agentleFS
MicrosoftKnown publishermicrosoft-foundry/foundry-agent-webapp/.github/skills/planning-features/SKILL.md

planning-features

Skill124 starsChanged 7 months agoMITView on GitHub

Provides structured plan template for feature implementation. Use when planning new features, multi-file changes, or creating implementation roadmaps before coding.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search existing patterns before proposing new ones — reuse what the codebase already does

    line 22
  2. Very specific:

    Read relevant skills (e.g., writing-csharp-code, writing-typescript-code, writing-bicep-templates) to follow project conventions

    line 23
  3. Distinctive:

    Check current implementations in files you plan to modify so the plan reflects actual code structure

    line 24
  4. Distinctive:

    Every plan must include these sections:

    line 28
  5. Distinctive:

    Document each edge case and how the implementation should handle it.

    line 69
  6. Very specific:

    If the plan affects state machines, SSE events, or API endpoints, include updates to ARCHITECTURE-FLOW.md.

    line 72

≈ “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

Feature Planning

Tip: For read-only planning mode, press Shift+Tab in VS Code or Copilot CLI to enter built-in plan mode.

Research-First Workflow

  1. Understand the request — clarify scope and success criteria
  2. Search the codebase for existing patterns and relevant files
  3. Load relevant skills from .github/skills/ for project conventions
  4. Generate a structured plan using the template below

Research Guidelines

  • Search existing patterns before proposing new ones — reuse what the codebase already does
  • Read relevant skills (e.g., writing-csharp-code, writing-typescript-code, writing-bicep-templates) to follow project conventions
  • Check current implementations in files you plan to modify so the plan reflects actual code structure

Required Plan Structure

Every plan must include these sections:

1. Overview

2-3 sentence description of the feature or change.

2. Requirements

- [ ] Requirement one
- [ ] Requirement two

3. Files to Modify

File PathChanges
path/to/fileDescription of modifications

4. Files to Create

File PathPurpose
path/to/new/fileWhat this file does

5. Implementation Steps

Numbered steps with sub-steps. Reference skill patterns where applicable.

1. Step one
   - Sub-step referencing `writing-csharp-code` skill patterns
   - Sub-step with specific code location
2. Step two
   - Sub-step referencing `writing-typescript-code` skill patterns

6. Testing Checklist

- [ ] Manual verification step one
- [ ] Manual verification step two

7. Edge Cases

Document each edge case and how the implementation should handle it.

8. Documentation Updates

If the plan affects state machines, SSE events, or API endpoints, include updates to ARCHITECTURE-FLOW.md. Load the understanding-architecture skill for validation rules.

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.