Skill
agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Development
Skill
/debug-memory
Query and manage the executable feedback debug memory
Install
$ npx -y skills add jmagly/aiwg --skill debug-memory --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
/debug-memory
Context preview
The summary Claude sees to decide when to auto-load this skill.
Query and manage the executable feedback debug memory
SKILL.md
debug-memory.SKILL.mdnamespace: aiwg
name: debug-memory
platforms: [all]
description: Query and manage the executable feedback debug memory
commandHint:
category: code-quality
Debug Memory Command
Query, analyze, and manage the debug memory from executable feedback loops.
Instructions
Manage the debug memory stored in `.aiwg/ralph/debug-memory/`:
Subcommand: query
Search debug memory for relevant past execution sessions.
1. Search `.aiwg/ralph/debug-memory/sessions/` for matching entries 2. Match by file path, error type, test name, or keyword 3. Display relevant sessions with fix attempts and outcomes 4. Highlight reusable patterns
Subcommand: patterns
Display learned patterns from past debug sessions.
1. Load `.aiwg/ralph/debug-memory/patterns/learned-patterns.yaml` 2. Show pattern frequency, success rate, and applicability 3. Suggest patterns applicable to current context
Subcommand: stats
Show aggregate statistics from debug memory.
1. Total sessions, pass rate, average attempts 2. Most common error types 3. Most effective fix patterns 4. Files with highest failure frequency
Subcommand: clear
Clear debug memory (with confirmation).
1. Prompt for confirmation 2. Archive current memory to `.aiwg/ralph/debug-memory/archive/` 3. Reset sessions and patterns
Arguments
- `query [keyword]` - Search debug memory
- `patterns` - Show learned patterns
- `stats` - Show aggregate statistics
- `clear` - Clear and archive debug memory
- `--file [path]` - Filter by source file
- `--error [type]` - Filter by error type
- `--since [date]` - Filter by date
References
- @$AIWG_ROOT/agentic/code/addons/ralph/schemas/debug-memory.yaml - Debug memory schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Executable feedback rules
- @$AIWG_ROOT/agentic/code/addons/ralph/docs/executable-feedback-guide.md - Guide
Read more
namespace: aiwg name: debug-memory platforms: [all] description: Query and manage the executable feedback debug memory commandHint: category: code-quality
Debug Memory Command
Query, analyze, and manage the debug memory from executable feedback loops.
Instructions
Manage the debug memory stored in `.aiwg/ralph/debug-memory/`:
Subcommand: query
Search debug memory for relevant past execution sessions.
1. Search `.aiwg/ralph/debug-memory/sessions/` for matching entries 2. Match by file path, error type, test name, or keyword 3. Display relevant sessions with fix attempts and outcomes 4. Highlight reusable patterns
Subcommand: patterns
Display learned patterns from past debug sessions.
1. Load `.aiwg/ralph/debug-memory/patterns/learned-patterns.yaml` 2. Show pattern frequency, success rate, and applicability 3. Suggest patterns applicable to current context
Subcommand: stats
Show aggregate statistics from debug memory.
1. Total sessions, pass rate, average attempts 2. Most common error types 3. Most effective fix patterns 4. Files with highest failure frequency
Subcommand: clear
Clear debug memory (with confirmation).
1. Prompt for confirmation 2. Archive current memory to `.aiwg/ralph/debug-memory/archive/` 3. Reset sessions and patterns
Arguments
- `query [keyword]` - Search debug memory
- `patterns` - Show learned patterns
- `stats` - Show aggregate statistics
- `clear` - Clear and archive debug memory
- `--file [path]` - Filter by source file
- `--error [type]` - Filter by error type
- `--since [date]` - Filter by date
References
- @$AIWG_ROOT/agentic/code/addons/ralph/schemas/debug-memory.yaml - Debug memory schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Executable feedback rules
- @$AIWG_ROOT/agentic/code/addons/ralph/docs/executable-feedback-guide.md - Guide
Ships withaiwg
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Get the whole plugin
Stats
211
Stars
32
Forks
Active
Maintenance
TypeScript
Language
MIT
License
1d ago
Last commit
1y ago
Created
Repo: jmagly/aiwg
Other skills on aiwg.
Skill
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Skill
auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Skill
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
Skill
execute-feedback
Execute tests on generated code and iterate until passing
Skill
infer-completion-crite…
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly