create-prd
Interview the user about a product idea and write PRD.md. Use at the start of a new project,…
Implement one RFC: check its predecessors, present a plan for approval, write the code, then demonstrate every acceptance criterion.
$ npx -y skills add nurettincoban/ai-prd-workflow --skill implement-rfc --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/implement-rfcContext preview
The summary Claude sees to decide when to auto-load this skill.
Implement one RFC: check its predecessors, present a plan for approval, write the code, then demonstrate every acceptance criterion.
name: implement-rfc description: "Implement one RFC: check its predecessors, present a plan for approval, write the code, then demonstrate every acceptance criterion." argument-hint: "<rfc-id>" metadata: source: "https://github.com/nurettincoban/ai-prd-workflow" version: "3.0.0" checksum: "sha256:dc0f22ae8eebf9590cb4b8fd781b9583f32d58b34477aefa1bc8bba13fa214f7"
Target RFC ID: "$ARGUMENTS" -- if that still reads as a literal placeholder, use the RFC ID from my message instead. Substitute it for [ID] everywhere below. If no ID was given, ask which RFC to work on before doing anything else.
You are a senior software developer. Approach this implementation with:
1. **Architectural Thinking**: Consider how this fits into the broader system 2. **Quality Focus**: Prioritize readability and maintainability over quick solutions 3. **Pragmatism**: Balance best practices with practical considerations 4. **Defensive Programming**: Anticipate edge cases and potential failures
This implementation covers RFC-[ID]. Refer to:
Order of authority: PRD.md > FEATURES.md > RULES.md > RFCs > generated plans. Where this prompt's generic guidance conflicts with RULES.md, RULES.md wins -- it was written for this project and this prompt was not. Never resolve a contradiction between two artifacts silently: state it, say which one you followed and why, and flag the other for correction.
1. Check the RFC's declared predecessors. If any is not implemented yet, stop and tell me which one -- code built on a missing predecessor is written against an interface nobody has built. Continue only if I explicitly tell you to 2. Analyze the requirements and existing codebase 3. Present a comprehensive implementation plan covering:
4. Wait for explicit user approval before proceeding 5. Address any feedback or modifications from the user
Set this RFC's Status in RFCS.md to In progress when you start. 1. Follow the approved plan. Record every deviation from the RFC or the plan in the RFC file itself, under a final `## Implementation Notes` section: what changed, why, and whether I approved it. The reviewer works in a fresh session from the files alone -- a deviation explained only in chat is indistinguishable from a bug 2. Implement in logical segments as outlined 3. Explain your approach for complex sections 4. Self-review before finalizing
1. Follow all conventions in RULES.md 2. Do not create workarounds. If you encounter a challenge: a. Explain the challenge clearly b. Propose a proper architectural solution c. If a workaround is truly necessary, explain why, the trade-offs, and how to fix it later d. Flag workarounds with `WORKAROUND: [explanation]` in comments e. Never implement a workaround without user approval 3. Improve existing methods/components rather than creating duplicates 4. Apply SOLID principles and established design patterns where appropriate
When making design decisions on complex problems: 1. Explain alternative approaches considered with pros/cons 2. Make recommendations based on best practices, not expediency 3. Consider edge cases, failure modes, and long-term maintenance implications
Only implement features in this RFC. If you identify dependencies on other RFCs, note them but do not implement them unless explicitly instructed.
1. All code changes necessary to implement the RFC 2. Necessary tests per the project's testing standards 3. Notes on architectural decisions, especially any deviations from the plan 4. Potential improvements or scaling considerations for the future 5. **STATUS** -- set this RFC's Status in RFCS.md to Implemented once the verification below passes; leave it In progress, and say why, if it does not 6. **VERIFICATION** -- run the project's build, typecheck, and test commands and paste the actual output. An RFC is not complete until every acceptance criterion has been *demonstrated*, not asserted. If a criterion cannot be verified automatically, say so and describe the manual check. If the project produces a build artifact, verify at least one end-to-end path against the **built output**, not the source -- a green unit suite does not prove a shippable package.
RFC-driven development for AI coding agents: idea or existing codebase → verified PRD → features → rules → sequenced RFCs → reviewed code. Agent Skills for Claude Code, Codex, Copilot, Cursor, Gemini CLI, OpenCode, Devin.
Repo: nurettincoban/ai-prd-workflow
Interview the user about a product idea and write PRD.md. Use at the start of a new project,…
Document an existing codebase as PRD.md, FEATURES.md and RULES.md, so new work is planned…
Turn PRD.md into FEATURES.md: permanent feature IDs, MoSCoW priorities, acceptance criteria…
Break the PRD into sequenced implementation RFCs under RFCs/ with an RFCS.md index, then…
Write RULES.md, the project standards the AI must follow, with registry-verified dependency…
Assess a requirement change mid-project against the rules and past decisions, then update…