CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

legal-risk-assessment

Structure legal-risk reviews by issue, rule source, likelihood, impact, evidence, uncertainty, controls, and escalation.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./resources/bundled-skills/legal-risk-assessment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

The body is an efficient, well-structured instruction-only skill with concrete field-level guidance, a clear sequenced workflow, and an explicit completion-gate checklist. Its only notable gaps are the lack of an output template or likelihood/impact scale and the absence of an explicit feedback loop between assessment steps. Progressive disclosure is appropriately handled within a single compact file.

DimensionReasoningScore

Conciseness

The 37-line body is lean and assumes Claude's competence: a tool-routing table, a five-step workflow, terse gates and boundaries, and no explanation of concepts Claude already knows. Every section earns its place; the only redundancy is the Purpose line restating the description verbatim, which is too trivial to drop it from anchor 5.

5 / 5

Actionability

As an instruction-only skill it gives concrete, specific guidance: exact fields to define ('jurisdiction, date, document scope, decision owner, and risk appetite'), lists of what to separate and what to output, and per-tool routing. Minor gaps remain — no output template and no suggested likelihood/impact scale — so it fits anchor 4 ('mostly concrete guidance with minor gaps') rather than the fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The five steps form a coherent define → analyze → assess → controls → recommend sequence, and 'Completion gates' provides an explicit end-of-work checklist. It is not a destructive or batch operation, so the validation cap does not apply; it stops short of anchor 5 because there is no explicit feedback loop (e.g., revisit likelihood when evidence is missing) and per-step checkpoints are implicit.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized into clearly labeled sections (Purpose, Tool routing, Workflow, Completion gates, Boundaries, Delivery). Per the simple-skill scoring note, well-organized sections with no bundle dependency earn a 5; no references are buried and no content that belongs in separate files is inlined.

5 / 5

Total

18

/

20

Passed

Description

53%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.

The description communicates a concrete and well-scoped capability through its enumerated review dimensions, and it is appropriately concise. Its main weaknesses are the absence of any 'when to use' trigger guidance and limited keyword variation, both of which reduce discoverability. It is distinctive within the legal-risk niche.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing legal exposure, regulatory issues, or contract risk, or when the user asks for a legal risk assessment.'

Include natural synonyms users would say, such as 'legal risk', 'regulatory risk', 'compliance review', or 'litigation exposure', to broaden trigger coverage.

Consider naming one or two concrete outputs (e.g., 'produce a risk matrix and escalation list') to strengthen the action vocabulary beyond the generic verb 'Structure'.

DimensionReasoningScore

Specificity

The description names the domain ('legal-risk reviews') and enumerates eight concrete review dimensions ('issue, rule source, likelihood, impact, evidence, uncertainty, controls, and escalation'), but the action verb remains a single generic one ('Structure...'). It goes beyond anchor 2's minimal generic action, but lacks the multiple distinct concrete actions of anchor 4.

3 / 5

Completeness

The 'what' is clearly stated (structure legal-risk reviews by the listed dimensions), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not anchor 2 because the 'what' is concrete rather than vague, and not anchor 4 because 'when' is entirely absent rather than weakly implied.

3 / 5

Trigger Term Quality

It includes relevant domain keywords such as 'legal-risk', 'likelihood', 'impact', 'evidence', and 'escalation', but misses common variations and synonyms users would naturally say, such as 'legal risk assessment', 'regulatory risk', 'compliance', or 'litigation'. This matches anchor 3: some relevant keywords but missing common variations.

3 / 5

Distinctiveness Conflict Risk

The phrase 'legal-risk reviews by issue, rule source, likelihood, impact... escalation' carves out a clear niche with domain-specific triggers, making it mostly distinguishable. There is minor overlap risk with general risk-analysis or compliance skills, so it fits anchor 4 rather than the fully distinct anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

KunAgent/Kun

Path

resources/bundled-skills/legal-risk-assessment/SKILL.md

Reviewed

Table of Contents

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.