CtrlK
BlogDocsLog inGet started
Tessl Logo

generate-verified-docs

Generates audit-grade, hallucination-free documentation from codebase features with full traceability. Use when documenting features, creating technical specs, or generating verified documentation with code references.

69

Quality

83%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered multi-stage workflow with excellent sequencing and validation gates, but actionability is capped by undefined thresholds and verification mechanics, and the monolithic single-file structure leaves room for progressive disclosure.

Suggestions

Define concrete values for the gating thresholds (e.g., minimum flow-coverage percentage, maximum unverifiable-claim count) and specify the mechanics for 'file_exists/line_exists/callable' checks so HALT conditions are unambiguous.

Split the per-stage output schemas and the failure-report JSON template into a reference file (e.g. OUTPUTS.md) referenced from each stage, reducing inline bulk and improving progressive disclosure.

Add at least one concrete tooling example (e.g., a Grep/Glob pattern for locating entry-point routes and exported functions) to make the discovery steps copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean and structured (Goal/steps/Gate/Output per stage) and assumes Claude's competence without explaining concepts Claude already knows; tokens are largely purposeful.

3 / 3

Actionability

Concrete structure and explicit output fields/classifications, but key details are missing — gates reference undefined thresholds ('coverage below threshold', 'too many unverifiable claims') and verification mechanics ('file_exists/line_exists/callable') without specifying how to perform them.

2 / 3

Workflow Clarity

Eight clearly sequenced stages each with explicit validation gates and a defined failure loop (STOP → PRESERVE → report → AWAIT), giving strong checkpoints and feedback recovery.

3 / 3

Progressive Disclosure

Well-organized into clear sections, but it is a ~230-line monolithic single file with no bundle files and substantial inline detail (output schemas, failure-report template) that could be split into references.

2 / 3

Total

10

/

12

Passed

Description

90%

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: third-person, explicit 'Use when' triggers, and a clearly distinct niche. The only soft spot is specificity, where the capability is a single action described with qualifiers rather than several distinct verbs.

DimensionReasoningScore

Specificity

Names the domain (codebase-feature documentation) and the core action (generating verified documentation with traceability), but the 'what' is essentially one capability with qualifiers rather than a list of multiple distinct concrete actions.

2 / 3

Completeness

It explicitly answers both what ('Generates audit-grade, hallucination-free documentation from codebase features with full traceability') and when (an explicit 'Use when...' trigger clause).

3 / 3

Trigger Term Quality

The 'Use when documenting features, creating technical specs, or generating verified documentation with code references' clause uses natural phrasings a user would actually say, giving good trigger coverage.

3 / 3

Distinctiveness Conflict Risk

The niche is distinct — verified, traceable documentation derived from codebase features with code references — making it unlikely to fire for generic writing or doc skills.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
quran/quran.com-frontend-next
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.