claude-for-legal

Full legal plugin suite for commercial contract review, privacy/DPA analysis, and AI governance vendor reviews. Use when the user invokes /commercial-legal:review, /privacy-legal:dpa-review, /ai-governance-legal:vendor-ai-review, renewal tracking, DSAR responses, or EU AI Act triage.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/pdf-and-documents/claude-for-legal/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tidy, efficient plugin index with concrete example prompts and sensible guardrails, with no bundle files to misstructure. Its main weakness is workflow clarity: the setup interview lacks validation checkpoints and the actual review workflows are demonstrated rather than sequenced.

Suggestions

Add a validation step to the practice-profile setup, e.g. 'Before the first review, confirm the profile covers all four areas and save it to the profile path' to close the workflow gap.

Give each of the three review commands a brief numbered sequence (intake → playbook check → redline draft → escalation route) instead of relying solely on example prompts to imply the process.

Move the per-skill example prompts for companion skills (renewal-tracker, dsar-response, use-case-triage) into a references file so the body stays a lean index with clearly signaled one-level pointers.

Dimension	Reasoning	Score
Conciseness	Lean, well-sectioned body with no explanation of concepts Claude already knows; only minor extraneous material such as the 'Verified citations via CourtListener, Trellis, and Westlaw' line keeps it below the top anchor.	4 / 5
Actionability	Concrete example prompts, executable install commands, and specific thresholds ('liability cap (must be 2x fees)', 'GDPR 30-day window') give mostly executable guidance, though companion skills are named without steps for invoking them.	4 / 5
Workflow Clarity	The cold-start interview is a numbered 4-step sequence ending in 'Save the profile', but there are no validation checkpoints (e.g., confirming the profile is complete before running a review) and each review workflow's steps are only implied by example prompts.	3 / 5
Progressive Disclosure	Well-organized per-practice sections with one-level pointers to the upstream repo and no nested references; slightly above the minimal self-contained case given the inlined per-skill descriptions that could live in separate files.	4 / 5
	Total	15 / 20 Passed

Description

78%Weight 40%Scale 1-5

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 strong description: explicit trigger guidance, concrete domain capabilities, and a well-delineated legal niche in third-person voice. It sits just below top marks on specificity and completeness because the 'full plugin suite' framing is broader than a fully enumerated, synonym-rich action list.

Suggestions

Add natural plain-language synonyms users might say, e.g. 'contract review', 'NDA review', or 'privacy policy analysis', alongside the slash-command triggers.

Replace the broad 'Full legal plugin suite' opener with one or two more concrete actions (e.g. 'Reviews vendor contracts and DPAs against your playbook...') to sharpen the 'what'.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('commercial contract review, privacy/DPA analysis, and AI governance vendor reviews') with only minor gaps, though the broad 'Full legal plugin suite' opener is less concrete than a fully enumerated action list.	4 / 5
Completeness	Explicitly answers 'when' with 'Use when the user invokes...' and conveys 'what' across three practice areas, but the 'what' relies on the broad suite framing rather than fully concrete trigger phrases, placing it just below the top anchor.	4 / 5
Trigger Term Quality	Good natural-term coverage ('renewal tracking, DSAR responses, or EU AI Act triage') plus explicit slash-command triggers, but common plain-language synonyms like 'contract review' or 'NDA review' are absent.	4 / 5
Distinctiveness Conflict Risk	Clear legal niche with distinct triggers (DPA, DSAR, EU AI Act, plugin slash commands) that are unlikely to fire for unrelated skills, matching the minimal-conflict-risk anchor.	5 / 5
	Total	17 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: eigent-ai/agent-skills
Path: skills/pdf-and-documents/claude-for-legal/SKILL.md
Commit: 9be8efc

Reviewed: 2 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.