deep-risk-analysis

Clause-by-clause contract risk analysis with severity scoring, financial exposure estimates, and prioritized remediation guidance

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/legal-risks/SKILL.md

Quality

Content

65%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 delivers concrete, actionable guidance with a clear scoring rubric and a thorough output template, and avoids teaching Claude basics. It is held back by overlapping risk categories, the absence of an explicit verification checkpoint in the workflow, and a monolithic single-file structure with no progressive disclosure.

Suggestions

Consolidate the overlapping risk categories in the Step 2 table (e.g., merge 'Unlimited Liability' into 'Financial Exposure' and 'Broad Indemnification' into 'Liability Transfer') to reduce redundancy and token cost.

Add an explicit verification step before writing the file, such as 'Verify every clause has a score, that Top 5 priorities correspond to the highest-scored clauses, and that every HIGH RISK entry includes alternative language'.

Consider moving the large output template into a referenced file (e.g., references/RISK-ANALYSIS-TEMPLATE.md) so SKILL.md stays a lean overview with a one-level-deep reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the 11-row risk category table contains genuine overlap (e.g., 'Financial Exposure' vs 'Unlimited Liability', 'Liability Transfer' vs 'Broad Indemnification') and could be tightened, matching 'mostly efficient but could be tightened'.	2 / 3
Actionability	Guidance is highly concrete: a 1-10 scoring rubric with defined bands, an exact 7-element per-clause specification, and a full copy-paste output template. Per the scoring notes, absence of code in an instruction-only skill is not penalized when guidance is this actionable.	3 / 3
Workflow Clarity	The five steps are clearly numbered and sequenced, but the workflow contains no explicit validation or verification checkpoint (e.g., 'verify every clause was scored', 'confirm Top 5 matches the highest-scored clauses'), so it does not reach the 3 anchor that requires explicit validation steps; the task is non-destructive so it stays at 2 rather than 1.	2 / 3
Progressive Disclosure	The skill is a single well-organized file over 50 lines with no bundle files and no external references, and substantial reference-style content (the output template, the category table) lives inline rather than being split out, matching 'some structure but content that could be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

67%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 and distinctive, naming several concrete capabilities within a clear legal-risk niche. Its main weakness is the absence of any explicit 'when to use' trigger guidance and limited natural-language trigger terms.

Suggestions

Add an explicit trigger clause such as 'Use when reviewing, redlining, or signing a contract, or when the user asks about contract risks, liabilities, or unfavorable terms'.

Include natural trigger terms users would actually say (e.g., 'contract review', 'what's wrong with this contract', 'liability check') to improve trigger-term coverage.

Keep the third-person voice and concrete action list as-is — they are already strong.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'clause-by-clause contract risk analysis', 'severity scoring', 'financial exposure estimates', and 'prioritized remediation guidance' — matching the anchor for listing several specific concrete actions rather than naming only a domain.	3 / 3
Completeness	It clearly answers 'what does this do' but provides no 'Use when...' or equivalent explicit trigger guidance for when to invoke it, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It contains relevant keywords like 'contract risk analysis' but lacks natural trigger phrasings a user would actually say (e.g., 'review a contract', 'check contract risks') and offers no common variations, so it stops at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	'Clause-by-clause contract risk analysis' carves out a clear, specialized niche that is unlikely to overlap with or mis-trigger other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 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: zubair-trabzada/ai-legal-claude
Path: skills/legal-risks/SKILL.md
Commit: 19ece98

Reviewed: 12 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.