agentleFS
IcodeNetIcodeNet/agent-skills/skills/plan-from-rfc/SKILL.md

plan-from-rfc

Skill0 starsChanged 4 months agoMITView on GitHub

Generate a phased implementation plan from an RFC, design doc, or spec (URL or file). Use when the user provides an RFC/design document and wants an implementation plan, migration plan, or execution-ready PR breakdown from it.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If any input is missing, ask the user first:

    line 15
  2. Distinctive:

    If the RFC source cannot be accessed, ask the user to paste key sections (goal, scope, constraints, decisions, risks), then continue with …

    line 22
  3. Distinctive:

    Keep behavior-preserving constraints explicit when requested.

    line 29
  4. Distinctive:

    Prefer small PRs over broad multi-domain PRs.

    line 44
  5. Distinctive:

    Do not invent undocumented architecture decisions.

    line 46
  6. Distinctive:

    If the user asked for a plan only, do not implement code.

    line 47
  7. Distinctive:

    Keep commands aligned with the repo's package scripts when possible.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan From RFC

Turn an RFC or design document into a phased, executable delivery plan.

Input collection

If any input is missing, ask the user first:

  1. RFC source (URL or workspace file path)
  2. Goal (implement, refactor, migrate, or review)
  3. Constraints (timeline, risk tolerance, no-behavior-change, testing scope)
  4. Output depth (high-level or execution-ready PR breakdown)

If the RFC source cannot be accessed, ask the user to paste key sections (goal, scope, constraints, decisions, risks), then continue with explicit assumptions.

Analysis steps

  1. Extract: problem statement, goals and non-goals, constraints, accepted decisions, dependencies.
  2. Identify ambiguities and missing information.
  3. Convert into a phased delivery plan with small, low-risk increments.
  4. Keep behavior-preserving constraints explicit when requested.

Output format (exact order)

  1. Context Summary
  2. Assumptions
  3. Scope In / Scope Out
  4. Implementation Plan — phased steps, per-step dependencies, rollback notes
  5. PR Breakdown — one bullet per PR with intent, likely files/areas touched, and risk
  6. Test Strategy — targeted tests first; broader checks only where risk justifies
  7. Risks and Mitigations
  8. Open Questions for Approval

Rules

  • Prefer small PRs over broad multi-domain PRs.
  • Highlight hotspot/conflict-prone files when likely.
  • Do not invent undocumented architecture decisions; mark them as open questions.
  • If the user asked for a plan only, do not implement code.
  • Keep commands aligned with the repo's package scripts when possible.
  • To stress-test the resulting plan, follow with the plan-critic skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.