CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

documents

Verify PsychSift document access, storage, signed images, metadata, extraction, labels, downloads, and lifecycle behavior. Use for private documents, image loading, signed URLs, document routes, or storage defects.

Quality

88%

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.

An extremely token-efficient checklist with a sensible verification sequence, but it operates entirely at the 'what to check' level without a single executable command, path, or example of the local fixtures and tests it tells the reader to use. Adding minimal concrete artifacts would lift actionability substantially.

Suggestions

Add one concrete example of the 'local fixtures and focused route or component tests' step — e.g., a file path to a fixture directory and a one-line test command or snippet showing how a signed-URL expiry case is reproduced.

Make the step-4 security check executable by naming how to detect a leaked service-role secret or private object path (e.g., a grep command over client bundles or a specific env var to look for).

Turn the implicit checkpoints into explicit ones — state what 'verified' means for steps 4 and 6 (e.g., the exact conditions that must hold before reporting).

DimensionReasoningScore

Conciseness

The six numbered steps are lean with zero padding — every line directs a specific check or constraint, fully assuming Claude's competence with no concept explanations.

5 / 5

Actionability

Steps name concrete items to check (owner scope, storage key, signed URL expiry, service-role secret) but never say how — no commands, file paths, code, or fixture examples for reproducing with 'local fixtures and focused route or component tests'.

3 / 5

Workflow Clarity

A clear six-step sequence is present with checkpoints at steps 4 (verify no secret/private path reaches the client) and 6 (report access proof and assumptions), though validation is implicit rather than an explicit pass/fail gate.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed; the single heading plus a well-ordered numbered checklist is appropriately organized per the rubric's simple-skill guideline.

5 / 5

Total

17

/

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: it states concrete capabilities in third person and pairs them with an explicit, trigger-rich 'Use for' clause. Only minor synonym coverage is missing from the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete verification actions — 'access, storage, signed images, metadata, extraction, labels, downloads, and lifecycle behavior' — giving comprehensive coverage of the skill's domain rather than a few examples with gaps.

5 / 5

Completeness

It explicitly answers both what it does ('Verify PsychSift document access, storage, signed images, metadata, extraction, labels, downloads, and lifecycle behavior') and when to use it via a concrete 'Use for...' clause with specific trigger phrases.

5 / 5

Trigger Term Quality

'Use for private documents, image loading, signed URLs, document routes, or storage defects' covers good natural phrases a user would say, but misses common synonyms and variations (e.g., 'document permissions', 'file downloads', 'broken images').

4 / 5

Distinctiveness Conflict Risk

Scoping to 'PsychSift document' behavior with distinct triggers (signed URLs, storage defects, document routes) carves out a clear niche with minimal risk of triggering for unrelated skills.

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

BigSimmo/PsychSift

Path

.agents/skills/documents/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.