Forge

Use when a user wants help turning a vague idea, messy workspace, existing project, small tool, MVP, docs task, AI-assisted task, review, handoff, or release into a real usable result with AI agents. Forge is a project-manager skill for ordinary people: clarify ideas, scope MVPs, plan work, create bounded current-agent tasks, verify results, write docs, and prepare handoff or release. Safe Work Order is the default execution unit for AI tasks, not the whole product.

9 starsWriting & Content

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add JYSimilar/Forge --skill forge

Manual install

git clone --depth 1 https://github.com/JYSimilar/Forge.git /tmp/Forge
mkdir -p ~/.claude/skills
cp -r /tmp/Forge/. ~/.claude/skills/forge

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Forge

Forge is a project-manager skill that helps ordinary people turn vague ideas, messy workspaces, and AI-assisted tasks into real, usable, shippable progress.

Safe Work Order is Forge's default execution unit: clear goal, context budget, limits, acceptance checks, verification evidence, stop condition, and review gate.

Default: **Token Saver**. Choose the smallest route, load fewer references, answer, and verify before calling work done. Do not explain routing unless useful.

## Token Policy

- **Token Saver** is default: direct output, minimal ceremony, one verification or next step.
- **Standard Deep** is for broad, risky, architectural, multi-step, or ambiguous tasks.
- **Burn Mode** is explicit and one-shot: `Forge: 燃烧模式`, `Forge: Burn Mode`, or `Forge: 燃烧 token`.
- "详细一点" or "展开说说" means Standard Deep, not Burn Mode.
- Burn Mode expands useful visible artifacts, never private chain-of-thought or filler, and keeps the same quality bar.

Read `references/token-policy.md` only for token behavior questions, Burn Mode, or complex output contracts.

## Smart Activation

Do not require `Forge:`. Apply Forge silently when requests are project-shaped:

- "我想做...", "能不能做...", "怎么开始", "下一步", "这个想法怎么样" -> route, clarify blockers, scope next step.
- "有没有现成方案", "参考一下", "别人怎么做" -> Reference Scout.
- "给别人用", "普通人能跑", "写 README/Quick Start" -> Docs/Compatibility/Handoff.
- "接手这个工程", "当前工作区有什么", "先自查", "列一个 md 汇总" -> Existing Project Audit.

Read the full skill on GitHub

Details

Skill name: forge
Repository: JYSimilar/Forge
License: MIT
Repo updated: 14 July 2026

FAQ

What does the Forge skill do?

How do I install the Forge skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add JYSimilar/Forge --skill forge. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Forge popular?

It lives in JYSimilar/Forge, which has 9 GitHub stars and 0 forks.

Related skills

Genpark Content Factory

alphaparkinc/openclaw-genpark-content-factory

High-volume bulk social media graphic and post generator.

Writing & Content

Deutsch Loop

ahmtsahin/deutsch-loop

Coach German writing and conversation with minimal corrections, persistent root-cause mistake tracking (FehlerDNA), mistake-based spaced repetition with a new sentence every time, roleplay whose words return in spaced reviews, continuing preparation for real-life goals across sessions, and an honest progress profile. Use for German correction, personalized review, vocabulary, progress, roleplay, or preparation for an interview, presentation, appointment, or other concrete event; do not use for translation-only requests without learning or feedback.

Writing & Content

Wechat Article Down

zyw-Wayne/wechat-article-down

Download WeChat public account articles (微信公众号文章下载). Use when the user provides one or more WeChat article URLs (https://mp.weixin.qq.com/...) and wants to download the full content including body text, images, audio, and video to local files. Triggers include "下载微信文章", "保存公众号文章", "下载这篇文章", "wechat article download", or any request to save/archive a WeChat article.

Writing & Content

Dan Koe Validator

antoinersx/dan-koe-validator

Validates and edits articles to match Dan Koe's writing style. Use when reviewing content for Koe-style voice, structure, or philosophy alignment. Triggers on requests to "validate article," "edit in Dan Koe style," "check if this sounds like Koe," "review my newsletter," or any content review against the Koe framework.

Writing & Content

X Social Manager

rabden/X-twitter-social-manager-skill

Personal X/Twitter social media manager. Use when the user asks to craft, write, review, or optimize X/Twitter posts, threads, replies, or DMs. Also use when the user wants content strategy advice, engagement analysis, profile optimization, audience growth tactics, post scheduling guidance, or wants to brainstorm content ideas. Triggers on mentions of "post", "tweet", "thread", "X", "Twitter", "content", "engagement", "followers", "growth", "reply strategy", "social media", "brand", or "DM outreach". Includes browser-based X account analysis, pre-post research pipeline, evolving memory system,

Writing & Content

Better Readme

Thomaszhou22/better-readme

Use when the user asks to create, improve, fix, or audit a README.md file, score their README, document an open source project, or set up new project docs. Provides 8-dimension 0-100 quality scoring, 5-type template matrix (Library, CLI, App, Skill, Data), and pre-publish checklist. Do NOT use for API docs, wikis, inline code comments, or general technical writing.

Writing & Content

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.