping' plus the colloquial 'what are we missing to prove [claim]' — broad coverage rather than the partial set at level 2.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (patent/civil claim and element charting) with distinctive triggers unlikely to fire for unrelated skills; not the level-2 'somewhat specific but could overlap' case.	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/claim-chart/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.