Structured bug tracking. Creates bug entries with severity, reproduction steps, and T-B tasks. Links to affected requirements. [EXPLICIT]
From jm-adknpx claudepluginhub javimontano/jm-adk-alfaThis skill uses the workspace's default tool permissions.
agents/guardian.mdagents/lead.mdagents/specialist.mdagents/support.mdevals/evals.jsonknowledge/body-of-knowledge.mdknowledge/knowledge-graph.mdprompts/meta.mdprompts/primary.mdprompts/variations/deep.mdprompts/variations/quick.mdtemplates/output.docx.mdtemplates/output.htmlSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
"A bug without reproduction steps is not a bug report. It's a rumor."
Creates structured bug entries in bugs.md with severity, reproduction steps, and assigned T-B tasks. Links bugs to affected FR-XXX requirements. [EXPLICIT]
When to use:
/jm:repair is invoked- [ ] [T-B###] [BUG-NNN] Fix: {description} to tasks.md. [EXPLICIT]| Input | Type | Required | Description |
|---|---|---|---|
| Bug description | Text | Yes | What went wrong |
| Output | Type | Description |
|---|---|---|
| bugs.md entry | File | Structured bug report |
| tasks.md update | File | T-B### fix task |
Example invocations:
| Scenario | Handling |
|---|---|
| Empty or minimal input | Request clarification before proceeding |
| Conflicting requirements | Flag conflicts explicitly, propose resolution |
| Out-of-scope request | Redirect to appropriate skill or escalate |