Spec Forge
Professional specification system for Codex. Use when the user asks to create, improve, review, audit, analyze, or propagate product/software documentation, including requirements documents to hand to an implementation team or vendor, SRS/functional/non-functional requirements, PRDs and business cases, ideas, technical designs, architecture/RFC docs, feature specs, test cases, documentation audits, document landscape analysis, and full idea-to-spec chains. The chain's spine is a delivery-grade requirements spec followed by a technical design, handed off to code-forge for implementation: [idea]
Install
npx skills add tercel/spec-forge --skill spec-forgegit clone --depth 1 https://github.com/tercel/spec-forge.git /tmp/spec-forge
mkdir -p ~/.claude/skills
cp -r /tmp/spec-forge/. ~/.claude/skills/spec-forgePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Spec-Forge Orchestrator Spec-forge is a documentation and specification workflow suite. This root skill is the Codex-facing orchestrator: decide which child skill to load, keep the document chain coherent, and avoid loading large generation references until they are needed. ## Trigger Patterns Use this skill when the user asks for any of the following: - Start or refine an idea before specs: use `skills/idea/SKILL.md` - Split a large project into sub-features: use `skills/decompose/SKILL.md` - Write a PRD, business case, or product definition — "is this worth building": use `skills/prd-generation/SKILL.md` - Write the requirements a team will be held to — a requirements spec, an SRS, functional/non-functional requirements, **a requirements document to hand to an implementation team or vendor**: use `skills/srs-generation/SKILL.md` - Write a technical design, architecture doc, design doc, or RFC: use `skills/tech-design-generation/SKILL.md` - Generate test cases, QA coverage, or a test case matrix: use `skills/test-cases-generation/SKILL.md` - Review spec-forge documents for quality and consistency: use `skills/review/SKILL.md` - Audit project docs against code: use `skills/audit/SKILL.md` - Analyze a document ecosystem for themes, conflicts, gaps, redundancy, or staleness: use `skills/analyze/SKILL.md` - Propagate an upstream doc change downstream: use `skills/propagate/SKILL.md`
Details
- Skill name
spec-forge- Repository
- tercel/spec-forge
- License
- MIT
- Repo updated
- 16 September 2026
FAQ
What does the Spec Forge skill do?
Professional specification system for Codex. Use when the user asks to create, improve, review, audit, analyze, or propagate product/software documentation, including requirements documents to hand to an implementation team or vendor, SRS/functional/non-functional requirements, PRDs and business cases, ideas, technical designs, architecture/RFC docs, feature specs, test cases, documentation audits, document landscape analysis, and full idea-to-spec chains. The chain's spine is a delivery-grade requirements spec followed by a technical design, handed off to code-forge for implementation: [idea]
How do I install the Spec Forge skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add tercel/spec-forge --skill spec-forge. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Spec Forge popular?
It lives in tercel/spec-forge, which has 10 GitHub stars and 0 forks.
Related skills
Typst
8akilrammohan/typst-skill
Write and create Typst documents (.typ files). Use when the user asks to create, write, edit, or convert documents to Typst format, write Typst markup, create academic papers, reports, or documents in Typst, convert LaTeX to Typst, or work with .typ files. Typst is a modern markup-based typesetting system alternative to LaTeX.
Human Writing
10w93139/human-writing
通用中文创作与改稿 Skill。用于知乎回答、论坛长帖、公众号文章、博客、评论、人物故事、历史叙事、新闻与行业解读、产品分析、科普、教程、评测、个人叙事、小说、故事、对白、口播和演讲稿。用户没有选题、材料或明确主旨时,先主动提供思考入口,与用户多轮澄清并共同确定主旨,再研究材料、确定选题和框架,不急着交稿。已有明确任务时,默认写成一个见过事、查过材料、愿意把来龙去脉讲清楚的人在说话,重点保留中文互联网长回答与长帖的活人感和自然中文韵律,避免空泛的机构腔、喊口号式演说腔、营销腔和模型腔。非虚构长文先检查材料够不够,材料不足时研究、追问或缩短,绝不用重复解释灌字数。现实内容额外核验事实、引语、数据与用户亲历;产品与行业观点稿在成稿前还会绑定关键论点与证据,并用最强反方压力测试暂定主旨。虚构内容可以创造人物、场景、对白、心理与情节。成稿正文严禁冒号、破折号、“不是……而是……”及同类翻案句,并清除商业黑话和模型惯用黑话。用户明确开启持续风格迭代时,可以在独立作者档案中记录经其确认的长期偏好;不根据一次换词或聊天口气静默学习,不自动修改本 Skill。
Better Readme
9Thomaszhou22/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.
Elegant Flirt Persona
8zhangzhanglaila/charm-mature-skill
Persona and response-style guidance for tasteful, adult, consensual, non-explicit Chinese flirtatious roleplay in a mature "御姐" tone. Use when the user asks for elegant teasing, romantic banter, charm coaching, attraction-oriented dialogue, or text rewritten with mature feminine allure. Keep responses non-explicit, non-coercive, adult-only, and avoid sexual acts, nudity, body-part descriptions, minors, pressure, or vulgar content.
Dan Koe Validator
9antoinersx/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.
Craft Names
10krzyzanowskim/craft-names-skill
Craft and evaluate names and interface text for an app or product: features, settings, buttons, menu items, tabs, plans, labels, error messages, empty states, and onboarding copy. Use when the user asks "what should I call this?", wants to brainstorm or compare name candidates, asks for a review of UI copy, labels, or microcopy, or is writing anything users read in an interface. Distilled from Apple's WWDC session "Craft clear names for features and labels in your app" and the Human Interface Guidelines on Writing: three criteria (belongs, sets expectations, works everywhere), a Think/Feel/Do
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.