Generates Gherkin .feature files from spec.md. SHA256 hash-locks assertions BEFORE implementation. Prevents silent requirement drift. [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"Tests are written from specs, not from code. Hash-locked, immutable until re-specified."
Transforms spec.md requirements into Gherkin .feature files. Computes SHA256 hashes for each feature file and stores them in context.json. These hashes LOCK assertions before implementation begins. [EXPLICIT]
When to use:
specs/{feature}/tests/features/*.feature files. [EXPLICIT]@FR-001, @US-1, @SC-001. [EXPLICIT]# DO NOT MODIFY — hash-locked header. [EXPLICIT].specify/context.json assertions object. [EXPLICIT]{ "file": "hash" }| Input | Type | Required | Description |
|---|---|---|---|
| spec.md | File | Yes | Source requirements |
| Output | Type | Description |
|---|---|---|
| *.feature files | Gherkin | Hash-locked test scenarios |
| context.json update | JSON | SHA256 hashes stored |
[!WARNING] IF .feature file modified during implementation THEN BLOCK. Re-specify first.
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.