vendor-agreement-review

Reference: review of an inbound vendor agreement against the team playbook in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. Flags deviations, assesses risk, generates specific redline language, and routes to the right approver. Loaded by /commercial-legal:review when a vendor MSA, services agreement, or similar is detected.

Quality

81%

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.

The workflow is highly actionable with clear sequenced steps and strong validation gates, making it reliable for a consequential legal task. It loses points for verbosity (repeated full paths and duplicated gate language) and for being monolithic with no reference-file split despite its length.

Suggestions

Introduce a shorthand for the repeated playbook path (e.g., define 'the playbook' once and reference it by name) to cut repeated token spend.

Move the reusable templates (liability-cap decision procedure, jurisdiction delta table, memo scaffold) into a bundled reference file and link to them one level deep to apply progressive disclosure.

De-duplicate the two non-lawyer gate blocks (redline-sending and DocuSign signing) into a single shared gating pattern referenced by both.

Dimension	Reasoning	Score
Conciseness	The body is lengthy (~330 lines) and repeats the full playbook path verbatim a dozen times plus near-identical non-lawyer gate language; much of the legal nuance earns its place, but the repeated paths and duplicated gating prose could be tightened with a shorthand alias.	2 / 3
Actionability	Provides copy-paste-ready finding/memo markdown templates, a severity calibration table, concrete redline-granularity examples ("twelve (12)" → "twenty-four (24)"), and a delivery checklist — fully actionable even without code.	3 / 3
Workflow Clarity	A clear Step 1–6 sequence with explicit validation gates ("stop and ask" before escalation math, deal-breaker-first, "Do not proceed past this gate without an explicit yes") and a closing quality checklist, giving real feedback loops for the outward-facing acts.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single monolithic ~330-line file with detailed templates (liability-cap procedure, jurisdiction delta, memo scaffold) inline; sections are well-organized but content that could live in separate reference files is not split out.	2 / 3
	Total	10 / 12 Passed

Description

85%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, complete, and well-scoped to a distinct commercial-legal niche with an explicit firing condition. Its main weakness is trigger phrasing centered on the command's load mechanism rather than natural user utterances, leaving common variations unsaid.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Flags deviations, assesses risk, generates specific redline language, and routes to the right approver" — each a distinct operation rather than vague abstractions.	3 / 3
Completeness	Clearly states what it does (flags deviations, assesses risk, generates redlines, routes approval) and when it fires ("when a vendor MSA, services agreement, or similar is detected"), answering both what and when with an explicit trigger.	3 / 3
Trigger Term Quality	Includes relevant terms ("vendor agreement", "vendor MSA, services agreement, or similar") but frames the trigger as a load mechanism ("Loaded by /commercial-legal:review when...") and omits common user phrasings like "review this contract" or "redline a vendor contract".	2 / 3
Distinctiveness Conflict Risk	The vendor-agreement niche against a team playbook, scoped to the /commercial-legal:review command, gives it a distinct trigger unlikely to collide with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/claude-for-legal
Path: commercial-legal/skills/vendor-agreement-review/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.