CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

access

Verify PsychSift authentication, authorization, ownership, tenancy, grants, RLS, administrative boundaries, and conservative denial behavior. Use for auth changes, private routes, owner scope, cross-tenant risk, or permissions.

Quality

86%

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

78%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 an exceptionally lean, well-sequenced checklist that assumes competence and gates risky operations behind approval. Its main weakness is actionability: several directives (run tests, inspect RLS) lack the specific commands or queries needed to execute them directly.

Suggestions

Make step 4 executable by naming the actual test command(s), e.g. "Run `npm test -- access` (or the repo's equivalent) covering access-model, owner-scope, and private-route suites".

Add one concrete inspection method for step 3, such as a sample SQL query for RLS policies/grants (e.g., `select * from pg_policies`) or the file/location where policies are defined.

Add a brief failure-handling branch after step 4 (e.g., "If an access test fails, fix the policy/guard and re-run before proceeding") to close the workflow's missing feedback loop.

DimensionReasoningScore

Conciseness

Six terse numbered directives with zero padding — every line adds domain-specific instruction (e.g., "security-definer functions, public API keys, and server/client trust boundaries") and assumes Claude's competence with no background explanation.

5 / 5

Actionability

The guidance names concrete artifacts and test paths (RLS, grants, stale-session, wrong-owner, cross-tenant) but contains no executable commands or examples — "Run focused local access-model, owner-scope, and private-route tests" names neither the test command nor how to run it, leaving key execution details missing.

3 / 5

Workflow Clarity

A clear map → test → inspect → verify → gate → report sequence is present, with an explicit validation step (step 4) and an approval gate for risky live checks (step 5); the gap is the absence of a failure-handling loop (what to do when a test or inspection finds an issue).

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and self-contained with no external references needed (no bundle files exist); the numbered list under a single heading is well-organized for such a compact skill.

5 / 5

Total

17

/

20

Passed

Description

87%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: it states a clear, niche-specific capability set and an explicit trigger clause with concrete natural-language terms. Its only weakness is that a single "Verify" verb carries the whole capability list and a few common synonym triggers (e.g., "login", "access control") are absent.

DimensionReasoningScore

Specificity

The description enumerates a comprehensive, specific set of objects — "authentication, authorization, ownership, tenancy, grants, RLS, administrative boundaries, and conservative denial behavior" — but a single verb ("Verify") governs them all rather than listing multiple distinct concrete actions, so it sits just below the top anchor.

4 / 5

Completeness

It explicitly answers both parts: a clear "what" ("Verify PsychSift authentication, authorization, ownership, tenancy, grants, RLS...") and an explicit "when" with concrete trigger phrases ("Use for auth changes, private routes, owner scope, cross-tenant risk, or permissions").

5 / 5

Trigger Term Quality

"Use for auth changes, private routes, owner scope, cross-tenant risk, or permissions" includes natural phrases users would say, but misses common synonyms and variations such as "login", "access control", "row-level security", or "session", so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (PsychSift access/auth verification) with distinct, domain-anchored triggers (RLS, tenancy, cross-tenant, owner scope), making conflict with other skills minimal.

5 / 5

Total

18

/

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

BigSimmo/PsychSift

Path

.agents/skills/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.