agentleFS
itmbastawiitmbastawi/product-skill-pack/developer-agent/SKILL.md

developer-agent

Skill7 starsChanged 4 months agoMITView on GitHub

Produce an implementation-ready plan and optionally begin coding based on all prior pipeline outputs. Use as step 7 (final step) of the product pipeline, after the sprint plan is complete. Requires `06-sprint-plan.md` and all prior outputs. Produces an implementation plan with file structure, coding standards, and initial setup instructions.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. thefrederiksen/cc-director★ 110same name
    2. thefrederiksen/devthrottle★ 110same 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 repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read ALL prior outputs from @output_dir@/: 01-interview-brief.md through 06-sprint-plan.md

    line 21
  2. Distinctive:

    If the user says "start coding" or "implement it":

    line 119
  3. Distinctive:

    Create the project structure

    line 120
  4. Distinctive:

    Create the first migration/schema

    line 123
  5. Distinctive:

    Write tests as you go

    line 125
  6. Distinctive:

    Follow the architecture design exactly

    line 132
  7. Distinctive:

    Use the tech stack specified in the architecture (which aligns with the user's confirmed preferences from the tech preferences checkpoint)

    line 133
  8. Distinctive:

    Write tests alongside code, not after

    line 135
  9. Distinctive:

    Commit frequently with descriptive messages

    line 136
  10. Distinctive:

    If you begin implementation, create a git repo and make initial commits

    line 137

≈ “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

Developer Agent — Step 7 of Product Pipeline

Goal

Produce a concrete implementation plan and optionally begin building the solution.

Input

Read ALL prior outputs from @output_dir@/: 01-interview-brief.md through 06-sprint-plan.md

Output

Save to @output_dir@/07-implementation-plan.md

Deliverables

1. Project Structure

project-name/
├── src/
│   ├── components/
│   ├── services/
│   ├── utils/
│   └── ...
├── tests/
├── docs/
├── config/
└── ...

2. Development Setup

  • Prerequisites (Node version, Python version, Go version, etc.) — align with confirmed tech stack from pipeline state
  • Installation steps
  • Environment variables
  • Local database setup
  • Running locally

3. Coding Standards

  • Language/framework conventions
  • Linting/formatting rules
  • Naming conventions
  • File organization
  • Comment/documentation standards

4. Implementation Order

Based on Sprint 1 tasks, specify:

  • What to build first
  • Database migrations
  • API endpoints to implement
  • Frontend screens to build
  • Integration points

5. Key Implementation Notes

  • Complex logic explanations
  • Third-party integration details
  • Performance considerations
  • Security implementation details

6. Testing Strategy

  • Unit test approach
  • Integration test approach
  • Test data setup
  • CI/CD test pipeline

7. Deployment Guide

  • Build process
  • Environment configuration
  • Deployment steps
  • Rollback procedure

Output Template

# Implementation Plan: [Project Name]

## Project Structure
[Directory tree]

## Development Setup
### Prerequisites
### Installation
### Environment Configuration
### Running Locally

## Coding Standards
[Conventions and rules]

## Implementation Order
### Phase 1: Foundation
### Phase 2: Core Features
### Phase 3: Integration
### Phase 4: Polish

## Key Implementation Notes
[Complex areas and how to handle them]

## Testing Strategy
[How to test each layer]

## Deployment Guide
[How to deploy to production]

## Next Steps
[Immediate actions to start development]

Optional: Begin Implementation

If the user says "start coding" or "implement it":

  1. Create the project structure
  2. Set up configuration files
  3. Initialize the repository
  4. Create the first migration/schema
  5. Implement Sprint 1 features
  6. Write tests as you go

Rules

  • The implementation plan must be executable by a developer who hasn't seen the prior steps
  • Include specific file names and paths
  • Reference specific requirements from the PRD by ID
  • Follow the architecture design exactly
  • Use the tech stack specified in the architecture (which aligns with the user's confirmed preferences from the tech preferences checkpoint)
  • Include error handling and logging from the start
  • Write tests alongside code, not after
  • Commit frequently with descriptive messages
  • If you begin implementation, create a git repo and make initial commits

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.