CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

readme

Conventions for writing and updating READMEs and project documentation in this repo, based on the Ruff, Ty, and OpenCode README style. Load when creating or editing a README, docs page, or component-level documentation.

Quality

85%

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 tight, well-organized conventions skill that is lean, specific, and assumes Claude's intelligence, with a clear construction sequence and a built-in verify-before-writing rule. The main lever is converting the implicit validation rule into an explicit checkpoint within the workflow.

DimensionReasoningScore

Conciseness

Lean body with no concept-explanation padding; every rule earns its place and Claude's competence is assumed ('No "Welcome to...", no history', 'no superlatives'), matching the lean-and-efficient top anchor.

5 / 5

Actionability

Concrete, specific guidance for an instruction-only skill ('one section per component/layer, in data-flow order ... env file to copy, required vars, dev command', 'point to .env.example', 'bold component paths'); absence of copy-paste code is acceptable here, but it stops short of fully executable examples, so below 5.

4 / 5

Workflow Clarity

A clear numbered construction sequence (Title+tagline → diagram → per-component sections → commands → license) with an explicit verification rule ('Every claim must be verifiable in the repo: check ... before writing setup steps'), but validation is framed as a standing rule rather than an explicit checkpoint step inside the sequence.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external bundle files and two well-organized sections (Structure, Rules); per the simple-skill note this earns the top score on structure alone.

5 / 5

Total

18

/

20

Passed

Description

78%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, third-person description that pairs a clear 'what' with an explicit 'Load when...' trigger clause and natural keywords. It is slightly light on enumerated concrete actions and could add a couple more trigger synonyms to reach the top tier.

DimensionReasoningScore

Specificity

Names the domain ('READMEs and project documentation') and a couple of concrete actions ('writing and updating') but does not enumerate several distinct actions, so it matches the 'domain + 1-2 actions, not comprehensive' anchor rather than the several-action anchor at 4.

3 / 5

Completeness

Explicitly answers both what ('Conventions for writing and updating READMEs and project documentation in this repo') and when ('Load when creating or editing a README, docs page, or component-level documentation') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('README', 'docs page', 'creating or editing', 'component-level documentation'); good coverage but misses common synonyms like 'documentation' as a standalone trigger, so below the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Scoped to README/docs style for this specific repo with reference models named, making it mostly distinct; minor overlap risk remains with general documentation skills, so not a clean niche 5.

4 / 5

Total

16

/

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

divaltor/starlight

Path

.opencode/skills/readme/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.