CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-auth-access

Fix authentication, session, role, tenant-isolation, and object-access bugs on the server with a single ownership helper applied to every route, verified in both directions and on old and new records. Use for IDOR, data leaks across users, session, cookie, or role bugs.

72

Quality

91%

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

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.

A lean, high-density procedural skill: every step is a concrete rule and the exit criteria define a measurable pass condition. The minor gaps are an underspecified helper contract (no signature or exact 404 behavior shown), no explicit fix-and-revalidate loop when the ownership matrix fails, and a step-6 dependency on another skill's sweep without a fallback.

Suggestions

Add one line after step 5 defining the failure loop: when a matrix cell fails, fix the helper/query and re-run the full matrix — a pass on the fixed cell alone is not sufficient.

Show the `requireOwner`/`ownAudit` contract in one code line (function signature plus the exact 404 return) so the helper's behavior is unambiguous across all routes.

In step 6, name the concrete entry point of the `fix-security-hotfix` sweep and log review, or inline a minimal fallback in case that skill is not available.

DimensionReasoningScore

Conciseness

19 dense lines with zero padding: every step adds project-specific rules ("Scope every collection query by owner or tenant inside the query, not after") and nothing Claude already knows is re-explained. The brief "Each was a cheat our Done-Gate caught" earns its place as a known-failure-mode signal; not 4 because there is nothing to trim without losing guidance.

5 / 5

Actionability

Concrete throughout — named helpers ("requireOwner / ownAudit"), exact cookie flags ("HttpOnly; SameSite=Lax; Secure"), and a specific test matrix ("both directions (A→B, B→A), signed-out access, aged records, a real-browser user-agent") — but the helper's contract is only sketched ("missing or not owned → 404") and step 6 defers to the `fix-security-hotfix` skill's sweep without stating what to run. Not 5 because guidance isn't fully copy-paste ready; not 3 because the instructions are executable as written, not pseudocode.

4 / 5

Workflow Clarity

Six numbered steps in a clear order with explicit validation checkpoints (step 5 "Prove both directions..." plus the Exit criteria "ownership matrix (role × object × action) passes"), so the missing-validation cap does not apply. Not 5 because there is no stated recovery loop for what to do when a check fails — error recovery is only implied; not 3 because checkpoints are explicit, not implicit.

4 / 5

Progressive Disclosure

Under 50 lines, single task, no bundle files; well-organized Procedure and Exit criteria sections, and the two cross-skill pointers (`fix-security-hotfix`, `qa-auth-access`) are clearly signaled and one level deep. Matches the simple-skill anchor of well-organized sections with no need for external references.

5 / 5

Total

18

/

20

Passed

Description

92%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.

A strong description: concrete capabilities, an explicit 'Use for' trigger clause in third-person imperative voice, and a well-delineated niche. The only weakness is that the trigger list omits a few natural synonyms (authorization, access control, permissions) that users commonly say for this domain.

DimensionReasoningScore

Specificity

Enumerates multiple concrete bug classes ("authentication, session, role, tenant-isolation, and object-access bugs") plus a concrete method ("a single ownership helper applied to every route") and concrete verification details ("verified in both directions and on old and new records"). This matches the anchor for multiple specific concrete actions with comprehensive coverage; not 4 because coverage of the domain is thorough with no notable gaps.

5 / 5

Completeness

Clearly answers both: what ("Fix authentication, session, role, tenant-isolation, and object-access bugs on the server with a single ownership helper applied to every route") and when ("Use for IDOR, data leaks across users, session, cookie, or role bugs") with concrete trigger phrases. Matches the anchor example for an explicit what-and-when description.

5 / 5

Trigger Term Quality

The explicit "Use for IDOR, data leaks across users, session, cookie, or role bugs" clause gives good natural keyword coverage, and "IDOR" is exactly what a user would say for this class of bug. Not 5 because common natural synonyms like "authorization", "access control", or "permission" bugs are missing; not 3 because the terms present are relevant and users' phrasings, not just jargon.

4 / 5

Distinctiveness Conflict Risk

A clear niche (server-side auth/access bug fixing via an ownership helper) with distinct triggers like "IDOR", "tenant-isolation", and "object-access" that are unlikely to fire for unrelated skills. Not 4 because the trigger surface is narrow and specific rather than having meaningful overlap risk.

5 / 5

Total

19

/

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

itsablabla/qa-bug-agent-skills

Path

skills/fix-auth-access/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.