listing near-synonymous phrasings, and keep behavioral instructions in the body.
### Reference files
Markdown documents in `references/` containing detailed API references, code templates, formulas, or schema docs. The SKILL.md instructions
verbose format)
plugins/awesome-chatgpt-search/ ← one plugin directory for both Claude Code and Codex
README.md ← plugin documentation
build_data.py ← regenerates data/ from the main JSON
.claude-plugin/plugin.json ← Claude Code plugin manifest
.codex
server on STDIO
fli-mcp-http # Run MCP server over HTTP
# Documentation
make docs # Build MkDocs documentation
uv run mkdocs serve # Serve docs locally
uv run mkdocs build # Build static
under `docs/`, load `.claude/skills/docs/SKILL.md` and follow it. Do not write docs without it. See **Documentation** below for TanStack-specific rules that also apply.
**PR description skill (mandatory).** Before
Auto Company - Autonomous AI Company
[English](CLAUDE.md) | [中文](i18n/zh-CN/CLAUDE.md) · [Documentation and language settings](i18n/README.md)
## Mission
**Make money legally.** Find real demand, build valuable products, deploy, and generate revenue. This
Inclua contexto do erro em mensagens ao usuário
- Sugira procedimentos de rollback quando apropriado
- Documente quaisquer correções manuais necessárias
---
## Comandos Frequentes
### Desenvolvimento
```bash
npm run dev # Iniciar desenvolvimento
npm test
Senior Agent Architect and QA Analyst.
Objective: Update the OPTIMIZATION_LOG.md to document whether the applied strategy worked.
Inputs:
1. Strategy Applied: [e.g., "Iteration 1: Tool Hardening"]
2. New Evaluation Data
improving interface polish, published for installation via `npx skills add jakubkrehel/make-interfaces-feel-better`. It is documentation-only; there is no build, lint, or test tooling.
## Structure
The skill lives in `skills/make-interfaces-feel-better/`:
- `SKILL.md
Data Transfer Vouchers, Human Profiles.
### Mandates & Tasks
A **mandate** is an owner-signed authorization document that grants a device permission to perform a task within defined bounds:
- `taskIntent` — what task
provider (`@ax-llm/ax-ai-sdk-provider`)
- `src/examples/` - Example implementations (`@ax-llm/ax-examples`)
- `website/` - Hugo documentation site (deployed to axllm.dev via GitHub Pages)
Each sub-repository under `src/` has its own `package.json
strict [`Agent Plugins v1 Portable Lite`](docs/agent-plugins-v1.md) projection
Do not preload every linked document. Start with this map, select the smallest route, then load the chosen Skill and only
with isolated `CLAUDE_CONFIG_DIR`.
All env values written into settings must be strings.
## Documentation Truth
Use the narrowest authoritative source:
1. Source, tests, package scripts, and workflows define implemented
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.