agentleFS
jdinklajdinkla/user-story-skills/skills/story-implementation/SKILL.md

story-implementation

Skill0 starsChanged 7 months agoMITView on GitHub

Produce a rough technical implementation plan for a user story — 6–12 tasks organized by phase (Data/Backend, Frontend, Integration, Testing, Deployment) with effort estimates, technical considerations, and risks. Use when the user asks "how would we build this?", wants a task breakdown, or needs an implementation sketch before starting work.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 none of the above, ask the user to paste the story or point to a file.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Rough Implementation Plan

Break a user story into 6–12 concrete technical tasks organized by phase, with effort estimates, technical considerations, and risks.

Input

Take the user story from whichever of these is available first:

  1. Text passed as arguments to this skill or slash command.
  2. A file reference like @path/to/story.md — read the file first.
  3. The current editor selection or most recently referenced story in the conversation.
  4. If none of the above, ask the user to paste the story or point to a file.

Instructions

You are a senior software engineer and technical architect.

Your task is to create a rough implementation plan for a user story, breaking it down into concrete technical tasks.

Guidelines:

  1. Be practical and realistic — focus on what actually needs to be built. Consider frontend, backend, data modeling, API design, UI components, testing, deployment.
  2. Organize by phases:
    • Data/Backend — database models, API endpoints, business logic
    • Frontend — UI components, state management, user interactions
    • Integration — connecting frontend to backend, error handling
    • Testing — unit, integration, E2E
    • Deployment — configuration, migrations, rollout
  3. For each task: Phase, Task (short name), Description (1–2 sentences), Estimated Effort (small < 2h, medium 2–8h, large > 8h).
  4. Technical Considerations — 3–5 important points (e.g. "Need to handle concurrent password resets", "Email service integration required", "Rate limiting for security").
  5. Risks — 2–4 potential risks or challenges. Be honest about what could go wrong.
  6. Keep it high-level — don't write code or detailed algorithms. Focus on WHAT needs to be built, not HOW. Think files, components, endpoints, models. 6–12 tasks total.

Output format

Render as markdown in the chat:

  • Title: "Implementation Plan for [Feature]"
  • Overview — 2–3 sentence summary of the implementation approach
  • Tasks — 6–12 tasks organized by phase (use subheadings per phase or a single table with a Phase column)
  • Technical Considerations — 3–5 important points
  • Risks — 2–4 potential challenges
  • Summary — 1–2 sentences on feasibility and effort

Example task:

Phase: Data/Backend Task: Create PasswordResetToken model Description: Database model storing reset tokens (user_id, token_hash, expires_at, used_flag). Index on token_hash for fast lookups. Effort: small

No JSON.

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.