Validates deliverables at quality gates G0-G3. Blocks phase transitions until criteria are met. Produces pass/fail reports with evidence. [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"No gate, no advance. No evidence, no pass."
Enforces the 4 quality gates (G0-G3) that govern phase transitions in the JM-ADK pipeline. Validates that deliverables meet defined criteria before allowing advancement. [EXPLICIT]
When to use:
/jm:advance is invoked[CODE]/[CONFIG]/[DOC]. No evidence = no pass. [EXPLICIT].specify/context.json stage field. [EXPLICIT]| Gate | Criteria | Pass Condition |
|---|---|---|
| G0 | Secrets scan, stack compliance (R-002/R-003) | Zero violations |
| G1 | Analysis deliverables complete, evidence tags present, stakeholder map exists | All artifacts exist with evidence |
| G2 | Firebase architecture documented, data model validated, security rules drafted | Architecture review passed |
| G3 | Tests pass, Lighthouse > 90, security audit clean, monitoring configured | All checks green |
.specify/score-history.json with findings. [EXPLICIT]| Input | Type | Required | Description |
|---|---|---|---|
| Gate ID | Enum | Yes | G0, G1, G2, or G3 |
| Artifacts | Files | Yes | Deliverables to evaluate |
| Output | Type | Description |
|---|---|---|
| Gate Report | Markdown | Pass/fail per criterion with evidence |
| Score Update | JSON | Updated score-history.json entry |
[!WARNING] IF gate evaluation finds >30%
[ASSUMPTION]tags THEN add WARNING banner to gate report.
[!WARNING] IF G3 is requested but G1 hasn't passed THEN STOP. Gates are sequential.
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.