Overview
This is a comprehensive Jupyter notebook cookbook demonstrating Claude's Skills feature for document generation (Excel, PowerPoint, PDF). It's designed for developers learning to integrate Skills into their
pasted chat/review replies. (Doc comments on an exported API — TSDoc `@param`/`@returns`/`@deprecated` — are documentation, not narration, and are exempt.)
#### Surgical Changes
- Touch only what the task requires
Database contracts stay inside `/packages/data-schemas`.** A Mongoose type in an exported
signature — `FilterQuery`, `Types.ObjectId`, `Document`, `HydratedDocument` — makes the storage
engine part of that module's public API, and every consumer
create targeted CV (`cv/main_ _ .tex`) and cover letter (`cover_letters/cover_ _ .tex`)
4. **Verify both documents** (see Verification Checklist below)
5. Prepare interview talking points based on the role requirements
một repository tutorial về các tính năng của Claude Code. Đây là **documentation-as-code** — sản phẩm chính là các file markdown được tổ chức thành các module học tập
pacman@skills-dir` loads from `.claude/skills/` in the trusted `claude-code-templates` checkout. Anthropic documents only `claude --plugin-dir mods/ ` for its reference mods; the `.claude/skills` auto-load is Claude
legacy `container.json` files into the DB on startup |
| `src/project-doc-compose.ts` | Composes each group's project document — every instruction source read on the host and inlined into one flat file, no imports
container, and do not request real
tokens through chat or MCP environment settings. A documented placeholder may
satisfy a client's local authentication check; it is not a connected account
CLAUDE.md
Claude Code compatibility shim.
Use `docs/AGENTS.md` for documentation-site guidance. Docs-agent context lives in `docs/agent-guidance/`, and neutral decisions live in `docs/decisions
scoped to the session's objects; command-bearing params stay denied except
for the documented audited exception. The PR must analyze local command/content
execution, access to unowned objects and local
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.