CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

access-matrix

Access matrix of role-by-module permissions, with per-role scope, confidentiality level and SME tier, as CSV, SQL, JSON Schema or Notion on request. Use for access reviews.

63

Quality

79%

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 ./skills/antigravity-access-matrix/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 delivers a clear five-step workflow with genuinely executable templates in all four formats, well-signaled sibling routing, and useful pitfalls and safety notes. Its weakness is redundancy: repeated recommendation/workflow text, and example values duplicated across the CSV block, mapping table, and Field Reference, which inflate the token cost without adding guidance.

Suggestions

Remove the verbatim repeats: state the recommended approach and the workflow line once (Step 4) and reference them from Examples instead of restating them.

Drop the CSV column values from the Field Reference 'CSV example' column (or from the CSV example row) so the sample data lives in one place only.

Move the CSV/Excel and type-formatting notes that restate common knowledge ('A CSV is not an .xlsx workbook', 'A CSV carries no types') into a single short note, and trim the Notion mapping table to only columns that differ from the default Text mapping.

DimensionReasoningScore

Conciseness

Mostly efficient instruction, but tighten-able: the example row's values are duplicated between the CSV block and the Field Reference 'CSV example' column; the Notion mapping table repeats the Field Reference 'Notion' column; and both the 'Keep the matrix in the tool the team already reviews in' recommendation and the workflow line appear verbatim in Step 4 and again in Examples. It also explains CSV facts Claude already knows ('A CSV is not an .xlsx workbook', 'A CSV carries no types').

3 / 5

Actionability

Fully executable: a copy-paste-ready CSV template, complete PostgreSQL DDL, a complete JSON Schema, a per-column Notion property mapping with post-import steps, enumerated select options, an example intake dialogue, and a reusable prompt. Concrete guidance covers the common cases with no pseudocode.

5 / 5

Workflow Clarity

Steps 1-5 are clearly sequenced with explicit intent-dispatch rules, one-question-at-a-time intake, and supporting pitfalls/safety checkpoints. Not 5: output validation is delegated or 'reported separately' rather than expressed as an explicit validate-fix-retry loop over generated artifacts. Not 3: checkpoints are present and the sequence is coherent, and the destructive/batch cap does not apply since the skill emits empty templates by default.

4 / 5

Progressive Disclosure

Good single-file structure with clean, navigable sections and a clearly signaled one-level-deep sibling reference (@notion-manual-import) for the Notion step. The four artifact templates are inline, but there are no bundle files and keeping all formats derived from one field list is an explicit design choice ('so they cannot drift apart'). Not 5: at ~320 lines the field reference and artifact templates could be split into a references file to slim the always-loaded body.

4 / 5

Total

16

/

20

Passed

Description

75%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 concise, third-person, and specific about the artifact and its four output formats, with an explicit 'Use for access reviews' trigger clause. Its main gaps are a thin when-clause that omits setup/build intent and missing natural trigger variations that the body already lists.

DimensionReasoningScore

Specificity

Names the domain ('role-by-module permissions') and several concrete deliverables ('per-role scope, confidentiality level and SME tier, as CSV, SQL, JSON Schema or Notion') with clear on-request behavior, matching 'lists several specific actions; minor gaps in coverage'. Not 5: the behavior beyond artifact generation (recommend-first, review cycle) is only hinted by 'Use for access reviews'.

4 / 5

Completeness

Both 'what' (a role-by-module access matrix with defined attributes and four output formats) and 'when' ('Use for access reviews') are explicit and in third person. Not 5 because the when-clause is terse and covers only the review intent, omitting setup/build triggers that the skill also handles.

4 / 5

Trigger Term Quality

Good natural-term coverage: 'access matrix', 'role-by-module permissions', 'access reviews', plus all four format names. Not 5 because common variations users would actually say ('access control', 'who can see what', 'role permission matrix') appear only in the body, not the description.

4 / 5

Distinctiveness Conflict Risk

Clear niche — a role-by-module access matrix with named output formats — making false triggers unlikely outside closely related SME-ops siblings (e.g. people-directory). Matches 'mostly distinct; minor overlap risk with closely related skills', not 5 since adjacent database/Notion-template skills share surface vocabulary.

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

boisenoise/skills-collections

Path

skills/antigravity-access-matrix/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.