openspec-continue-change
Use this skill at Step 3 (after openspec-new-change) to expand proposal / design / specs into implementation-ready content. Iteratively fills out the technical approach, data model, contract specs, test strategy, and risk table. Stop when the change is "implementation-ready": every spec has acceptance criteria, design covers all PRD scope items, and the Compliance Design section is fully populated. Chinese trigger examples: "继续 OpenSpec", "OpenSpec 续写", "完善 design.md", "specs 填充". Do NOT use for task decomposition (next step), do NOT use to write code. Success = design.md covers 100% of in-s
npx skills add charliehzm/medharness --skill openspec-continue-change --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# OpenSpec Continue Change The "make it implementation-ready" expansion. After `openspec-new-change` scaffolds, this fills. ## Quality bar — when to stop The change is ready when **every PRD in-scope item maps to ≥ 1 spec row**, and **every spec row has acceptance criteria**. ## Workflow 1. **PRD ↔ Spec mapping** — list every in-scope item in PRD §3; ensure each has a spec id. 2. **Design body** —
What does the openspec-continue-change skill do?
Use this skill at Step 3 (after openspec-new-change) to expand proposal / design / specs into implementation-ready content. Iteratively fills out the technical approach, data model, contract specs, test strategy, and risk table. Stop when the change is "implementation-ready": every spec has acceptance criteria, design covers all PRD scope items, and the Compliance Design section is fully populated. Chinese trigger examples: "继续 OpenSpec", "OpenSpec 续写", "完善 design.md", "specs 填充". Do NOT use for task decomposition (next step), do NOT use to write code. Success = design.md covers 100% of in-s
How do I install it?
Run `npx skills add charliehzm/medharness --skill openspec-continue-change --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From charliehzm/medharness, a repository with 96 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.