agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Run a comprehensive health check on the AIWG installation and workspace with pass/fail diagnostics and remediation steps
$ npx -y skills add jmagly/aiwg --skill aiwg-doctor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/aiwg-doctorContext preview
The summary Claude sees to decide when to auto-load this skill.
Run a comprehensive health check on the AIWG installation and workspace with pass/fail diagnostics and remediation steps
name: aiwg-doctor namespace: aiwg platforms: [all] kernel: true description: Run a comprehensive health check on the AIWG installation and workspace with pass/fail diagnostics and remediation steps
You run a comprehensive health check on the AIWG installation and workspace, reporting pass/fail for each diagnostic with remediation steps for any failures.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action | |---------|---------|--------| | Health check | "check health" / "is aiwg healthy" | Run `aiwg doctor` | | Diagnostic request | "diagnose" / "run diagnostics" | Run `aiwg doctor` | | Broken install | "aiwg isn't working" | Run `aiwg doctor` | | Setup validation | "check my aiwg setup" | Run `aiwg doctor` | | Troubleshooting | "troubleshoot installation" | Run `aiwg doctor` | | Verbose check | "run full diagnostics" | Run `aiwg doctor --verbose` |
When triggered:
1. **Extract intent**:
2. **Run the appropriate command**:
# Standard health check aiwg doctor # Verbose output (additional detail per check) aiwg doctor --verbose
The doctor command (`tools/cli/doctor.mjs`) validates:
3. **Report the result** — present a summary of checks passed and failed. For each failure, include the remediation step from the doctor output. Common remediations:
**User**: "Check AIWG health"
**Extraction**: Routine health check, no specific symptom
**Action**:
aiwg doctor
**Response**: "All checks passed. npm package v2026.3.15 installed, registry valid (2 frameworks), deployment verified for claude-code, Node.js v20.11.0 compatible."
**User**: "AIWG commands aren't showing up in Claude"
**Extraction**: User reports missing commands — deployment check is the likely culprit
**Action**:
aiwg doctor
**Response**: "Doctor found 1 issue: framework files are not deployed to `.claude/commands/`. Run `aiwg sync` to redeploy, then restart your Claude session."
**User**: "I just installed AIWG — is everything set up correctly?"
**Extraction**: New install, full validation requested
**Action**:
aiwg doctor
**Response**: "Installation looks good. One note: no frameworks are deployed yet. Run `aiwg use sdlc` to deploy the SDLC framework, or `aiwg use all` to deploy everything."
**User**: "Run full diagnostics on AIWG"
**Extraction**: Verbose check requested
**Action**:
aiwg doctor --verbose
**Response**: "Verbose diagnostics complete. [Output summary with per-check detail, paths, and versions.]"
If the user mentions a specific symptom before triggering doctor:
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