agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Scaffold a new SKILL.md inside an existing addon or framework
$ npx -y skills add jmagly/aiwg --skill add-skill --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/add-skillContext preview
The summary Claude sees to decide when to auto-load this skill.
Scaffold a new SKILL.md inside an existing addon or framework
namespace: aiwg name: add-skill platforms: [all] description: Scaffold a new SKILL.md inside an existing addon or framework
Scaffold a new SKILL.md inside an existing addon or framework.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action | |---------|---------|--------| | Named add | "add skill voice-apply --to voice-framework" | Scaffold directly | | Description-driven | "create a skill that validates metadata" | Derive name=`validate-metadata`, prompt target | | Interactive | "add skill --interactive --to aiwg-utils" | Guided design mode | | Target omitted | "add skill my-skill" | Ask which addon or framework |
Extract from `$ARGUMENTS`:
If either `<name>` or `--to` is missing, ask before proceeding.
**Note**: Skills cannot be added to extensions. Extensions provide language/ecosystem-specific capabilities; skills require standalone, cross-cutting functionality.
Confirm the target addon or framework exists:
# Check addons ls agentic/code/addons/<target>/ # Check frameworks ls agentic/code/frameworks/<target>/
If target is an extension directory, explain the constraint and suggest using an addon instead.
Guide through skill design before generating:
1. **Purpose**: What does this skill do in one sentence? 2. **Trigger phrases**: What natural language phrases activate it?
3. **Input**: What does the skill need? (content, file path, parameters) 4. **Process**: What are the 3-7 execution steps? 5. **Output**: What does it produce? (transformed content, report, status) 6. **Reference materials**: Does it need supporting docs in `references/`? 7. **Platform targeting**: Which platforms should it deploy to?
aiwg add-skill <name> --to <target>
The generated file needs these sections populated:
--- platforms: [all] --- # Skill Name [One-paragraph description of what the skill does and when it activates] ## Triggers Alternate expressions and non-obvious activations: - "<phrase>" → <what happens> - "<phrase>" → <what happens> ## Trigger Patterns Reference | Pattern | Example | Action | |---------|---------|--------| | <category> | "<example>" | <action> | ## Process ### 1. <Step Name> [Description and any code blocks] ### 2. <Step Name> [Description] ## Generated Structure (if applicable) \`\`\` <what files are created> \`\`\` ## Output Format \`\`\` <what success output looks like> \`\`\` ## Examples ### Example 1: <scenario> **User**: "<trigger phrase>" **Extraction**: <what was parsed> **Action**: <what runs> **Result**: <what happens> ## References - @path/to/related/file — description
If the skill references supporting documentation:
mkdir -p <target>/skills/<name>/references/ # Create reference files as needed
The CLI tool updates `<target>/manifest.json`. Verify:
{
"skills": ["existing-skill", "<name>"]
}<target>/skills/<name>/ ├── SKILL.md # Main skill definition └── references/ # Supporting documentation (optional)
Manifest updated: `<target>/manifest.json`
Skill Created: <name> ───────────────────── Location: <target>/skills/<name>/ Created: ✓ SKILL.md ✓ references/ (placeholder) Manifest updated: <target>/manifest.json Next Steps: 1. Edit SKILL.md trigger phrases 2. Write execution process steps 3. Add reference materials (if needed) 4. Test with natural language: "<trigger phrase>"
**User**: "add skill lint-manifests --to aiwg-utils"
**Action**:
aiwg add-skill lint-manifests --to aiwg-utils
**Result**: `agentic/code/addons/aiwg-utils/skills/lint-manifests/SKILL.md` scaffolded with standard platform frontmatter and section stubs.
**User**: "create a skill voice-apply --to voice-framework --interactive"
**Process**: Guided questions establish trigger phrases ("apply voice", "write in X voice"), process steps (identify voice, load profile, transform), and reference materials needed (voice profile templates).
**Result**: `agentic/code/addons/voice-framework/skills/voice-apply/SKILL.md` plus `references/` directory.
**User**: "scaffold skill requirement-tracer --to sdlc-complete"
**Action**:
aiwg add-skill requirement-tracer --to sdlc-complete
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.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing