agentleFS
felipefontourafelipefontoura/pi-sdd-kit/skills/sdd-plan/SKILL.md

sdd-plan

Skill36 starsChanged 6 months agoMITView on GitHub

Cognitive SDD skill for creating or updating optional PLAN.md from captured ideas or project goals. Use when the conversation calls for roadmap, personas, feature mapping, phases, dependencies, and open decisions before requirements, even without an explicit command. Do not use for feature-level requirements or coding.

We split this skill into the rules it gives an agent

17 rules. 0 are common, 8 are distinctive, and 9 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 9

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ../_shared/references/templates.md when drafting the artifact.

    line 19
  2. Very specific:

    Use package-level templates/plan.md as the user-facing template when available.

    line 20
  3. Very specific:

    If .ai/strategy/handoff/strategy-brief.md exists, read it as optional upstream context.

    line 22
  4. Very specific:

    Read .ai/sdd/ideas/*.md relevant to the requested project or feature set.

    line 25
  5. Very specific:

    Read existing .ai/sdd/PLAN.md when updating.

    line 26
  6. Distinctive:

    When a strategy handoff is used, reflect it in plan source/context notes and call out any unresolved readiness gaps.

    line 29
  7. Distinctive:

    Ask one question at a time.

    line 32
  8. Distinctive:

    Keep this at project/roadmap level.

    line 34
  9. Very specific:

    Use the Plan Template from ../_shared/references/templates.md.

    line 37
  10. Distinctive:

    Ask for explicit approval or requested changes.

    line 48
  11. Very specific:

    After explicit approval, update .ai/sdd/PLAN.md to approved and set .status to plan:approved if a project-level .status is used.

    line 53
  12. Very specific:

    Create .ai/sdd/INDEX.md if useful for tracking feature specs.

    line 54
  13. Distinctive:

    Do not write code in this skill.

    line 71
  14. Distinctive:

    Do not create feature-level requirements unless the user explicitly changes phase.

    line 72
  15. Distinctive:

    Do not over-plan small one-screen work.

    line 73
  16. Distinctive:

    Do not mark a plan approved without explicit user approval.

    line 74
  17. Very specific:

    Do not silently change feature-spec .status values from this skill unless the user explicitly requested a project-level plan status update.

    line 76

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

SDD Plan

Convert explored ideas into a product or project plan.

Purpose

PLAN is the bridge between open-ended IDEA exploration and feature-level REQUIREMENTS. It is optional for very small work and recommended for medium projects with multiple features, modules, or phases.

Workflow

  1. Load the SDD reference.
    • Read ../_shared/references/sdd-practical.md.
    • Apply the Language Policy: respond and write artifacts in the user's initial chat language while keeping skill instructions and templates in EN-US.
    • Read ../_shared/references/templates.md when drafting the artifact.
    • Use package-level templates/plan.md as the user-facing template when available.
    • Load relevant .ai/steering/*.md files when present, especially product.md, tech-stack.md, conventions.md, and principles.md.
    • If .ai/strategy/handoff/strategy-brief.md exists, read it as optional upstream context; use it to reduce rediscovery, but do not require it or bypass plan approval.
  2. Gather context.
    • Read .ai/sdd/ideas/*.md relevant to the requested project or feature set.
    • Read existing .ai/sdd/PLAN.md when updating.
    • Inspect .ai/sdd/specs/ if feature specs already exist.
    • Briefly inspect project README or product docs when available.
    • When a strategy handoff is used, reflect it in plan source/context notes and call out any unresolved readiness gaps.
  3. Clarify planning scope.
    • Ask one question at a time.
    • Cover vision, personas, MVP boundary, feature map, dependencies, constraints, and open decisions.
    • Keep this at project/roadmap level; do not design implementation details.
  4. Draft the plan.
    • Use the Plan Template from ../_shared/references/templates.md.
    • Organize features by MoSCoW phases:
      • Phase 1 — MVP / Must Have
      • Phase 2 — Essentials / Should Have
      • Phase 3 — Nice to Have / Could Have
    • Include feature IDs such as F01, F02, F03.
    • Include dependencies only when they affect sequencing.
    • Include Open Decisions for unresolved strategy or scope questions.
  5. Review with the user.
    • Present the complete draft.
    • Ask for explicit approval or requested changes.
    • Revise until approved.
  6. Save draft and guide next step.
    • Save drafts to .ai/sdd/PLAN.md with > Status: Draft and .status as plan:draft when useful for collaboration.
    • After explicit approval, update .ai/sdd/PLAN.md to approved and set .status to plan:approved if a project-level .status is used.
    • Create .ai/sdd/INDEX.md if useful for tracking feature specs.
    • Recommend creating requirements.md for the first Phase 1 feature.

Output

  • .ai/sdd/PLAN.md
  • Optional .ai/sdd/INDEX.md

Quality Bar

  • The plan must make MVP boundaries clear.
  • Feature IDs must be specific enough to become spec directories.
  • Dependencies must reflect real sequencing constraints, not arbitrary order.
  • Open Decisions must capture unresolved ambiguity instead of hiding it.

Critical Rules

  • Do not write code in this skill.
  • Do not create feature-level requirements unless the user explicitly changes phase.
  • Do not over-plan small one-screen work; recommend going directly to PRD when PLAN would be wasteful.
  • Do not mark a plan approved without explicit user approval.
  • Draft plans may be saved, but they do not authorize feature implementation.
  • Do not silently change feature-spec .status values from this skill unless the user explicitly requested a project-level plan status update.

Download now (ZIP)

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. khangpqvn/SDDADD★ 12same name
    2. ad1code/sdd-harness★ 4same name
    3. monaccode/astromesh-sdd★ 0same name
    4. pchemguy/Skill-SDD-Manager★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

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.