oss-review

Open source license compliance check for a dependency list, a single library, or outbound code. Use when reviewing a manifest, SBOM, or repo for copyleft obligations and license compatibility, when asked whether a library can ship, or when preparing code to be open-sourced.

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 well-structured, highly actionable legal-review workflow with strong sequencing and validation, but it is verbose due to repeated restatements of the same steps (Instructions vs. Workflow vs. Precondition/Decision posture) and keeps reference material inline rather than splitting it into bundle files.

Suggestions

Collapse the duplication between the "Instructions" section and the "Workflow" section, and fold the standalone "Precondition" and "Decision posture" paragraphs into their corresponding workflow steps to remove repeated content.

Move the stable reference material — the license-bucket classification table, the severity-calibration table, and the memo output template — into a bundled reference file (e.g. references/LICENSE-BUCKETS.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Trim or relocate the repeated license-name enumerations (SSPL/BUSL/Commons Clause/Elastic License appear in Step 3, Step 4, and Step 5) to a single canonical list referenced where needed.

Dimension	Reasoning	Score
Conciseness	The material is substantive and does not lecture on concepts Claude already knows, but it restates the same content multiple times — the "Instructions" section (items 1–6) previews the later "Workflow" steps, "Precondition" re-states the load-profile instruction, and "Decision posture" repeats instruction 6 — so it could be tightened rather than earning the lean/every-token-earns-its-place bar at 3.	2 / 3
Actionability	Highly actionable for an instruction-only skill: concrete classification buckets with examples and obligations, a deployment-model-to-licenses table, a copy-paste-ready memo output template with checkboxes, specific license names (SSPL, BUSL, Elastic License) and named incompatibilities (GPL-2.0 + Apache-2.0); absence of code is not penalized per the scoring notes.	3 / 3
Workflow Clarity	A clearly sequenced 7-step workflow (scope → deployment model → classify → map obligations → flag failure modes → outbound check → assemble memo) with explicit validation checkpoints — a "Quality checks before delivering" checklist, precondition gating, and license-unknown-as-needs-review gating — so the batch-operation cap at 2 does not apply.	3 / 3
Progressive Disclosure	Good section structure and clearly signaled one-level-deep external references (the practice-profile CLAUDE.md, CONNECTORS.md), but no bundle reference files exist and the ~280-line body keeps all reference material inline (license-bucket table, severity calibration, full memo template) that could be split out, matching the "content that should be separate is inline" anchor at 2 rather than the appropriately-split bar at 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.

A strong description: it states the concrete capability across three input scopes, gives an explicit "Use when..." trigger list with natural terms, occupies a distinct niche, and uses correct third-person voice.

Dimension	Reasoning	Score
Specificity	Enumerates concrete scopes and actions — "compliance check for a dependency list, a single library, or outbound code" plus "copyleft obligations and license compatibility" — matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly states what it does ("Open source license compliance check...") and when to use it via an explicit "Use when..." clause naming multiple triggers, matching the score-3 what-and-when anchor exactly.	3 / 3
Trigger Term Quality	Covers natural terms a legal/engineering user would actually say — "manifest, SBOM, or repo", "copyleft obligations", "license compatibility", "whether a library can ship", "open-sourced" — with good variation coverage, not just a single keyword.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (OSS license compliance) with distinct triggers (SBOM, copyleft, open-sourcing) unlikely to fire for unrelated skills; written in third person with no first/second-person voice to penalize.	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: ip-legal/skills/oss-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.