CtrlK
BlogDocsLog inGet started
Tessl Logo

clause

Reviewing legal documents for Terms of Service, Privacy Policy, and Tokushoho compliance. Detects clause gaps and flags risks. Not a substitute for legal advice — consult a lawyer.

60

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.archive/clause/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured and highly actionable with a clear phased workflow, concrete report template, and a strong reference map, but it is somewhat long: time-sensitive regulatory dates are inlined rather than isolated, and some sections duplicate the frontmatter comment. Tightening these would lift conciseness and progressive disclosure.

Suggestions

Move scattered time-sensitive dates and version numbers into a dedicated 'Current regulatory dates' section (or a reference file) so they can be updated without bloating the overview.

Relocate the long mobile-app-store disclosures and jurisdiction-specific rule detail into reference files, keeping SKILL.md as a tighter overview that points to them.

Add one fully worked inline example finding (e.g. a sample [H-01] block) so the report format is copy-paste ready without needing reference/examples.md.

DimensionReasoningScore

Conciseness

Mostly efficient domain content (statute tables, risk framework) rather than generic explanations Claude already knows, but a large volume of time-sensitive dates (2024-10-16, 2025-04-23, 2026-01-01, etc.) is scattered through the main body rather than isolated in a deprecated/old-patterns section, and the mobile-disclosures and jurisdiction rules duplicate the frontmatter comment, which could be tightened.

3 / 5

Actionability

Concrete, executable guidance for an instruction-only skill: a phased workflow table, a copy-paste report-output template, risk-level definitions, recipe subcommands, and a signal-keyword dispatch table; minor gaps remain (no fully worked example inline — that lives in reference/examples.md).

4 / 5

Workflow Clarity

A clearly sequenced SCOPE → SCAN → ASSESS → REPORT → SUGGEST workflow with an Ask-first gate for ambiguous jurisdiction and a statute-verification checkpoint ('Cite ... only after verifying they exist'); minor validation gaps keep it just below 5.

4 / 5

Progressive Disclosure

A clear Reference Map table signals one-level-deep references to reference/*.md and _common/*.md files, but substantial inline content (jurisdiction-specific rules, the long mobile-store disclosures section) that could live in separate reference files keeps it just below 5; no bundle files are present to verify the referenced paths exist.

4 / 5

Total

15

/

20

Passed

Description

70%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 is specific and distinctive, naming concrete legal-review actions and natural trigger terms, but it omits an explicit 'Use when...' clause, capping completeness at 3. Adding a trigger phrase would likely raise the overall score.

Suggestions

Add an explicit 'Use when ...' clause naming concrete trigger scenarios (e.g. reviewing ToS/Privacy Policy, pre-launch legal sweeps, multi-document consistency checks).

Include common synonyms such as 'ToS', 'terms of use', and 'legal review' to broaden trigger-term coverage.

Briefly mention the multi-document / consistency review capability to round out the action coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Reviewing legal documents for ... compliance', 'Detects clause gaps and flags risks' — across a named domain (ToS, Privacy Policy, Tokushoho), with minor coverage gaps (e.g. no mention of consistency/DPA review present in the body).

4 / 5

Completeness

Clearly states the 'what' (review legal documents, detect gaps, flag risks) but provides no explicit 'when/Use when' trigger guidance; the closing disclaimer stands in for trigger phrasing, so completeness caps at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural user-facing terms like 'Terms of Service', 'Privacy Policy', 'Tokushoho', 'clause gaps', and 'risks', but misses common synonyms such as 'ToS', 'terms of use', or 'T&C'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (legal-document clause review with statute-specific compliance) with distinct triggers and minimal overlap risk against general document or code skills.

5 / 5

Total

16

/

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
simota/agent-skills
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.