CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-quality

Load for any coding or development task in any repository: writing, changing, fixing, refactoring, or testing code or scripts in any language.

Quality

76%

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 ./skills/code-quality/SKILL.md
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.

An exceptionally lean standards document: every line is a directive with no filler, stack-specific detail is properly delegated to real one-level references, and validation requirements are woven in wherever risky operations appear. Its only weaknesses are the absence of worked examples for the more abstract rules and the lack of an explicit stepwise procedure with checkpoints.

DimensionReasoningScore

Conciseness

The body is wall-to-wall directives with zero concept explanations and zero padding ("A pathname alone grants no right to replace or delete a file"; "One lifetime, one owner"), fully assuming Claude's competence — every token earns its place.

5 / 5

Actionability

Concrete, specific guidance is present throughout (`mktemp -d` outside the worktree, `CARGO_TARGET_DIR` scoping, `text eol=lf` in `.gitattributes`, winerror 32 handling), and the must-fail control mechanics are stated precisely, but most rules are abstract directives with no worked example of a control, which is the minor gap keeping it below fully executable guidance.

4 / 5

Workflow Clarity

The reading/application flow is clearly sequenced ("Before changing code, load the reference for each affected stack under § Language Discipline"; "Load only the references for the code being changed"), and § Prove Your Guards embeds a control procedure with validation requirements (assert match counts, reject assertions matching skip notes, remove the mktemp root afterward); it is not a 5 because no explicit stepwise workflow with error-recovery checkpoints is laid out.

4 / 5

Progressive Disclosure

The Language Discipline section maps each stack (Rust/Cargo, Bash, TypeScript/JavaScript, views/UI) to a real, one-level-deep file in references/ with clear load conditions, keeps cross-cutting doctrine in the body, and correctly splits stack specifics into the four existing reference files.

5 / 5

Total

18

/

20

Passed

Description

58%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.

This is a strong, natural-sounding trigger description with concrete enumerated actions and explicit load conditions, but it is purely a "when" clause: it never states what the skill provides, and its maximal breadth (any coding task, any language, any repository) creates high overlap risk with every other code-related skill.

Suggestions

State the skill's function in the description itself (e.g., "Applies code-authoring standards — failure semantics, resource ownership, test contracts — when writing, changing, fixing, refactoring, or testing code") so the "what" is explicit alongside the "when", not only in the separate summary field.

Narrow the trigger claim to the skill's niche (authoring-time quality standards) or name the niche explicitly, reducing conflict with code-review, testing, and language-specific skills that currently also match "any coding task".

Add commonly used trigger phrases such as "debugging" or "reviewing your changes" to round out the natural-keyword coverage.

DimensionReasoningScore

Specificity

The description enumerates five concrete actions ("writing, changing, fixing, refactoring, or testing code or scripts in any language"), matching the several-specific-actions anchor; it is not a 5 because the skill's own capability (code-authoring standards) is never stated, leaving a coverage gap.

4 / 5

Completeness

The "when" is explicit and comprehensive ("Load for any coding or development task in any repository"), but the "what" — what the skill actually does — is absent from the description (it appears only in the separate summary field), so the description sits above the bare "when-only" anchor but below any anchor requiring both.

3 / 5

Trigger Term Quality

Natural trigger terms are well covered ("coding", "development task", "writing", "changing", "fixing", "refactoring", "testing", "code or scripts", "any repository", "any language"), but common user phrasings like "debugging", "code review", and "building" are missing.

4 / 5

Distinctiveness Conflict Risk

By claiming "any coding or development task in any repository ... in any language", the description is very broad within the coding domain and would trigger alongside many similar skills (code review, testing, security review, language-specific skills); it is not entirely generic, so it does not score 1.

2 / 5

Total

13

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/code-quality/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.