CtrlK
BlogDocsLog inGet started
Tessl Logo

django-access-review

django-access-review

42

Quality

43%

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/skills/django-access-review/SKILL.md

The canonical home for this skill is django-access-review in administrakt0r/AI-Agents-Safe-Coding-Skills

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 a well-structured, actionable investigation methodology with concrete grep commands, a worked IDOR example, confidence-gated reporting, and a closing checklist. Its main weaknesses are some over-explanation of basic Django patterns and a monolithic single-file structure that begins with a malformed duplicate frontmatter header.

DimensionReasoningScore

Conciseness

Mostly efficient procedural guidance, but the 'Common Django Authorization Patterns' section re-explains basics Claude already knows (permission_classes, has_object_permission) and the core question is repeated across multiple sections; could be tightened.

3 / 5

Actionability

Copy-paste grep commands, a fully worked DocumentViewSet IDOR trace, and concrete good/bad fix code make it highly actionable; a few 'what to look for' lists are descriptive rather than executable, keeping it just below a 5.

4 / 5

Workflow Clarity

Five sequenced phases with a 'Do not proceed until you understand the authorization model' gate, confidence-level reporting validation (HIGH/MEDIUM/LOW), and a final checklist; no explicit error-recovery feedback loop, though that is less critical for read-only review.

4 / 5

Progressive Disclosure

Well-organized into clear phased sections with no nested references, but the ~330-line body is monolithic with no external file split despite sizable patterns and report-template sections that could be progressively disclosed.

4 / 5

Total

15

/

20

Passed

Description

18%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 frontmatter description field is just the skill name 'django-access-review', providing no capability detail or usage triggers; a richer description exists only in a malformed second frontmatter block inside the body, not in the actual frontmatter. It fails to tell Claude what the skill does or when to invoke it.

Suggestions

Replace the frontmatter description with the full sentence already present in the body (e.g. 'Django access control and IDOR security review. Use when reviewing Django views, DRF viewsets, ORM queries, or any Python/Django code handling user authorization.').

Add explicit 'Use when...' trigger guidance with natural phrases a user would say: 'IDOR', 'access control', 'authorization', 'Django permissions', 'object permissions', 'tenant isolation'.

Name 2-3 concrete actions (e.g. 'trace authorization flows, identify IDOR gaps, suggest enforcing fixes') instead of only the domain slug.

DimensionReasoningScore

Specificity

The frontmatter description is merely the slug 'django-access-review' — no concrete actions are stated, only a domain name, matching the 'entirely vague; no concrete actions' anchor.

1 / 5

Completeness

It states neither what the skill does nor when to use it; the description field is just the skill name repeated, so both 'what' and 'when' are missing.

1 / 5

Trigger Term Quality

The slug surfaces 'Django' and 'access' as domain words, but these are not natural trigger phrases a user would say and lack synonyms or 'use when' guidance; it is just below the midpoint for keyword coverage.

2 / 5

Distinctiveness Conflict Risk

'django-access-review' names a specific niche (Django access control) with low overlap risk against other skills, though it lacks explicit trigger phrases that would make it unmistakable (not a 5).

4 / 5

Total

8

/

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.

Validation15 / 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
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.