ccbot

Two-layer memory system — read and update long-term facts, recall past events from conversation history.

Browser automation via Playwright MCP — navigate, click, fill forms, take screenshots, scrape pages, run E2E tests. Use when the user needs web automation, testing, or scraping JavaScript-rendered sites.

Structured code review — security, correctness, performance, maintainability. Use when asked to review code, a PR, or a diff.

Analyze CSV, JSON, Excel data; generate charts and reports. Use when the user provides data files or asks for statistics, charts, or data insights.

Deploy applications to cloud platforms — Fly.io, Railway, Vercel, or via SSH. Use when the user wants to publish, deploy, or release an application.

Build, run, and manage Docker containers and images. Use when the user asks about containers, Docker builds, logs, or deployment.

Interact with Feishu (Lark) API directly — read/write docs, send messages, manage bitable, query user info. Use when the user wants to automate Feishu operations.

Advanced git operations — bisect, worktree, stash, cherry-pick, rebase, submodules, and more. Use for complex git workflows beyond basic add/commit/push.

Make HTTP requests, test REST APIs, handle auth, inspect responses. Use when the user wants to call an API, test an endpoint, or fetch web data.

Resize, convert, compress, crop, annotate images and process video/audio. Use when working with image files or when output needs to be an image.

Read, extract text from, merge, split, or create PDF files. Use when the user provides a PDF path or URL, or wants to produce a PDF output.

Query and manage SQLite, PostgreSQL, and MySQL databases. Use when the user wants to query data, inspect schemas, or run database operations.

Search the web for real-time information using multiple free services. Use when the user asks about current events, facts, documentation, or anything requiring live data.

Update repository documentation so README, architecture docs, runtime docs, and troubleshooting guides stay aligned with the actual implementation.

Review an existing repository for architecture issues, runtime risks, testing gaps, and code quality regressions. Use when asked to review, audit, harden, or check whether the current implementation is stable.

Operate and regression-test a local ccbot runtime through CLI, including worker control, memory commands, schedule commands, and observability checks.

Create and manage recurring scheduled jobs in ccbot.

Search and install agent skills from ClawHub, the public skill registry.

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Two-layer memory system with grep-based recall.

Summarize or extract text/transcripts from URLs, podcasts, and local files.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Get current weather and forecasts (no API key required).