CtrlK
BlogDocsLog inGet started
Tessl Logo

orch-refine-code

Orchestrate a behavior-preserving refactor — confirm tests are green, restructure without changing behavior, keep tests green, review, and gated commit. Use when the structure should improve but behavior must not change.

68

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 known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A tight, well-structured orchestration skill with strong workflow gates and validation checkpoints and no token waste. Its one weakness is actionability: execution is delegated to an external engine not bundled here, and the example is illustrative rather than executable.

Suggestions

Add a minimal concrete command or invocation showing how the `orch-pipeline` engine is actually run, so the skill stands on its own rather than relying on an unbundled sibling.

Make the Example block distinguish input from action more explicitly (e.g., label the trigger request vs. the orchestrated steps) so it reads as a reproducible recipe.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — it never explains what a refactor is or how tests work, and every section (settings, how it works, example) earns its place.

3 / 3

Actionability

It gives concrete operational settings (phase mask, gates, the `refactor:` commit prefix, named tools like knip/depcheck/ts-prune), but the actual executable mechanism is delegated to an unbundled `orch-pipeline` engine and the example is illustrative rather than copy-paste runnable.

2 / 3

Workflow Clarity

The sequence is explicit with validation checkpoints — confirm tests green before touching code, re-run after each step, and stop at Gate 1 and Gate 2 — giving a clear feedback loop for a risky operation.

3 / 3

Progressive Disclosure

Under 50 lines with no bundle files, it is well-organized into clear sections and points one level deep to the `orch-pipeline` engine and `refactor-cleaner` agent with clearly signaled references.

3 / 3

Total

11

/

12

Passed

Description

85%

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, concise description that states concrete actions and an explicit use-when trigger with a clear niche. The main gap is trigger-term breadth, which leans on technical phrasing over the natural variations a user might say.

Suggestions

Broaden trigger terms to natural user phrasing — e.g., add "clean up code", "remove dead code", "reduce duplication", or "improve code structure" so it surfaces for common requests.

Avoid relying on the somewhat jargon-y "behavior-preserving refactor" as the lead; pair it with plainer language a user would actually type.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "confirm tests are green", "restructure without changing behavior", "keep tests green", "review", and "gated commit" — rather than vague language.

3 / 3

Completeness

It answers both what (orchestrate a behavior-preserving refactor via the listed actions) and when ("Use when the structure should improve but behavior must not change") with an explicit trigger clause.

3 / 3

Trigger Term Quality

It includes some natural terms users would say ("refactor", "structure should improve") but misses common variations and relies on somewhat technical phrasing rather than broad keyword coverage.

2 / 3

Distinctiveness Conflict Risk

The "behavior-preserving" / "behavior must not change" framing carves a clear niche that is unlikely to trigger for sibling skills meant to change behavior.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.