Skip to content
Development
Skill

/auto-test-execution

Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern

From plugin
aiwg
176200 skills199 agents23 commands
Install
$ npx -y skills add jmagly/aiwg --skill auto-test-execution --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/auto-test-execution

Context preview

The summary Claude sees to decide when to auto-load this skill.

Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern

SKILL.md

auto-test-execution.SKILL.md
namespace: aiwg
name: auto-test-execution
platforms: [all]
description: Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern

auto-test-execution

Automatically execute tests when code-generating agents write to source files, enforcing the execute-before-return pattern.

Triggers

Primary phrases matched automatically from skill description. No additional alternate expressions defined.

Purpose

This skill enforces the MetaGPT executable feedback pattern: code-generating agents must execute tests before returning results to the user. It activates automatically when agents modify source code files.

Behavior

When triggered, this skill:

1. **Detect modified files**:

  • Track which source files the agent has written to
  • Identify the relevant test framework

2. **Find related tests**:

  • Look for test files matching the modified source
  • Convention: `src/foo/bar.ts` -> `test/unit/foo/bar.test.ts`
  • If no tests exist, prompt agent to generate them

3. **Execute tests**:

  • Run the project's test command focused on relevant tests
  • Capture results: passed, failed, errors

4. **Handle results**:

  • All pass: Allow agent to return results
  • Failures: Trigger debug-and-retry loop (max 3 attempts)
  • Persistent failures: Escalate with debug memory context

5. **Update debug memory**:

  • Record session in `.aiwg/ralph/debug-memory/sessions/`
  • Extract patterns for future reference

Activation Conditions

activation:
  always_active_for:
    - software-implementer
    - debugger
    - test-engineer

  triggered_by:
    - file_write:
        patterns:
          - "src/**/*.ts"
          - "src/**/*.js"
          - "src/**/*.py"
          - "**/*.go"
          - "**/*.rs"

  skip_when:
    - test_files_only: true
    - documentation_only: true
    - configuration_only: true

Integration

This skill uses:

  • `project-awareness`: Detect test framework and configuration
  • Debug memory at `.aiwg/ralph/debug-memory/` for pattern learning

References

  • @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Feedback rules
  • @$AIWG_ROOT/agentic/code/addons/ralph/docs/executable-feedback-guide.md - Guide
  • @$AIWG_ROOT/agentic/code/addons/ralph/schemas/debug-memory.yaml - Memory schema
  • @.aiwg/research/findings/REF-013-metagpt.md - Research foundation
Read more
Ships withaiwg

Multi-agent AI framework for Claude Code, Copilot, Cursor, Warp, and 6 more platforms 200+ agents, 109+ CLI commands, 400+ deployable agent/skill/command/rule artifacts, 8 core frameworks, 32 addons, and a 40-plugin Claude Code marketplace.

Get the whole plugin