CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

legal-advisor

Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements.

Quality

61%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/legal-advisor/SKILL.md

The canonical home for this skill is legal-advisor in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

35%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 has a sensible section layout and enumerates relevant regulations and output expectations, but it is undermined by circular boilerplate sections, generic instruction bullets, no concrete drafting guidance, and a dangling reference to a nonexistent playbook file. It reads as an auto-generated template rather than an operational legal-drafting skill.

Suggestions

Delete the circular 'Use this skill when / Do not use this skill when' sections and replace the generic Instructions bullets with concrete guidance: a document skeleton (e.g., mandatory GDPR policy sections under Art. 13) and a per-regulation compliance checklist.

Fix or remove the dangling `resources/implementation-playbook.md` reference — either ship the playbook in the bundle or inline the key drafting patterns it should contain.

Add an explicit validation checkpoint in the Approach workflow, e.g. 'Before delivering, verify every mandatory clause for the identified jurisdictions is present and the disclaimer is included.'

DimensionReasoningScore

Conciseness

Multiple padded sections add no information: 'Use this skill when - Working on legal advisor tasks or workflows', 'Do not use this skill when - The task is unrelated to legal advisor', and generic instruction bullets like 'Clarify goals, constraints, and required inputs' and 'Apply relevant best practices and validate outcomes'. This matches 'Noticeably verbose; several unnecessary explanations or padded sections'. Not 3 because these are wholly contentless boilerplate (circular restatements of the skill name), not merely tightenable phrasing; not 1 because the Focus Areas, Key Regulations, and Output sections are reasonably lean lists.

2 / 5

Actionability

Beyond naming regulations and the verbatim disclaimer, the body gives only high-level direction — 'Identify applicable jurisdictions and regulations', 'Include all mandatory disclosures and clauses', 'Structure documents with logical sections and headers' — with no example clauses, document skeletons, per-regulation checklists, or templates. This matches 'Minimal concrete guidance; high-level hints but missing the specific steps to execute'. Not 3 because the promised 'Compliance checklist for each regulation' is never provided and the one pointer to executable detail, `resources/implementation-playbook.md`, references a file that does not exist in the bundle.

2 / 5

Workflow Clarity

The Approach section lists a real sequence ('Identify applicable jurisdictions... Structure documents... Flag areas requiring specific legal review') but checkpoints are implicit at best — no step verifies completeness of mandatory clauses or validates compliance before delivery, matching 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'. Not 4 because 'flag areas requiring legal review' is a vague gesture rather than a defined checkpoint; not 2 because the six steps are coherent and correctly ordered.

3 / 5

Progressive Disclosure

The body is sectioned (Focus Areas, Approach, Key Regulations, Output) and keeps a reasonable length, but its only external reference — 'If detailed examples are required, open `resources/implementation-playbook.md`' — points to a nonexistent file (no resources/ or other bundle directory exists). This matches 'Some structure but could be better organized; references present but not clearly signaled' in effect: navigation leads to a dead end. Not 4 because a broken reference fails the 'references mostly clear' criterion; not 2 because the inline content itself is appropriately short and well-sectioned rather than a monolithic wall.

3 / 5

Total

10

/

20

Passed

Description

71%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 strong on specificity and trigger terms, naming concrete legal artifacts in third-person voice with natural keywords. Its main weakness is the complete absence of an explicit 'Use when...' clause, capping completeness at 3 and weakening its ability to be triggered reliably.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a privacy policy, terms of service, cookie policy, or any GDPR/CCPA compliance document.'

Add missing natural synonyms such as 'terms and conditions', 'EULA', or 'compliance policy' to broaden trigger-term coverage.

Mention supporting regulations beyond GDPR (e.g., CCPA, COPPA) in the description to sharpen distinctiveness against general contract-drafting skills.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete artifacts — 'Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements' — covering the domain comprehensively, matching the anchor 'Lists multiple specific concrete actions; comprehensive coverage'. It fits this anchor better than 4 because the action verbs are concrete (draft/create) and the artifact coverage spans the domain's main outputs rather than having minor gaps.

5 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which per the judging guidelines caps completeness at 3. This matches the anchor 'Has a clear what but when is missing or only weakly implied' — the when can only be inferred from the artifact names themselves. Not 4 because the guidelines explicitly forbid it without an explicit when-clause.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'privacy policies', 'terms of service', 'GDPR', 'cookie policies', 'data processing agreements'. This matches 'Good keyword coverage; a few natural terms missing' — common variations like 'terms and conditions', 'EULA', 'ToS', or 'compliance policy' are absent. Not 5 because synonym coverage is incomplete; not 3 because the included keywords are exactly what a user requesting legal documents would naturally say.

4 / 5

Distinctiveness Conflict Risk

The legal-documentation niche ('privacy policies', 'GDPR-compliant texts', 'data processing agreements') is distinct from most skills, matching 'Mostly distinct; minor overlap risk with closely related skills' — it could overlap with a general compliance or contract-review skill. Not 5 because triggers like 'disclaimers' and 'legal notices' are somewhat broad and could collide with general document-drafting skills; not 3 because the regulatory terms (GDPR, DPA) anchor it firmly to a specific domain.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/legal-advisor/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.