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.

73

Quality

92%

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

92%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 concise, well-structured orchestration skill with explicit gates and test-green feedback loops. Actionability is slightly below max because the actual engine mechanics are delegated to the wrapper rather than shown inline.

DimensionReasoningScore

Conciseness

Lean ~37-line body with no padding and no explanation of concepts Claude already knows; every section earns its place.

5 / 5

Actionability

Provides concrete phase masks, commit prefix, agent delegation, and gates, but execution relies on the wrapped orch-pipeline engine rather than copy-paste-ready code shown inline.

4 / 5

Workflow Clarity

Clear sequenced workflow with explicit validation checkpoints ('confirm tests green before touching code', 're-running tests after each') and Gate 1/Gate 2 feedback loops for the refactor.

5 / 5

Progressive Disclosure

Well-organized short skill with clearly signaled one-level-deep references (orch-pipeline/SKILL.md, refactor-cleaner agent) and no nested references.

5 / 5

Total

19

/

20

Passed

Description

92%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 that clearly states concrete refactor actions, an explicit use trigger, and disambiguates from sibling change/fix skills. Only minor gap is missing common synonyms like 'clean up code' or 'restructure'.

DimensionReasoningScore

Specificity

Names the refactor domain and lists multiple concrete actions — 'confirm tests are green, restructure without changing behavior, keep tests green, review, and gated commit' — giving comprehensive coverage rather than just several actions.

5 / 5

Completeness

Explicitly answers both 'what' (orchestrate a behavior-preserving refactor with listed steps) and 'when' ('Use when the structure should improve but behavior must not change').

5 / 5

Trigger Term Quality

Includes natural terms ('refactor', 'structure', 'behavior') and an explicit 'Use when' trigger, but misses common synonyms a user might say such as 'clean up code' or 'restructure'.

4 / 5

Distinctiveness Conflict Risk

Defines a clear niche — behavior-preserving refactor — with an explicit trigger and sibling disambiguation, giving minimal conflict risk with adjacent skills.

5 / 5

Total

19

/

20

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.