/execute-feedback
Execute tests on generated code and iterate until passing
$ npx -y skills add jmagly/aiwg --skill execute-feedback --agent claude-codeHow 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
/execute-feedback
Context preview
The summary Claude sees to decide when to auto-load this skill.
Execute tests on generated code and iterate until passing
SKILL.md
execute-feedback.SKILL.mdnamespace: aiwg
name: execute-feedback
platforms: [all]
description: Execute tests on generated code and iterate until passing
commandHint:
category: code-quality
Execute Feedback Command
Run executable feedback loop on generated code: execute tests, analyze failures, fix, and retry.
Instructions
When invoked, perform the executable feedback loop per REF-013 MetaGPT:
1. **Identify Target**
- Load the specified file or recently modified code files
- Determine test framework (jest, pytest, cargo test, go test, etc.)
- Find existing tests or generate test stubs if none exist
2. **Execute Tests**
- Run the specified test command (or auto-detect)
- Capture full output (stdout, stderr, exit code)
- Parse test results: passed, failed, errors, skipped
3. **Analyze Failures**
- For each failing test:
- Extract error type and message
- Identify root cause (null check, type error, logic error, etc.)
- Map to source code location
- Check debug memory for similar past failures
4. **Apply Fixes**
- Generate targeted fix based on root cause analysis
- Apply fix to source code
- Increment attempt counter
5. **Re-Execute**
- Run tests again after fix
- Compare results to previous attempt
- If all pass: record success in debug memory, return
- If still failing: repeat from step 3
6. **Escalate if Needed**
- After max attempts (default: 3), escalate to human
- Include: all test results, failure analyses, fix attempts
- Save debug memory session
7. **Update Debug Memory**
- Record execution session in `.aiwg/ralph/debug-memory/sessions/`
- Extract learned patterns to `.aiwg/ralph/debug-memory/patterns/`
- Update success metrics
Arguments
- `[file-path]` - Source file to test (default: recently modified files)
- `--test-command [cmd]` - Test command to run (default: auto-detect)
- `--max-attempts [n]` - Maximum fix attempts (default: 3)
- `--coverage [%]` - Minimum coverage target (default: 80)
- `--no-fix` - Run tests only, report without fixing
- `--verbose` - Show full test output
References
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Executable feedback rules
- @$AIWG_ROOT/agentic/code/addons/ralph/docs/executable-feedback-guide.md - Implementation guide
- @$AIWG_ROOT/agentic/code/addons/ralph/schemas/debug-memory.yaml - Debug memory schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/flows/executable-feedback.yaml - Workflow schema
- @.aiwg/research/findings/REF-013-metagpt.md - Research foundation
Read more
namespace: aiwg name: execute-feedback platforms: [all] description: Execute tests on generated code and iterate until passing commandHint: category: code-quality
Execute Feedback Command
Run executable feedback loop on generated code: execute tests, analyze failures, fix, and retry.
Instructions
When invoked, perform the executable feedback loop per REF-013 MetaGPT:
1. **Identify Target**
- Load the specified file or recently modified code files
- Determine test framework (jest, pytest, cargo test, go test, etc.)
- Find existing tests or generate test stubs if none exist
2. **Execute Tests**
- Run the specified test command (or auto-detect)
- Capture full output (stdout, stderr, exit code)
- Parse test results: passed, failed, errors, skipped
3. **Analyze Failures**
- For each failing test:
- Extract error type and message
- Identify root cause (null check, type error, logic error, etc.)
- Map to source code location
- Check debug memory for similar past failures
4. **Apply Fixes**
- Generate targeted fix based on root cause analysis
- Apply fix to source code
- Increment attempt counter
5. **Re-Execute**
- Run tests again after fix
- Compare results to previous attempt
- If all pass: record success in debug memory, return
- If still failing: repeat from step 3
6. **Escalate if Needed**
- After max attempts (default: 3), escalate to human
- Include: all test results, failure analyses, fix attempts
- Save debug memory session
7. **Update Debug Memory**
- Record execution session in `.aiwg/ralph/debug-memory/sessions/`
- Extract learned patterns to `.aiwg/ralph/debug-memory/patterns/`
- Update success metrics
Arguments
- `[file-path]` - Source file to test (default: recently modified files)
- `--test-command [cmd]` - Test command to run (default: auto-detect)
- `--max-attempts [n]` - Maximum fix attempts (default: 3)
- `--coverage [%]` - Minimum coverage target (default: 80)
- `--no-fix` - Run tests only, report without fixing
- `--verbose` - Show full test output
References
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Executable feedback rules
- @$AIWG_ROOT/agentic/code/addons/ralph/docs/executable-feedback-guide.md - Implementation guide
- @$AIWG_ROOT/agentic/code/addons/ralph/schemas/debug-memory.yaml - Debug memory schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/flows/executable-feedback.yaml - Workflow schema
- @.aiwg/research/findings/REF-013-metagpt.md - Research foundation
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.
Repo: jmagly/aiwg
Other skills on aiwg.
- /agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Open skill - /agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Open skill - /auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Open skill - /cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
Open skill - /debug-memory
Query and manage the executable feedback debug memory
Open skill - /infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly
Open skill