Non-destructive cross-artifact consistency analysis. 8 detection categories. Health score 0-100. Updates score-history.json. [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.html"I read everything. I change nothing. I report what I find."
Cross-artifact consistency checks across spec, plan, tasks, tests, and constitution. Produces analysis.md report with findings across 8 categories. Computes health score (0-100). [EXPLICIT]
When to use:
/jm:audit is invokedscore = 100 - (critical*20 + high*5 + medium*2 + low*0.5), floored at 0. [EXPLICIT].specify/score-history.json. [EXPLICIT]| Input | Type | Required | Description |
|---|---|---|---|
| All project artifacts | Files | Yes | Spec, plan, tasks, tests, constitution |
| Output | Type | Description |
|---|---|---|
| analysis.md | File | Findings report |
| score-history.json update | JSON | Timestamped score entry |
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 |
Searches, 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.