From grounded-ai-dev
Phase 4 of Grounded AI — IMPLEMENT. Use after tests are approved (Gate B) to build code that satisfies the specification and passes the test suite. Trigger when grounded-test-first completes and tests are approved, or when the user asks to build, code, or implement against an approved spec and tests. Produces the delivered codebase with review notes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/grounded-ai-dev:grounded-implementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate and write code governed by the specification and the test suite. Use AI tools for
Generate and write code governed by the specification and the test suite. Use AI tools for speed, but speed is directed by the spec, not by intuition.
grounded-security-review on every engagement — run the checklist before Phase 5.grounded-ui-review if there is a user interface.grounded-ai-guardrails if there is an LLM, agent, RAG, or generative feature.Build is complete only when all tests pass, code is reviewed against the spec, security and data
handling are reviewed, and every part is explainable. Then proceed to grounded-verify.
Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.
npx claudepluginhub pmj7671/grounded-ai-dev --plugin grounded-ai-dev