t4sh/skills4sh
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
Agent skills for Codex, Claude, Cursor, and other AI coding agents.
概要
Practical skills for developers and their agents: preserve project understanding, turn designs into code, verify interfaces, and maintain reusable workflows. Each skill is an Agent Skills folder. The core workflows are portable. Installation paths and host-specific capabilities are documented separately; each skill tells the agent when differences in tools, permissions, or instruction loading affect execution. Agent setups tend to grow by accretion: a CLAUDE.md here, a Cursor rule there, and "never push without asking" pasted into each. init-rulebook replaces that with one personal rulebook, a plain AGENTS.md index with optional rule files, kept wherever you like. Each host gets a short startup pointer; the skill does the loading. Try: “Set up my personal agent rulebook.” Then, in a fresh session: “init-rulebook: status.” Stable since 1.0.0: changes to its triggers or scope require a major version.
README
以下は原文 README の抜粋です。原文を見る。
skills4sh
Practical skills for developers and their agents: preserve project understanding, turn designs into code, verify interfaces, and maintain reusable workflows.
Each skill is an Agent Skills folder. The core workflows are portable. Installation paths and host-specific capabilities are documented separately; each skill tells the agent when differences in tools, permissions, or instruction loading affect execution.
Choose a skill
| Skill | What it helps you do | Version |
|---|---|---|
| agent-memory | Share project decisions, rationale, conventions, and handoffs across developers and agents through Git | 2.8.0 |
| code-to-figma | Build a CI pipeline that exports design tokens and page structure for a Figma plugin to consume | 0.3.0 |
| discord-harvest | Archive Discord images and attachments, and catalog shared links, using authorized bot access or supplied exports | 2.1.0 |
| eleventy-nunjucks | Build, debug, and review Eleventy sites and Nunjucks templates, with a separate Build Awesome prerelease migration guide | 1.0.0 |
| figma-to-code | Bring your repo’s tokens, components, and agent rules to Figma work; pairs with Figma’s official figma-design-to-code skill and implements designs itself when that skill is absent |
0.2.0 |
| init-rulebook ⭐ | Keep one personal rulebook that every agent loads: only the rules that apply, reloaded after compaction, with action gates read just in time | 1.0.0 |
| localhost-screenshots | Capture responsive screenshots and compare interface changes on a local development server | 3.5.0 |
| skill-architect | Create, review, and improve skills with clear triggers, reusable procedures, and meaningful verification | 1.1.0 |
Start here: init-rulebook
Write your rules once. Every agent loads the ones that apply, every session.
Agent setups tend to grow by accretion: a CLAUDE.md here, a Cursor rule there, and “never push without asking” pasted into each. init-rulebook replaces that with one personal rulebook, a plain AGENTS.md index with optional rule files, kept wherever you like. Each host gets a short startup pointer; the skill does the loading.
| What you get | How it works |
|---|---|
| One rulebook for every agent | Claude Code, Codex, Cursor, and other Agent Skills hosts point at the same index. Changing tools doesn’t mean rewriting your preferences. |
| Only the rules that apply | Rules are always on, task-conditional, or action-gated, using headings you choose. A documentation task loads your documentation rules; production rules stay unread until production work starts. |
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add t4sh/skills4sh