CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-implementation

Implement, fix, refactor, or remove repository code under required scope, non-regression, verification, and review gates. Use whenever a task may change a production, test, script, or other implementation artifact, including build logic, generated source, and behavior-affecting configuration. Also use it alongside a specialized code-changing Skill. Do not use for read-only analysis or review, diagnosis-only work, or prose-only changes.

Quality

89%

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

85%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 well-engineered orchestration skill: a lean, gate-oriented body that routes to per-topic references with precise load conditions, and a clearly sequenced workflow with explicit validation checkpoints and feedback loops. The only room for improvement is tightening the dense, sometimes convoluted prose in workflow step 1.

DimensionReasoningScore

Conciseness

No padding or explanation of concepts Claude already knows; every line is repository-specific policy. However, step 1's constraint-provenance paragraphs ("distinguish original user requirements... trace every hard constraint to its original source"; "Approval to implement a proposal preserves the approved choice but does not establish...") are convoluted and partially repetitive, so minor tightening is possible.

4 / 5

Actionability

Concrete, directive guidance throughout: exact reference paths with precise load triggers, Maven routing facts ("for Maven source trees only src/main/** may be the subject of added or updated tests"), and specific inspection/rerun conditions. As an instruction-only skill the absence of code is not penalized, though a few directives remain abstract ("trace every hard constraint to its original source"), leaving minor gaps.

4 / 5

Workflow Clarity

The 8-step workflow is clearly sequenced with explicit validation checkpoints and feedback loops: inspect every changed path and hunk after each batch and immediately after formatters (step 5), the Coding Standards recheck with "Any later write returns the affected files and rules to this step" (step 6), and verification reuse/rerun rules keyed to task-state changes (step 7).

5 / 5

Progressive Disclosure

The body is a lean router that delegates detail to five one-level-deep reference files (implementation.md, testing.md, artifact-removal-and-contract-impact.md, non-regression.md, verification.md), all present in the bundle, each signaled with an exact load condition (e.g., read non-regression.md only "when a change affects a public or shared contract"). Navigation is unambiguous and content is appropriately split.

5 / 5

Total

18

/

20

Passed

Description

88%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: concrete action verbs, explicit use and do-not-use triggers, and explicit conflict management through composition semantics. The only weakness is that it lacks synonyms for common user phrasings like "update", "modify", or "add code".

Suggestions

Add natural trigger synonyms such as 'update', 'modify', 'add', or 'write' alongside 'implement, fix, refactor, or remove' to catch the most common user phrasings.

Consider naming concrete file types users mention (e.g., source files, config files) in the 'Use whenever' clause to sharpen trigger matching.

DimensionReasoningScore

Specificity

Lists four concrete actions ("Implement, fix, refactor, or remove repository code") and comprehensively enumerates affected artifact types ("production, test, script, or other implementation artifact, including build logic, generated source, and behavior-affecting configuration"). Coverage of actions and scope is broad rather than gap-ridden, matching the top anchor.

5 / 5

Completeness

Explicitly answers both what ("Implement, fix, refactor, or remove repository code under required scope, non-regression, verification, and review gates") and when ("Use whenever a task may change a production, test, script, or other implementation artifact"), plus concrete negative triggers ("Do not use for read-only analysis or review, diagnosis-only work, or prose-only changes").

5 / 5

Trigger Term Quality

Natural terms users would say are present ("implement", "fix", "refactor", "remove", "test", "build"), but common variations such as "update", "modify", "add", or "write code" are missing. Good keyword coverage with a few natural terms absent fits score 4, not 5.

4 / 5

Distinctiveness Conflict Risk

The trigger (any code change) inherently overlaps with specialized code skills, but conflict is explicitly managed through composition guidance ("Also use it alongside a specialized code-changing Skill") and clear exclusions for read-only and prose work. Minor residual overlap keeps it at 4 rather than 5.

4 / 5

Total

18

/

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

apache/shardingsphere

Path

.codex/skills/code-implementation/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.