32 skills · updated 2026-09-14
Agent Skills for Claude Code and Codex
Reusable instructions that teach your coding agent how to review code, ship iOS and desktop apps, deploy to Cloudflare, and write clearly. Install the whole catalog with one command, or add only the skill you need.
npx skills add xingkaixin/skillsnpx skills add xingkaixin/skills --skill use-modern-goWorks with any agent that reads the open Agent Skills format. No config files to edit.
Browse skills by category
10 areas of everyday engineering and writing work. Each category page lists its skills with install commands.
- Backend and CLI skills5Build agent-friendly CLIs, choose a project stack, organize a monorepo, and write modern Go with reusable skills for Claude Code and Codex.
- Git commit and release skills2Write consistent Git commit messages and bilingual release notes. Install skills for Claude Code and Codex to prepare version changes and releases.
- Cloudflare deployment skills1Deploy to Cloudflare Pages or Workers and migrate from Vercel. Use an agent skill covering Wrangler configuration, secrets, storage, and deployment checks.
- UI and visual design skills3Improve layout, typography, color, and error messages. Apply a design system with Claude Code and Codex skills for clearer product interfaces.
- Electron and Tauri skills2Build Tauri menu bar agent apps and ship Electron releases. Browse agent skills for desktop integration, packaging, updates, and distribution.
- Stock research skills1Prepare source-backed company research and stock reports with an agent skill covering financial statements, valuation, risks, and report structure.
- React and frontend performance skills2Choose React state management and improve large-data frontend performance. Install Claude Code and Codex skills for state ownership and rendering decisions.
- iOS development and release skills3Build iOS audio recording, on-device vision and ML, and widgets. Use agent skills for Apple platform integration and App Store release preparation.
- Code review and planning skills6Review code, plan implementation, track issues, and write agent skills. Browse repeatable engineering workflows for Claude Code and Codex.
- Writing, translation and illustration skills7Edit natural prose, translate literature, structure stories, and create article illustrations. Install reusable writing skills for Claude Code and Codex.
All skills
Search by task, tool or platform. Every card links to the full SKILL.md and its install command.
32 skills
Layout, typography and color
visual-design-principles
Apply grouping, alignment, repetition, contrast, typography, and color to interfaces, posters, slides, and documents, then inspect and refine the actual result.
Updated 2026-09-14writingUpstream
Natural prose editing
ai-avoid
Edit prose to remove inflated vocabulary, formulaic contrasts, false suspense, and repetitive sentence rhythms while preserving meaning.
Updated 2026-09-11writingAdaptedArticle illustration prompts
article-illustrator
Find where an article needs illustrations and write image prompts by information type, visual style, and optional palette. Includes educational diagrams and black-ink visual notes.
Updated 2026-09-11writingAdaptedArticle cover image prompts
cover-image
Turn an article into a cover-image prompt with configurable type, palette, rendering, text, and mood. Choose from 11 palettes and 8 rendering styles, with color instructions kept out of visible image text.
Updated 2026-09-11backendOriginal
CLI design for AI agents
agent-friendly-cli-design
Design a CLI that AI agents can actually drive: resource and verb layering, non-interactive defaults, token-lean output, and errors that teach the agent how to retry.
Updated 2026-07-18ciOriginal
Bilingual release notes
bilingual-release-changelog
Ship a release with Chinese and English changelogs in sync — commit-range analysis, user-facing wording, version bumps per stack, and recovery when a release half-fails.
Updated 2026-07-18deployOriginal
Cloudflare deployment and migration
cloudflare-deploy-migration
Move a site onto Cloudflare — static to Pages, Next.js via vinext, full-stack to Workers with D1 and KV — with the wrangler config splits and pitfalls mapped out.
Updated 2026-07-18workflowOriginal
Code review checklist
code-review-checklist
Review a diff in layers — design first, then call sites, then naming, then actually run it — and know what to skip and how to phrase the hard feedback.
Updated 2026-07-18workflowOriginalCodebase audit workflow
codebase-review-loop
Audit a codebase through numbered improvement proposals: evidence-backed findings, a read-only recheck before fixing, one fix at a time, status written back.
Updated 2026-07-18backendOriginalCoding agent session formats
coding-agent-session-formats
Parse local session files from Codex, Claude Code, Kimi, OpenCode, and Pi — storage paths, message schemas, a unified export shape, and cache-aware cost math.
Updated 2026-07-18workflowOriginalImplementation planning
decision-complete-plan
Write an implementation plan another agent can execute without asking anything: explore before you ask, separate facts from preferences, state every assumption.
Updated 2026-07-18designOriginalUI from a design system
design-system-as-input-ui
Stop AI-generated screens from each inventing their own blue. Feed the agent a design system as a token contract instead of describing pixels every time.
Updated 2026-07-18desktopOriginal
Electron app releases
electron-desktop-release
Package, sign, and notarize an Electron app for distribution outside the store, and keep its secrets somewhere that is actually a secret store.
Updated 2026-07-18writingOriginalEnglish to Chinese literary translation
en-zh-literary-translation
Translate English prose into Chinese that reads as if it were written in Chinese, using the faithful/fluent/elegant framework and concrete rules for killing translationese.
Updated 2026-07-18designOriginalActionable error messages
error-message-writing
Write error messages that answer what happened, why, and how to fix it — with four anti-patterns to avoid and a nine-point check for each message.
Updated 2026-07-18frontendOriginal
Frontend performance for large datasets
frontend-large-data-performance
Make a frontend survive 50-300MB files and streaming data, with benchmark-driven fixes for quadratic batching, full re-derivation, and virtual-list conflicts.
Updated 2026-07-18ciOriginalGit commit messages
git-commit-message
Write commit messages that carry the why a diff cannot: the seven-rule convention, with a good and a bad example for each.
Updated 2026-07-18iosOriginal
On-device vision and ML for iOS
ios-on-device-vision-ml
Build on-device visual recognition on iOS: viewfinder crop geometry, Vision foreground segmentation, classification and color, and evaluating models on synthetic data.
Updated 2026-07-18iosOriginaliOS audio recording integration
ios-recording-system-integration
Wire iOS recording into Live Activities, the Action Button, and background audio, starting from the four hard platform limits that shape the whole design.
Updated 2026-07-18iosOriginaliOS widgets and App Store releases
ios-widget-appstore-shipping
Ship a WidgetKit extension and get the app through review: App Group data sharing, refresh pitfalls, encryption declarations, and real rejection post-mortems.
Updated 2026-07-18workflowOriginalIssue-driven development
issue-driven-dev-loop
Work a backlog end to end: pick up an issue, settle the design, implement, open the PR, update status after merge, move to the next.
Updated 2026-07-18workflowOriginalMarkdown issue tracking
issue-tracker
Track issues in Markdown inside the repo itself — milestones, status lanes, PR links, and an HTML board — with no Linear or GitHub Issues involved.
Updated 2026-07-18backendOriginalMonorepo architecture
monorepo-architecture-principles
Organize a monorepo that stays organized: a one-way dependency graph over apps and packages, ten recurring principles, and the anti-patterns worth naming.
Updated 2026-07-18frontendOriginalReact state management
react-state-management-decisions
Decide where each piece of React state belongs — useState, useRef, useMemo, Context, Zustand, or React Query — from a decision tree instead of habit.
Updated 2026-07-18desktopOriginalTauri menu bar agent apps
tauri-menubar-agent-app
Build a macOS menu-bar app in Tauri v2 that watches external coding agents: native window layering through objc2, Unix-socket hook bridges, event normalization.
Updated 2026-07-18backendOriginalProject stack scaffolding
tech-stack-scaffolding
Bootstrap a new project on house conventions across four stacks — web, browser extension, Python CLI, Go CLI — with drop-in configs and script naming.
Updated 2026-07-18writingOriginalStructured deep reading
triple-mind-deep-reading
Read a long article or talk through three deliberate lenses — Challenger, Builder, Practitioner — instead of flattening it into a summary.
Updated 2026-07-18workflowOriginalWriting agent skills
writing-agent-skills
Build an agent skill that actually triggers and delivers: pick the type, write directive instructions, engineer the description as a routing contract, then eval it.
Updated 2026-07-18writingOriginalSave the Cat story structure
save-the-cat-writing
A Save the Cat checklist for tech writing: sharpen the topic, test the headline, rescue a flat opening, and cut hard before publishing.
Updated 2026-04-24writingOriginalChinese article writing
klip-writing
Write a KLIP: a structured technical design document that carries one decision from background and motivation all the way to acceptance criteria.
Updated 2026-04-21backendOriginalModern Go development
use-modern-go
Write Go that matches the version the project actually targets, reaching for slices, maps, and cmp instead of the legacy patterns they replaced.
Updated 2026-03-12financeOriginal
Stock research reports
stock-report
Generate a fixed-format HTML report for a single A-share stock through this repository's ds CLI data pipeline.
Updated 2026-03-11No skill matches this search. Try a broader word or another category.
How agent skills work
- 01
Install once
One command adds every skill, or a single one, to the coding agent on your machine.
- 02
Loaded only when relevant
The agent reads each skill's short description and opens the full instructions only when your task matches.
- 03
Same steps every time
A review, a release or a migration follows a written procedure instead of whatever the model improvises that day.
Frequently asked questions
Something missing? Open an issue on GitHub
What is an agent skill?
A folder with a SKILL.md file: a short description that tells the agent when to use it, followed by step-by-step instructions and references. Claude Code, Codex and other compatible agents load a skill only when the task calls for it.
How do I install every skill?
Run npx skills add xingkaixin/skills in your terminal. It installs the full catalog into your coding agent. No further configuration is needed.
How do I install a single skill?
Add --skill with the skill's slug, for example npx skills add xingkaixin/skills --skill use-modern-go. Installing only what you need keeps the agent's context small.
Which AI coding tools are supported?
Claude Code and Codex, plus any agent that reads the open Agent Skills format. The skills are plain Markdown, so they carry over between compatible tools.
Some skills are written in Chinese. Do they still work?
Yes. The agent follows the instructions regardless of their language and replies in yours. Each skill page notes the language its SKILL.md is written in.