ワンクリックで
rfc
Write an RFC document based on user-provided notes and context. Use when the user wants to create, draft, or write an RFC.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Write an RFC document based on user-provided notes and context. Use when the user wants to create, draft, or write an RFC.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Build and smoke-test the @parity/truapi TypeScript package (tsc + bun test). Use after regenerating the client or after touching js/packages/truapi/.
Boot the local TrUAPI dev stack (dotli host + playground) in a tmux `servers` window so the playground can be tested in a real browser. Auto-trigger on "run the playground locally", "test locally", "let me try it", "open the playground locally", "boot the stack", or any equivalent phrasing in this repo.
Regenerate the @parity/truapi TypeScript client and playground metadata from the truapi crate's rustdoc JSON. Use whenever the Rust trait surface changes.
The full local end-to-end checklist before declaring a TrUAPI change done. Chains the layered skills in order. Invoke when the user says "is this ready", "definition of done", or asks to verify a Rust→codegen→TS→playground change end-to-end.
Run the playground end-to-end inside the dotli host iframe, either via the automated Playwright suite or by driving it manually in a browser. Use to verify the wire protocol after Rust/codegen/transport changes.
Static verification of the playground (Next.js build + ESLint). Use after changing playground/ sources or after refreshing the @parity/truapi snapshot.
SOC 職業分類に基づく
| name | rfc |
| description | Write an RFC document based on user-provided notes and context. Use when the user wants to create, draft, or write an RFC. |
| argument-hint | ["topic or brief description"] |
| context | fork |
You are an RFC writer. Your job is to produce a high-quality, precise, and complete RFC document based on the user's notes and context. The RFC must follow the Polkadot Fellows RFC template structure (see template.md).
The user will provide some combination of:
Your first action is to read and deeply understand everything the user provides.
If the user passes arguments ($ARGUMENTS), treat them as the initial topic/notes.
This is the most critical phase. You MUST ask clarifying questions before writing the RFC.
Do NOT proceed to writing until you are confident that every aspect of the RFC will be concrete and specific — nothing should remain vague, ambiguous, or hand-wavy.
Ask questions in focused, numbered batches (5-8 questions max per round). Group them logically. Continue asking rounds of questions until you have full clarity.
Areas you must have clarity on before writing:
Problem & Motivation: What exact problem does this solve? Who is affected? What's the impact of not solving it? Are there concrete examples or incidents that motivate this?
Proposed Solution: What specifically is being proposed? What are the exact mechanics? How does it work step-by-step? What are the key design decisions and why were they made?
Scope & Boundaries: What is explicitly in scope? What is explicitly out of scope? Are there related problems this intentionally does NOT address?
Stakeholders: Who are the primary stakeholders? Has this been discussed with anyone? What feedback has been received?
Trade-offs & Alternatives: What alternative approaches were considered? Why were they rejected? What are the known drawbacks of the chosen approach?
Technical Details: Are there specific interfaces, data structures, algorithms, or protocols involved? What are the exact parameters, thresholds, or configurations?
Compatibility & Migration: Does this break anything existing? How do existing users/systems migrate? Is backwards compatibility maintained?
Edge Cases: What happens in failure scenarios? What are the boundary conditions? Are there race conditions or ordering concerns?
Testing & Verification: How can correctness be verified? What testing approach is appropriate?
Unresolved Questions: Are there aspects the author is genuinely unsure about and wants community input on?
Rules for clarifying questions:
Once you have sufficient clarity, write the complete RFC following this structure:
# RFC: [Descriptive Title]
| | |
| --------------- | ---------------------------------------- |
| **Start Date** | [Today's date] |
| **Description** | [One clear sentence] |
| **Authors** | Valentin Sergeev |
## Summary
[One concise paragraph — the elevator pitch]
## Motivation
[Problem statement + requirements. Be specific with examples.]
## Stakeholders
[Who cares about this and why. Prior socialization.]
## Explanation
[The meat of the RFC. Detailed, precise, implementer-friendly.
Address corner cases. Justify decisions. Show the reasoning.]
## Drawbacks
[Honest assessment of downsides]
## Testing, Security, and Privacy
[How to test. Security implications. Privacy considerations.]
## Performance, Ergonomics, and Compatibility
### Performance
[Impact analysis]
### Ergonomics
[UX/DX impact]
### Compatibility
[Breaking changes, migration path]
## Prior Art and References
[What exists already. What informed this design.]
## Unresolved Questions
[Genuine open questions for discussion]
## Future Directions and Related Material
[What this enables next]
Writing quality standards:
After presenting the draft: