CtrlK
BlogDocsLog inGet started
Tessl Logo

matter-intake

Intake a new matter — uniform questions covering identification, conflicts, source, risk triage, materiality, outside counsel, owners, legal hold, and key dates; writes matter.md and history.md and appends a structured row to _log.yaml. Use when the user says "new matter", "intake this matter", or wants to bring a new matter into the portfolio.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 and the workflow is sequenced with an explicit validation gate and confirm step. Its main weakness is token efficiency from repeated full path strings and large inline templates that could be offloaded to reference files.

Suggestions

Define the long plugin path once as a short variable (e.g. base = ~/.claude/plugins/config/claude-for-legal/litigation-legal) and reuse it instead of repeating the full ~15 times.

Move the full matter.md and _log.yaml templates into a bundled reference file (e.g. references/templates.md) and link to it, keeping SKILL.md as an overview.

Consider extracting the conflicts-gate decision logic into a short reference so the inline intake stays leaner while preserving the STOP/Path 1-2-3 structure.

DimensionReasoningScore

Conciseness

Mostly efficient and free of generic-concept padding, but the ~15 verbatim repeats of the full '~/.claude/plugins/config/claude-for-legal/litigation-legal/' path and large inline templates could be tightened with a short alias, so it stops short of 'every token earns its place'.

2 / 3

Actionability

Provides complete, copy-paste-ready templates for matter.md, history.md, and a full _log.yaml row with real example values, plus specific field enums and gating rules — fully concrete guidance rather than vague direction.

3 / 3

Workflow Clarity

A clearly sequenced ten-step intake with an explicit conflicts gate ('not-run → STOP. This is a gate. ... Do not proceed silently'), three enumerated resolution paths, and a confirm-before-write checkpoint providing validation and feedback structure.

3 / 3

Progressive Disclosure

Sections are clearly labeled and the only references are one-level pointers to a single CLAUDE.md, but the full matter.md and _log.yaml templates live inline rather than in separate reference files, so content that could be split is not.

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 concrete, third-person, and answers both what and when with explicit, natural-language triggers. It is specific to a legal-intake niche with low conflict risk.

DimensionReasoningScore

Specificity

Names many concrete actions — the ten intake categories plus 'writes matter.md and history.md and appends a structured row to _log.yaml' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly states what the skill does (uniform intake across nine areas plus three written artifacts) and when to use it via an explicit 'Use when...' clause, answering both what and when.

3 / 3

Trigger Term Quality

Quotes natural user phrasings ('new matter', 'intake this matter') plus a plain-language trigger for bringing a matter into the portfolio, which are phrases a user would naturally say.

3 / 3

Distinctiveness Conflict Risk

A clear legal-matter-intake niche anchored to specific artifacts (matter.md, history.md, _log.yaml) with triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anthropics/claude-for-legal
Reviewed

Table of Contents

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.