orch-refine-code

Actor · action · target: orch · refine · code. Thin wrapper over the shared engine in orch-pipeline.

When to Use

Same behavior, better structure: extract modules, remove duplication, kill dead code, reduce nesting, rename for clarity.
Distinguish from siblings: if behavior is meant to change at all, this is the wrong skill (orch-change-feature / orch-fix-defect).

Operation settings

Default size floor: standard — restructures touch multiple files.
Phase mask: 0 → 2 (plan the restructure) → 4 (keep green) → 5 → 6. No new behavior tests are written — the existing suite is the safety net.
First move (phase 4): confirm the relevant tests exist and are green before touching code; if coverage is thin, add characterization tests first. Then restructure in small steps, re-running tests after each.

How It Works

Run the orch-pipeline engine with the settings above.
For dead-code / duplication sweeps, delegate to the refactor-cleaner agent (it runs knip / depcheck / ts-prune and removes safely).
Stop at Gate 1 (restructure plan) and Gate 2 (pre-commit).
Commit as refactor: — the diff must be behavior-neutral.

Example

orch-refine-code: extract the NWS HTTP client out of poller.py
→ confirm tests green → plan extraction  [GATE 1: approve]
→ move in small steps, tests green throughout → code-review
→ commit refactor:  [GATE 2: confirm]

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

77/100

Grade

B

Good

Safety

82

Quality

72

Clarity

80

Completeness

68

Summary

This skill orchestrates behavior-preserving code refactoring by confirming tests pass, restructuring code without changing behavior, re-running tests, reviewing, and gating commits with a "refactor:" prefix. It delegates to a shared `orch-pipeline` engine and optionally invokes `refactor-cleaner` for dead code removal.

Detected Capabilities

test executioncode analysisfile restructuringgit commitdelegation to external agent (orch-pipeline, refactor-cleaner)

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

extract modulesremove dead codereduce duplicationrefactor structureimprove code clarityrename for readabilityconsolidate functions

Use Cases

Extract modules while keeping tests green
Remove dead code and duplication safely
Reduce code nesting and improve structure
Rename variables/functions for clarity without behavior changes
Refactor monolithic files into smaller, well-scoped components

Quality Notes

Skill is appropriately scoped to behavior-preserving refactoring and explicitly distinguishes itself from feature/defect work
Phase mask and gate structure (phases 0→2→4→5→6, gates at plan and pre-commit) provide clear checkpoints and human oversight
Emphasis on confirming tests are green before and after changes is a strong safety pattern for refactoring
Example provided is concrete and illustrative (NWS HTTP client extraction)
Relies on external skills (orch-pipeline, refactor-cleaner) and assumes their availability and correct behavior — dependencies are documented but not detailed
No explicit guidance on what constitutes 'thin coverage' or when to add characterization tests, though the intent is clear
Missing concrete guidance on 'small steps' — no explicit size thresholds or examples of incremental restructuring
No coverage of edge cases: what if tests are flaky? What if a refactor breaks subtle behavior assumptions?

Model: claude-haiku-4-5-20251001Analyzed: Jun 7, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

orch-refine-code

orch-refine-code

When to Use

Operation settings

How It Works

Example

Summary

Detected Capabilities

Trigger Keywords

Use Cases

Quality Notes

Reviews

Command Palette