Skip to main content
Agent skill

Orch Fix Defect

Orchestrate fixing a bug — reproduce it as a failing regression test, fix to green, review, and gated commit — by delegating each phase to the matching ECC agent. Use when existing behavior is broken or wrong.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Orch Fix Defect when an AI agent needs a reusable SKILL.md workflow for this job: Orchestrate fixing a bug — reproduce it as a failing regression test, fix to green, review, and gated commit — by delegating each phase to the matching ECC agent. Use when existing behavior is broken or wrong.

When not to use it

Skip Orch Fix Defect when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/orch-fix-defect
# Save SKILL.md to ~/.claude/skills/orch-fix-defect/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/orch-fix-defect/SKILL.md. For a shared project, commit the folder at .claude/skills/orch-fix-defect/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Orch Fix Defect skill for this task: Something is broken: wrong output, an error, a crash, a regression. Confirm any required inputs or files before making changes.

What supports this recommendation?

74/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
82/100
Practical detail
74/100
Source evidence
63/100
Source signals
72/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# orch-fix-defect

Actor · action · target: **orch · fix · defect**. Thin wrapper over the shared engine in [`orch-pipeline`](../orch-pipeline/SKILL.md).

## When to Use

- Something is **broken**: wrong output, an error, a crash, a regression. - Distinguish from siblings: - behavior is correct but you want it different → `orch-change-feature`. - the capability does not exist yet → `orch-add-feature`.

## Operation settings

- **Default size floor:** small (often trivial). - **Phase mask:** 0 → (light 2 only if root cause is non-obvious or standard+) → 4 → 5 → 6. Research (1) is usually skipped. - **First move (phase 4):** reproduce the bug as a **new failing** test (regression test), then fix until it goes green. Proving the bug exists first is what separates a fix from a tweak.

## How It Works

1. Run the `orch-pipeline` engine with the settings above. 2. If the root cause is unclear, scope it with `code-explorer` before the red test; escalate build breaks to `build-error-resolver` / `/build-fix`. 3. Stop at **Gate 1** (only if a plan was produced) and **Gate 2** (pre-commit). 4. Add `security-reviewer` if the defect sits in a security-sensitive path.

## Example

``` orch-fix-defect: poller crashes on empty NWS response → write failing test reproducing the crash → fix to green → code-review → commit [GATE 2: confirm] (commit: fix:) ```

Intended uses

  • Something is broken: wrong output, an error, a crash, a regression.
  • Distinguish from siblings:
  • behavior is correct but you want it different → orch-change-feature.
  • the capability does not exist yet → orch-add-feature.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.