feature-risk-assessment

Deeper risk assessment for a single feature or product area when the launch review found something that needs more than a line item. Structured analysis: what could go wrong, how likely, how bad, what mitigates it. Use when user says "deep dive on this risk", "risk assessment for [feature]", "what could go wrong with", or when launch-review flags a novel issue.

Quality

96%

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

92%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 dense, actionable instruction-only skill with a well-sequenced workflow and explicit verification checkpoints, plus genuinely non-obvious domain guidance on citation fabrication and source attribution. The only soft spot is progressive disclosure: everything lives inline in one ~150-line file with no reference files to offload detail.

Suggestions

Consider extracting the per-risk template and the citation-check/source-attribution procedures into a references/ file (e.g. RISK_TEMPLATE.md and CITATION_GUIDANCE.md), keeping SKILL.md a leaner overview that links one level deep.

If keeping the skill single-file is intentional, note that explicitly (e.g. a one-line 'Self-contained — no separate references needed') so the lack of bundle files reads as a deliberate design choice rather than an omission.

The Matter context boilerplate paragraph is generic plumbing shared across skills; if it is duplicated in a practice-level CLAUDE.md, trimming it here would improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it adds non-obvious expert guidance (company-specific calibration, citation-fabrication risk, source attribution) with no padding explaining concepts Claude already knows; the punchy directives are scope-setting, not filler.	3 / 3
Actionability	It provides copy-ready concrete artifacts: a full per-risk template, an options table format, a recommendation template, exact handoff commands, and explicit citation attribution tags, all directly executable for an instruction-only skill.	3 / 3
Workflow Clarity	A clear numbered sequence (assess → risks → regulatory → precedent → options → recommendation) is paired with explicit pre-finalize checkpoints ('Calibration check', 'Citation check') and a no-silent-supplement error-recovery loop, matching the validation-with-feedback anchor.	3 / 3
Progressive Disclosure	The single file is well-organized into clear sections (avoiding a monolithic wall of text), but there is no file-based progressive disclosure and the skill exceeds the 50-line simple-skill carve-out, with substantial inline procedural content and no references to offload detail into.	2 / 3
	Total	11 / 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, third-person description that clearly states the skill's concrete capabilities and provides explicit natural-language triggers for when to use it. It is well-differentiated from the broad launch-review skill it complements.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('what could go wrong, how likely, how bad, what mitigates it') for a structured risk analysis, matching the 'multiple specific concrete actions' anchor rather than the partial domain+actions anchor at 2.	3 / 3
Completeness	It explicitly answers both what ('Deeper risk assessment... Structured analysis: what could go wrong...') and when ('Use when user says... or when launch-review flags a novel issue') with explicit triggers, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	It supplies natural phrases a user would actually say ('deep dive on this risk', 'risk assessment for [feature]', 'what could go wrong with'), giving good coverage rather than just some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (deeper assessment escalated beyond launch-review) with distinct trigger phrases, making it unlikely to fire for the wrong skill; not merely 'somewhat specific'.	3 / 3
	Total	12 / 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: product-legal/skills/feature-risk-assessment/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.