docs-anthropic
The docs-anthropic skill fetches and delivers official Claude Code documentation by matching user queries to the most relevant page from Anthropic's docs site. Use it when seeking guidance on skills authoring, lifecycle hooks, built-in tools, plugins, MCP channels, custom commands, or the interactive REPL environment. The skill searches a curated index of seven core topics and can fall back to a master index for discovering additional documentation pages.
git clone --depth 1 https://github.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas /tmp/docs-anthropic && cp -r /tmp/docs-anthropic/.claude/skills/docs-anthropic ~/.claude/skills/docs-anthropicSKILL.md
# Anthropic / Claude Code documentation index The curated set of official Claude Code docs to reach for, with what each one covers. All live under `https://code.claude.com/docs/en/`. | Topic | URL | What it covers | | :-- | :-- | :-- | | **skills** | https://code.claude.com/docs/en/skills | Authoring Agent Skills: `SKILL.md` format and frontmatter, progressive disclosure (description always in context, body on invoke), `disable-model-invocation` / `user-invocable`, supporting files, `context: fork`, packaging. | | **hooks** | https://code.claude.com/docs/en/hooks | Lifecycle hooks — `PreToolUse`, `PostToolUse`, `UserPromptSubmit`, `PreCompact`, `SessionStart`, `Stop`, `SubagentStop`, `Notification` — their JSON stdin/stdout contract, exit codes, and `settings.json` wiring. **(`PreCompact` = the compact-hook event.)** | | **tools-reference** | https://code.claude.com/docs/en/tools-reference | Reference for the built-in tools (Bash, Read, Edit, Write, Glob, Grep, WebFetch, …) and how permissions gate them. | | **plugins-reference** | https://code.claude.com/docs/en/plugins-reference | Plugin structure: `plugin.json`, bundling commands / agents / skills / hooks / MCP servers, marketplace layout, skills-dir plugins. | | **channels-reference** | https://code.claude.com/docs/en/channels-reference | Building an MCP **channel** server that pushes webhooks, alerts, and chat into a session: capability declaration, notification events, reply tools, sender gating, permission relay. (Research preview.) | | **commands** | https://code.claude.com/docs/en/commands | Slash commands — built-ins plus custom commands in `.claude/commands/` (now merged into skills), frontmatter, `$ARGUMENTS`/`$N`, and `:`-namespacing (plugin-only). | | **interactive-mode** | https://code.claude.com/docs/en/interactive-mode | The interactive REPL: keyboard shortcuts, vim mode, multiline input, and session controls. | **Master index:** `https://code.claude.com/docs/en/llms.txt` — the full list of every docs page, for discovering anything not in the table above. ## How to use this skill Argument passed: **$ARGUMENTS** - **If a topic was given** (a keyword above, or something one of these docs would answer — e.g. `hooks`, `precompact`, `skill frontmatter`, `channels`, `slash command args`): pick the single best-matching URL, `WebFetch` it, and answer the question from the live page. Cite the URL. If nothing matches the seven, fetch the master `llms.txt` index, find the closest page, then fetch it. - **If the argument is blank:** present the table above as the index — no fetching. Offer to pull any specific page on request. Keep the verdict-open, no-overclaim floor: report what the docs actually say, and if a page has moved or 404s, say so plainly rather than reconstructing it from memory.
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
Code review a pull request
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Commit what is already staged — runs the commit subagent in the background, following the ATLAS commit convention.
Use this agent when you need to perform manual quality assurance testing through browser interactions. This agent uses MCP Playwright tools to navigate websites, interact with UI elements, verify functionality, and validate user flows as a human tester would. Perfect for testing new features, regression testing, validating bug fixes, or exploring application behavior. Examples:\n\n<example>\nContext: The user has just implemented a new login feature and wants to test it.\nuser: "I've added a new login form, can you test if it works correctly?"\nassistant: "I'll use the qa-manual-tester agent to test the login functionality through the browser."\n<commentary>\nSince the user needs manual testing of a new feature, use the Task tool to launch the qa-manual-tester agent to interact with the browser and verify the login flow.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to verify that a bug fix is working properly.\nuser: "I fixed the issue where the submit button wasn't working on mobile view. Can you verify?"\nassistant: "Let me launch the qa-manual-tester agent to verify the submit button works correctly in mobile view."\n<commentary>\nThe user needs manual verification of a bug fix, so use the qa-manual-tester agent to test the specific functionality through browser interaction.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to perform regression testing after code changes.\nuser: "I've refactored the checkout flow. Please test that everything still works."\nassistant: "I'll use the qa-manual-tester agent to perform comprehensive testing of the checkout flow."\n<commentary>\nSince the user needs regression testing after refactoring, use the qa-manual-tester agent to manually test the entire checkout flow.\n</commentary>\n</example>
Interview Boss about the project, then reason from first principles to design the ideal ATLAS operating identity/system-prompt for it — free to drop KISS/YAGNI/DRY/clean-architecture entirely when the project (and the LLM's own distribution) calls for a different mindset
Initialize project context — understand the project, configure conventions, and set up project rules