agentleFS
Sign inStart free
jord0-cmdjord0-cmd/jord0.skills/skills/FORGE/SKILL.md

FORGE

Skill1 starsChanged 8 months agoMITView on GitHub

Project onboarding and CLAUDE.md generation. Use when: starting work on a new codebase, setting up a project for the first time, creating or updating a project CLAUDE.md, generating module summaries, or when opening a project with no CLAUDE.md file. Forges a complete project knowledge base so Claude understands the codebase from day one.

  • Reads credentials

We split this skill into the rules it gives an agent

12 rules. 0 are common, 8 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When this skill is invoked:

    line 71
  2. Very specific:

    Read package.json, pyproject.toml, Cargo.toml, or equivalent

    line 76
  3. Distinctive:

    Read README.md if present

    line 77
  4. Very specific:

    Check for .env.example or .env.template

    line 78
  5. Distinctive:

    Read key entry points (main files, index files, app files)

    line 81
  6. Distinctive:

    Look for common patterns (routes/, controllers/, models/, services/)

    line 89
  7. Distinctive:

    After major refactoring that changed project structure

    line 101
  8. Distinctive:

    When Claude says "I'm not sure about the architecture"

    line 102
  9. Distinctive:

    If a CLAUDE.md exists, FORGE reads it and offers to update (not replace)

    line 109
  10. Distinctive:

    No external packages required

    line 118
  11. Very specific:

    Run /forge check periodically to verify the CLAUDE.md is still accurate

    line 138
  12. Very specific:

    After major changes, run /forge update instead of a full re-forge

    line 139

“Common” is measured: kept by at least 6 in 10 of the 66 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

FORGE

Onboard any project. Generate a CLAUDE.md. Make Claude understand your codebase.

Usage

/forge                  - Forge the current project (auto-detect)
/forge <path>           - Forge a specific project directory
/forge update           - Update an existing project's CLAUDE.md
/forge check            - Verify project knowledge completeness

What FORGE Does

FORGE performs a deep scan of a codebase and generates a comprehensive CLAUDE.md file that gives Claude full context about the project. It's the difference between Claude guessing at your architecture and Claude knowing it.

The Forging Process

  1. Detect project type — language, framework, build tools, package manager
  2. Scan directory structure — map the project layout, identify key directories
  3. Read configuration files — package.json, pyproject.toml, Cargo.toml, tsconfig.json, etc.
  4. Analyze entry points — find main files, API routes, CLI entry points
  5. Map dependencies — external packages, internal module relationships
  6. Identify patterns — architecture style (MVC, hexagonal, etc.), testing approach, CI/CD
  7. Generate CLAUDE.md — structured project context file

What Gets Generated

# Project Name

## Overview
Brief description, purpose, key technologies.

## Architecture
Directory structure, key patterns, data flow.

## Key Files
Entry points, configuration, critical modules.

## Development
How to install, run, test, build, deploy.

## Conventions
Naming, file organization, coding patterns used.

## Important Context
Things Claude should know that aren't obvious from code.

AUTO-EXECUTE Protocol

When this skill is invoked:

  1. Check for existing CLAUDE.md — if present, read it first
  2. Scan the project root:
    • ls the top-level directory
    • Read package.json, pyproject.toml, Cargo.toml, or equivalent
    • Read README.md if present
    • Check for .env.example or .env.template
  3. Scan source directories:
    • Glob for source files (**/*.py, **/*.ts, **/*.rs, etc.)
    • Read key entry points (main files, index files, app files)
    • Identify test directories and patterns
  4. Scan configuration:
    • Build tools (webpack, vite, esbuild, cargo)
    • Linting (eslint, ruff, clippy)
    • CI/CD (GitHub Actions, GitLab CI)
    • Docker/containerization
  5. Detect architecture patterns:
    • Look for common patterns (routes/, controllers/, models/, services/)
    • Identify state management, API patterns, database layers
  6. Generate CLAUDE.md — write to project root
  7. Report findings — summarize what was discovered

When to Use

  • Opening a project for the first time
  • Joining a new team or codebase
  • A project has no CLAUDE.md and Claude keeps making wrong assumptions
  • After major refactoring that changed project structure
  • When Claude says "I'm not sure about the architecture"

Safety

  • FORGE will never overwrite an existing CLAUDE.md without asking first
  • If a CLAUDE.md exists, FORGE reads it and offers to update (not replace)
  • FORGE only reads files — it does not execute any code from the project

Prerequisites

  • Claude Code with file read/write access
  • A project directory with source code to scan
  • No external packages required

Quality Checklist

A properly forged CLAUDE.md should:

  • Accurately describe the project's purpose
  • List all major dependencies and their roles
  • Map the directory structure with explanations
  • Document how to install, run, test, and build
  • Identify naming conventions and coding patterns
  • Note any non-obvious architecture decisions
  • Be concise enough to fit in context without waste

Tips

  • Run /forge check periodically to verify the CLAUDE.md is still accurate
  • After major changes, run /forge update instead of a full re-forge
  • FORGE reads your code — it doesn't execute it. Safe to run on any project.
  • The generated CLAUDE.md is a starting point. Edit it to add context only you know.

Know the codebase. Then write the code.

Download now (ZIP)

  • Other versions77 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 77

    1. cwinvestments/memstack★ 425same name
    2. ansari-project/codev★ 289same name
    3. cluesmith/codev★ 289same name
    4. swyxio/skills★ 189same name
    5. simota/agent-skills★ 96same name
    6. alp82/forge★ 36same name
    7. TT-Wang/forge★ 34same name
    8. emiliosheinz/agent-skills★ 20same name
    9. MetalLegBob/solana-vibes-kit★ 19same name
    10. kecoma1/MQL5-SKILLS★ 17same name

    67 more not listed

    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.

  • Used alongsideProjects with it also use forge-review, forge-ship and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • tonmoy007Skill

      forge-review

      Run a multi-dimensional parallel code review over the current change.

      Also in 7 projects that use this

    • redteamlifeSkill

      forge-ship

      Use when the user asks to merge, release, promote, reconcile, or close out work in a repo containing `docs/forge/` or governed by FORGE. Not for per-task commits; those complete inside forge-execute-task.

      Also in 5 projects that use this

    • DailenGSkill

      forge-design

      Design, UX, and polish discipline for the forge lifecycle. Covers the design tier, the design brief in docs/DESIGN.md, UX requirements and their verification methods, the per-slice design pass, the UX defect register, and the release polish pass. Load whenever work touches a user-facing surface (GUI, terminal, library API, or operated service), whenever a UX observation needs disposing of, and whenever a release is in reach.

      Also in 3 projects that use this

    • weselbenSkill

      forge-docs

      Load before code changes, before writing docs or an ADR, when a user question exposes a missing how-to, and when closing a chunk of work; also loaded by forge after each squash-merge and by deep-research after a report.

      Also in 3 projects that use this

    • DshamirSkill

      forge-plan

      Takes analysis.json + budget cap → derives the full phase sequence, hyperparameters, instance type, cost estimate, and acceptance thresholds. Emits plan.md (the single human gate document) and plan.json (the machine-readable spec that dispatch-v2 consumes). Refuses to plan if estimated cost exceeds budget×1.2.

      Also in 3 projects that use this

    • AnthropicSkill

      brief

      Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.

      Also in 3 projects that use this

  • In this repository13 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.

Check your setup, free