Red-green-verify implementation cycle. Verifies hash integrity of .feature files. NEVER modifies test assertions. Enforces coverage. [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.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
"Tests are sacred. Code bends to tests, never the reverse."
Guides implementation following red-green-verify TDD cycle. Verifies SHA256 hash integrity of .feature files before coding. Blocks any attempt to modify test assertions. [EXPLICIT]
When to use:
implementing-NN%. [EXPLICIT]- [x] [T###]. [EXPLICIT]| Input | Type | Required | Description |
|---|---|---|---|
| tasks.md | File | Yes | Task to implement |
| *.feature files | Gherkin | Yes | Hash-locked tests |
| context.json | JSON | Yes | Hash verification |
| Output | Type | Description |
|---|---|---|
| Source code | Files | Implementation |
| context.json update | JSON | Progress percentage |
[!WARNING] IF .feature hash mismatch THEN STOP. Do not code. Report integrity violation.
[!WARNING] IF test modified to pass THEN REVERT. Fix code, not tests.
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 |