CtrlK
BlogDocsLog inGet started
Tessl Logo

akf-trust-metadata

The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.

66

Quality

80%

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/akf-trust-metadata/SKILL.md

The canonical home for this skill is akf-trust-metadata in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 lean and highly actionable with copy-paste commands and a sensible before/after/audit workflow; the only gap is a missing explicit post-stamp verification checkpoint.

DimensionReasoningScore

Conciseness

Lean, command-driven body that assumes Claude's competence — the one-line EXIF/ID3 analogy and short evidence list earn their place, and there is no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases — stamp/read/inspect/audit with concrete flags, evidence examples, classification labels, and install instructions.

5 / 5

Workflow Clarity

Clear before/after/audit sequence with pre-modification checkpoints ('akf read', 'akf inspect' before modifying), but no explicit post-stamp verification or feedback loop, leaving a minor validation gap versus the 5 anchor.

4 / 5

Progressive Disclosure

Under 50 lines with no bundle files needed and well-organized sections (When to Use, After creating, Before modifying, Compliance, Classification, Install, Links), so per the simple-skill guidance it scores 5 on structure alone.

5 / 5

Total

19

/

20

Passed

Description

66%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 punchy and names concrete actions in a distinct niche, but it omits any explicit 'when to use' trigger clause, which caps completeness and slightly weakens trigger-term naturalness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. provenance, compliance audit, AI-generated content handoff) to lift completeness above 3.

Include the native file extension (.akf) or 'AKF file' phrasing so users have a natural term to invoke the skill.

Soften the marketing framing ('EXIF for AI') slightly in favor of a concrete action verb first, keeping distinctiveness without the buzzword lean.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions — 'stamps every file with trust scores, source provenance, and compliance metadata', 'Embeds into 20+ formats (DOCX, PDF, images, code)', 'EU AI Act, SOX, HIPAA auditing' — with only minor coverage gaps, fitting the 4 anchor better than 3's '1-2 concrete actions'.

4 / 5

Completeness

The 'what' is clear (stamp/inspect/audit trust metadata) but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3.

3 / 5

Trigger Term Quality

Good keyword coverage across 'trust scores', 'provenance', 'compliance metadata', format names (DOCX, PDF) and regulations (EU AI Act, SOX, HIPAA), though a few natural terms like the '.akf' extension or 'AKF file' phrasing are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (AI-native trust/provenance metadata tied to specific regulations) with mostly distinct triggers, though broad 'stamps every file with metadata' language leaves minor overlap risk with general metadata or compliance skills.

4 / 5

Total

15

/

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.