Lingchu Bot documentation is now live — check it out!
Lingchu Bot

Agent Skills

Agent Skills

The project ships a set of skills — structured prompts loaded on demand by AI coding agents (Trae, Codex, Claude Code). Skills turn common workflows into repeatable, disciplined processes. They live in .agents/skills/ and are indexed by .agents/skills/available-skills/SKILL.md.

Skills are not injected into every conversation. They are loaded only when the user's task matches the skill trigger. This keeps context lean while making specialized workflows available when needed.

Skill categories

Development Workflow

Debugging, TDD, code review, issue planning, and design prototyping

Code Intelligence

Architecture exploration, impact analysis, safe refactoring, and PR review

Frontend Quality

React diagnostics, visual polish, accessibility, and health checks

Documentation Lookup

Up-to-date library and framework documentation via Context7

Project-local skills

These skills are stored in .agents/skills/ and tailored to this project's conventions and tooling.

delivery-loop

Disciplined implementation loops for debugging, test-driven development, and code review validation.

RouteWhen to use
debug-investigationBugs, crashes, flaky behavior, performance problems
tddTest-first development, red-green-refactor cycles
change-reviewCode review of diffs, branches, or PRs

Key principle: Build a reliable feedback loop before changing code. Reproduce the problem, localize the cause, make the smallest fix, and prove the regression is covered.

TDD anti-pattern

Do not write all tests first and then all implementation (horizontal slicing). Instead, use vertical slices: write one failing test, implement to pass, then repeat. This produces tests that verify actual behavior, not imagined behavior.

frontend-quality

React/frontend UI quality for the docs site (apps/docs), including responsive behavior, visual consistency, accessibility, and architecture health.

RouteWhen to use
react-doctorReact diagnostics, lint, accessibility, bundle, architecture scan
frontend-polishVisual polish, responsive states, layout consistency
# Run React Doctor on changed files
npx react-doctor@latest --verbose --diff

# Run a full scan
npx react-doctor@latest --verbose

The project has a 🩺-react-doctor.yml CI workflow that runs on PRs. Local scores should not regress before committing.

issue-planning

Turn conversation, bugs, and plans into trackable work on GitHub Issues.

RouteWhen to use
to-prdWrite a PRD from conversation context
to-issuesBreak a plan into vertical-slice issues
triageMove issues through triage states
request-refactor-planCreate a detailed refactor plan with tiny commits

Key principle: Issues should be independently grabbable vertical slices, not horizontal layers. Each slice delivers a narrow but complete path through all integration layers.

design-prototyping

Explore and harden product, API, UI, or architecture designs before committing to implementation.

RouteWhen to use
design-an-interfaceGenerate multiple radically different interface designs, then compare
design-grillInterrogate a plan through focused questions until the next move is clear
prototypeBuild a throwaway prototype to answer a specific design question

Key principle: Your first design is unlikely to be the best. Generate 3+ radically different approaches, compare them, then synthesize. Prototypes are throwaway — the answer is the only thing worth keeping.

Code intelligence skills (GitNexus)

GitNexus provides code intelligence through a knowledge graph. See GitNexus Workflow for the full guide.

SkillPurpose
gitnexus-exploringUnderstand architecture and execution flows
gitnexus-impact-analysisAssess blast radius before changing symbols
gitnexus-debuggingTrace errors and unexpected behavior
gitnexus-refactoringRename, extract, split, or move code safely
gitnexus-pr-reviewReview pull requests with graph-aware analysis
gitnexus-cliRun GitNexus CLI commands
gitnexus-guideReference for tools, resources, and schema

Other skills

SkillPurpose
prekSet up or run Git hook checks with prek
context7-mcpLook up current library/framework documentation

Platform skills (routing-only)

These skills are loaded from the Codex platform at runtime. They have no local SKILL.md file.

SkillPurpose
GitHubRepository, issue, PR, review-comment, CI, and publish workflows
Browser / Playwright / ChromeIn-app browser checks, terminal automation, Chrome state
VercelNext.js, React, shadcn/ui, AI SDK, deployments, storage
CloudflareWorkers, Wrangler, Durable Objects, Agents SDK
Documents / Presentations / Spreadsheets / PDFOffice document creation and editing
imagegenRaster image generation or edits
skill-creator / skill-installer / plugin-creatorSkill and plugin authoring

How skills are loaded

  1. The description field from each SKILL.md frontmatter is listed in the agent's available skills.
  2. When the user's task matches a skill trigger, the agent loads the full SKILL.md.
  3. The SKILL.md routes to specific reference files in references/ for detailed workflows.
  4. Reference files contain the actual step-by-step instructions.

Only AGENTS.md (or CLAUDE.md for Claude Code) and .trae/rules/git-commit-message.md are injected into every conversation. Everything else loads on demand.

Adding a new skill

Use the skill-creator skill to create or update skills. A skill folder must contain:

  • SKILL.md — frontmatter with name and description, plus routing instructions
  • references/ — optional detailed guides loaded on demand

After creating a skill, update the routing index in .agents/skills/available-skills/SKILL.md and the skill tables in AGENTS.md / CLAUDE.md / .github/note/AGENTS-zh.md.

Last updated on

On this page