agentleFS
SrejonKhanSrejonKhan/agent-skills/skills/list_features/SKILL.md

list_features

Skill3 starsChanged 2 months agoMITView on GitHub

Scans the codebase to generate a comprehensive, prompt-based feature list in 'features_listed.md' for recreating the app in any language.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to extract a complete, technically precise blueprint of the application, formatted as a series of prompts that could be used …

    line 8
  2. Very specific:

    Use list_dir to map the project structure.

    line 17
  3. Very specific:

    Use view_file to inspect README.md, CODE_DOCUMENTATION.md (if available), and key source files (entry points, controllers, UI components).

    line 18
  4. Very specific:

    Use write_to_file to generate the final Markdown report.

    line 19
  5. Distinctive:

    Precision: Use standard technical jargon (e.g., "JWT Authentication", "Responsive Grid Layout", "RESTful Endpoint", "WebSocket Stream").

    line 36
  6. Distinctive:

    Completeness: If a button exists, the feature is "Clickable Button that triggers X".

    line 37
  7. Distinctive:

    Create a file that looks like a specification document for an AI or Developer:

    line 41
  8. Distinctive:

    The "Rebuild Test": Ask yourself: "If I gave this file to a stranger, could they build the _exact_ same app without seeing the code?"

    line 53
  9. Distinctive:

    Ensure no hidden features (middleware, schedulers) are missed.

    line 54
  10. Distinctive:

    When extracting features, ensure you also capture the underlying mechanics:

    line 62

≈ “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

List Features (Recreation Spec)

Use this skill to extract a complete, technically precise blueprint of the application, formatted as a series of prompts that could be used to rebuild the app from scratch.

Inputs

  • Project Scope: The root directory of the application to analyze.
  • Output File: features_listed.md (default).

Tooling Strategy

  • Use list_dir to map the project structure.
  • Use view_file to inspect README.md, CODE_DOCUMENTATION.md (if available), and key source files (entry points, controllers, UI components).
  • Use write_to_file to generate the final Markdown report.

Workflow

1. Analysis (Deep Scan)

  • Objective: Understand exactly what the app does, not just how it's written.
  • Sources:
    • Documentation (README.md, DESIGN_PHILOSOPHY.md).
    • Configuration (package.json, requirements.txt) to identify tech stack implications.
    • Source Code: Look for routes, UI components, state management, and database schemas.

2. Feature Extration & Prompt Generation

For every identified feature, convert it into a Technical Prompt.

  • Format: "Implement [Feature Name] using [Input/Constraint]. The system must [Action] when [Trigger]."
  • Precision: Use standard technical jargon (e.g., "JWT Authentication", "Responsive Grid Layout", "RESTful Endpoint", "WebSocket Stream").
  • Completeness: If a button exists, the feature is "Clickable Button that triggers X". If a background task runs, the feature is "Background Cron Job for X".

3. Report Structuring (features_listed.md)

Create a file that looks like a specification document for an AI or Developer:

Structure:

  1. Core Architecture: High-level stack agnostic requirements (e.g., "Client-Server Architecture").
  2. User Interface (UI): Detailed prompts for every page/component (e.g., "Create a dashboard with glassmorphism...").
  3. Business Logic & Functional Requirements: (e.g., "Calculate tax based on...").
  4. Data Persistence: (e.g., "Schema must support...").
  5. API & Integration: (e.g., "Expose GET /api/v1/users...").

4. Verification

  • The "Rebuild Test": Ask yourself: "If I gave this file to a stranger, could they build the exact same app without seeing the code?"
  • Ensure no hidden features (middleware, schedulers) are missed.

5. Final Output

  • Save the file to features_listed.md in the project root.

Advanced Feature Extraction (Recreation Standards)

When extracting features, ensure you also capture the underlying mechanics:

  • Domain Modeling: Extract the core data entities and their relationships (e.g., "User has many Orders, Order has many Items").
  • Third-Party Dependencies: Explicitly call out if a feature relies on an external API or specific SDK (e.g., "Payment processing via Stripe API").
  • State Management: Note how global state or complex UI states are handled, as this drastically changes how the app is rebuilt.

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.