> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wolffi.sh/llms.txt
> Use this file to discover all available pages before exploring further.
# Built-in Capabilities
> All 20+ capabilities that ship with Wolffish by default
# What Ships by Default
These capabilities are included in the default workspace when Wolffish creates `~/.wolffish/workspace/` on first launch. Each lives in its own folder under `brain/cerebellum/`.
**No artificial guardrails.** Wolffish is built for smarter, more capable models. We've removed hard-coded timeouts, result caps, and arbitrary limits from all capability plugins. The LLM decides when to set a timeout and how many results to request. Commands run until they finish naturally. The only limits that remain are OOM-protection caps (100MB for documents, 500MB for audio, 100KB output buffer) — these protect memory, not restrict functionality.
## Self-Management
Wolffish can read, manage, and **write its own capabilities** at runtime — no code change, no restart. This is the heart of what makes it extensible: a workflow you do often can become a permanent tool just by asking.
**Type:** Plugin
**Triggers:** skill, skills, capability, create a skill, new skill, teach yourself, add a tool, list skills, disable skill, enable skill, delete skill, what can you do, extend yourself
Lets Wolffish manage — and write — its own capabilities at runtime. It can list and search what it has, read a skill's source to learn the pattern, toggle skills on and off (built-ins included, e.g. "turn off the browser"), delete ones you created, and author brand-new skills from a request like "do this every time."
**Tools:**
* `skill_list` — List every skill: name, description, enabled/official status, tool count
* `skill_search` — Search skills by keyword across name, description, triggers, and tool names
* `skill_read_source` — Read a skill's SKILL.md and plugin code before amending it or learning from it
* `skill_enable` / `skill_disable` — Toggle any skill on or off (reversible; only the `skills` capability itself can't be disabled)
* `skill_delete` — Permanently remove a skill you created (official/built-in skills are protected)
* `skill_create` — Author a new pure skill or plugin capability from scratch
* `skill_reload` — Re-scan the workspace so changes take effect
Changes persist and take effect on the next turn. This is how Wolffish extends itself without a code change — see [Self-Authoring Skills](/capabilities/self-authoring-skills) for the full create → test → edit loop and a complete copy-paste example.
**Type:** Plugin
**Triggers:** automation, automations, automate, schedule, scheduled, heartbeat, cron, recurring, every morning, every day, daily, weekly, remind me, run automatically, from now on
Lets Wolffish manage its own [heartbeat](/configuration/heartbeat) — the jobs that run autonomously on a schedule. Ask for something recurring ("every morning…") or one-time ("in 2 days remind me…") and it writes, edits, or removes the job for you, applied live without a restart. It picks **one-time vs recurring** from how you phrase it; one-time jobs (`In (15m)` / `Once (2026-...)`) fire once and delete themselves.
**Tools:**
* `automation_list` — List every automation: schedule, plain-English timing, instruction, and whether it's valid/running
* `automation_create` — Create a job (recurring or one-time) from a schedule + instruction
* `automation_edit` — Change a job's schedule and/or instruction
* `automation_delete` — Permanently remove a job (asks you to confirm)
* `automation_check` — Runtime status: what's running now and how recent runs went
* `automation_run` — Run a job immediately, to test it
Heartbeat jobs run with tool calls **auto-approved**, so it confirms anything recurring or consequential with you before scheduling it. Memory compaction is configured separately in Settings, not here.
### Asking Wolffish to build a skill for itself
You don't write any code — you describe the ability in plain language and Wolffish authors the capability for you. The clearest requests signal a **recurring** need:
* *"From now on, whenever I send you a CSV, clean it up and reply with a summary table."*
* *"Make yourself a skill that posts a daily standup to our Slack channel."*
* *"You keep doing this resize-and-watermark dance by hand — turn it into a reusable tool."*
* *"Teach yourself to look up parcel tracking from a tracking number."*
When you ask, Wolffish:
1. **Picks the kind of skill** — a *pure skill* (a written procedure it follows with tools it already has), a *plugin skill* (a real new tool backed by JavaScript), or a plugin with npm dependencies — choosing the smallest that does the job.
2. **Writes the files** via `skill_create` — the `SKILL.md` (name, description, triggers) plus `plugin/index.mjs` and a `package.json` only when a real new tool is needed.
3. **Loads and tests it live**, then it's available from your next message — triggered automatically whenever your wording matches what the skill is for.
Be specific about the **trigger** ("whenever I…", "every time a…") and the **outcome** you want. Wolffish builds reusable skills, not one-offs — for a single task it just does the work directly instead of creating a skill. You can always say "list your skills" to see what it has, or "delete that skill" to remove one it made.
## Core System
**Type:** Plugin
**Triggers:** run, execute, command, terminal, shell, bash, npm, npx, git, pip, docker, curl
Wraps Node.js `child_process` to execute shell commands. The workhorse tool that many other capabilities depend on.
**Tools:**
* `shell_exec` — Run a command with optional cwd and timeout. Commands run until they exit naturally. Pass `timeout` only when you want fast failure (e.g. 5000ms for a quick `which` check). Omit for installs, builds, or anything with unpredictable duration.
**Safety:**
* **Block:** `mkfs`, `dd if=` (disk-level destruction)
* **Destructive:** `rm -rf`, `sudo` (requires approval)
* **Confirm:** package installs, docker operations
Background mode (`background: true`) detaches the process and returns its PID immediately — use for dev servers, watchers, and long-running processes.
**Type:** Plugin
**Triggers:** file, read, write, edit, create, save, open, patch, modify, folder, directory
Wraps Node.js `fs` for precise file operations without needing shell access.
**Tools:**
* `file_read` — Read file contents with optional line range (startLine/endLine)
* `file_write` — Create or overwrite a file (supports append mode)
* `file_patch` — Find and replace a literal string in a file (all occurrences)
Prefer these over `shell_exec` for file operations — they're faster, safer, and produce cleaner audit trails.
**Type:** Plugin
**Triggers:** install, package, brew, winget, apt, dependency
Detects and uses the system package manager: Homebrew (macOS), winget (Windows), apt (Debian/Ubuntu), dnf (Fedora/RHEL). Installs run until completion — no timeout.
**Tools:**
* `pkg_check` — Check which package manager is available
* `pkg_install_manager` — Install Homebrew on macOS if missing (no-op elsewhere)
* `pkg_install` — Install a package with platform-specific name resolution
Other capabilities declare their system dependencies via the `packages` field in SKILL.md — the package-manager resolves the correct name per platform.
**Type:** Plugin
**Triggers:** node, npm, npx, nvm, javascript, js, typescript, ts
Checks for Node.js installation and installs it via package-manager if missing. Install runs until complete.
**Tools:**
* `node_check` — Verify Node.js is installed and get version
* `node_install` — Install Node.js via system package manager
Once installed, use `shell_exec` for `node`, `npm`, and `npx` commands.
## Web & Search
**Type:** Plugin
**Triggers:** search, google, look up, find online, web, browse, latest, news, documentation
Provides web search and page fetching for current information.
**Tools:**
* `web_search` — Search the web, returns titles, snippets, and URLs. Defaults to 5 results, no upper limit enforced.
* `web_fetch` — Fetch full text content of a web page. No length floor — the LLM decides how much content to request.
Use `web_search` for discovery, then `web_fetch` to read specific results in detail. If a Brave API key is configured in Variables, the agent prefers the Brave search tool instead.
**Type:** Plugin
**Triggers:** browser, web, website, navigate, login, scrape, screenshot, form, click, automate
Launches a headless Chromium instance for interactive web tasks — filling forms, clicking buttons, navigating SPAs, and scraping JS-rendered content. Navigation uses Playwright's default timeout unless you explicitly pass `timeout_ms`.
**Tools:**
* `browser_launch` — Start a browser session (headed/headless, viewport size, locale)
* `browser_navigate` — Go to a URL
* `browser_click` — Click an element by CSS selector
* `browser_type` — Type text into an input
* `browser_screenshot` — Capture the current page
* `browser_evaluate` — Execute JavaScript in the page context
* `browser_close` — End the session
Use `web_fetch` for static pages — only use the browser when you need interaction.
## Documents & Media
**Type:** Plugin
**Triggers:** document, word, docx, report, letter, memo, template, convert document
Read, create, modify, and convert documents (docx, html, markdown, plain text).
**Tools:**
* `document_read` — Extract content as text, HTML, or markdown from any document
* `document_create` — Create .docx with headings, paragraphs, tables, images, lists, headers/footers
* `document_modify` — Edit existing documents
* `document_convert` — Convert between formats
* `document_merge` — Combine multiple documents
**Type:** Plugin
**Triggers:** pdf, merge pdf, split pdf, watermark, form fill, encrypt pdf, compress pdf
Full PDF toolkit with RTL/Arabic support.
**Tools:**
* `pdf_read` — Extract text, metadata, and structure (with optional page range)
* `pdf_create` — Create PDFs with headings, paragraphs, images, tables (supports RTL with custom fonts)
* `pdf_merge` — Combine multiple PDFs
* `pdf_split` — Extract page ranges into separate files
* `pdf_secure` — Encrypt/decrypt with passwords
* `pdf_compress` — Reduce file size
* `pdf_watermark` — Add text watermarks
**Type:** Plugin
**Triggers:** spreadsheet, excel, xlsx, csv, tsv, table, data, formula, chart
Read, create, modify, and analyze spreadsheet files.
**Tools:**
* `spreadsheet_read` — Read xlsx/csv/tsv with optional sheet selection and cell range
* `spreadsheet_create` — Create new spreadsheets with multiple sheets, columns, rows, and styles
* `spreadsheet_modify` — Edit existing files (add rows, update cells, add sheets)
* `spreadsheet_analyze` — Compute statistics, summaries, and derived columns
**Type:** Plugin
**Triggers:** ffmpeg, video, audio, convert, transcode, compress
Wraps the FFmpeg CLI for multimedia processing. Runs until completion — no timeout, regardless of file size or encoding complexity.
**Tools:**
* `ffmpeg_check` — Verify ffmpeg is installed
* `ffmpeg_install` — Install via package-manager
* `ffmpeg_run` — Run any ffmpeg command (pass args after `ffmpeg`)
The capability auto-checks for ffmpeg and offers to install it if missing.
## Voice
**Type:** Plugin
**Triggers:** transcribe, speech to text, stt, whisper, audio to text, dictation
Local speech-to-text using **faster-whisper** (CTranslate2 + PyAV) — far lighter than reference Whisper (no PyTorch, no external ffmpeg). Supports 99+ languages with automatic detection and runs entirely on your machine — no API keys, no cloud, fully offline after setup. Transcription runs until it finishes regardless of file size.
**Tools:**
* `stt_transcribe` — Transcribe an audio file at a given path
* `stt_transcribe_upload` — Transcribe a file uploaded in the current conversation
* `stt_transcribe_voice_memo` — Transcribe a voice memo generated by text-to-speech
* `stt_detect_language` — Detect the spoken language without a full transcription
Models available: tiny, base (default), small, medium, large — larger is more accurate but slower. The engine installs into a managed Python runtime automatically on first use (or on demand from Settings → Speech-to-Text); the chosen model downloads once and caches.
**Type:** Plugin
**Triggers:** voice, speak, say, audio, read aloud, voice memo, tts
Fully local neural text-to-speech using **Kokoro** — no cloud, no API keys, no Microsoft. Synthesis runs entirely on-device and produces an MP3. Generation runs until complete — no timeout.
**Tools:**
* `voice_generate` — Convert text to MP3 (returns file path)
* `voice_respond` — Respond entirely as a voice memo (the audio IS the response)
* `voice_list` — List all voice memo files in the workspace
English voices only — American (`af_`/`am_`, e.g. the default **`af_bella`**) and British (`bf_`/`bm_`). The voice and speech rate are chosen in **Settings → Text-to-Speech** and applied automatically; the model installs into a managed Python runtime on first use (or on demand from Settings, with a live progress bar and a real in-app preview).
## Version Control & Code
**Type:** Pure Skill (no plugin)
**Triggers:** git, commit, branch, merge, push, pull, PR, diff, stash, rebase
Teaches the LLM how to use `shell_exec` for Git with the user's conventions. Instructions include:
* Always run `git status` before making changes
* Use Conventional Commits format: `type(scope): subject`
* Show diffs and proposed commit messages before executing
* Branch naming: `feature/`, `fix/`, `chore/` prefixes with kebab-case
Since this is a pure skill, it has no plugin — it relies on the shell capability.
**Type:** Plugin
**Triggers:** github, pull request, PR, issue, repo, CI, actions, workflow, release, gist
Full GitHub API access via Octokit. Requires a personal access token (Settings > GitHub).
**Tools:** list repos, create/read/update issues, create/list/merge PRs, list branches, trigger workflows, create releases, manage gists, manage labels/milestones, review PRs, list notifications, star/fork repos, compare branches.
**Pagination:** GitHub hard-caps `per_page` at 100. For larger result sets, page through with multiple calls.
See [GitHub Integration](/integrations/github) for full setup and usage.
## External Services
**Type:** Plugin
**Triggers:** google, gmail, email, inbox, drive, calendar, events, contacts, tasks, sheets
Gmail, Drive, Calendar, Contacts, Tasks, and Sheets via OAuth. Multi-account support. All API calls run until completion — no artificial timeouts.
**Tools:** gmail search/read/send/reply/archive, drive list/upload/download, calendar events CRUD, contacts, tasks, sheets read/write.
See [Google Workspace Integration](/integrations/google-workspace) for full setup.
**Type:** Plugin
**Triggers:** notion, workspace, wiki, knowledge base, database, page, kanban, board
Read, create, and manage Notion content via the Notion API.
**Tools:** search, read pages, read blocks, create pages, update pages, append blocks, create/query databases, add comments.
See [Notion Integration](/integrations/notion) for full setup.
**Type:** Plugin
**Triggers:** cloudflare, tunnel, cloudflared, expose, public url
Create quick Cloudflare Tunnels to expose local ports to the internet. Install runs until complete.
**Tools:**
* `cloudflared_check` — Check if cloudflared is installed
* `cloudflared_install` — Install via package-manager
* `cloudflared_tunnel` — Create a tunnel for a local port (returns public URL)
Always requires user confirmation before exposing a local service.
## Desktop Automation
**Type:** Plugin
**Triggers:** screenshot, click, screen, desktop, mouse, keyboard, computer use, automate, UI
Desktop automation for visual tasks — screenshots, mouse clicks, keyboard typing, scrolling.
**Tools:**
* `computer_screenshot` — Capture the full screen (or specific display)
* `computer_mouse_move` — Move cursor to x,y coordinates
* `computer_mouse_click` — Click at position (left/right/double)
* `computer_keyboard_type` — Type text
* `computer_keyboard_press` — Press key combinations
* `computer_scroll` — Scroll at position
Must be enabled in Settings > Computer Use. The agent sees screenshots and can interact with any application on screen.
## Interaction
**Type:** Plugin
**Triggers:** ask the user, ask me, which option, let me choose, give me options, clarify, confirm with me, multiple choice, quiz me
Lets Wolffish put a decision back to you with concrete choices instead of guessing. It pauses the turn, renders an interactive question card — the question, 2–5 numbered options each with a short description, and (unless disabled) a free-text box to type your own instructions — then resumes the moment you answer.
**Tools:**
* `ask_user` — Pose a multiple-choice question and wait for the answer. Returns the option you picked or the custom instructions you typed.
Works on every channel: the desktop UI shows the card; on Telegram and WhatsApp you reply with the option number (or your own text). If the run is stopped without an answer, Wolffish falls back to a sensible default instead of re-asking in a loop.
## Fun
**Type:** Plugin
**Triggers:** meme, funny, gif, laugh, humor, joke, celebrate, lol
Create captioned memes from popular templates or search for reaction GIFs. No result caps — request as many GIFs as needed.
**Tools:**
* `meme_generate` — Create a meme from a template (drake, fry, buzz, distracted-boyfriend, this-is-fine, etc.)
* `meme_templates` — List available templates
* `gif_search` — Search for reaction GIFs
* `gif_trending` — Get trending GIFs
* `add_to_chat` — Insert the generated meme/GIF into the conversation
Uses memegen (zero-config) or imgflip (with credentials) as the backend.
**Type:** Plugin
**Triggers:** status, health, performance, how are you, what do you know, uptime, stats
Lets Wolffish answer questions about its own state by reading its workspace files.
**Tools:**
* `wolffish_status` — Uptime, active provider, loaded capabilities, channel connectivity, and system health
* `channel_status` — Whether each messaging channel (Telegram, WhatsApp, in-app) is connected, and the exact steps to reconnect one that isn't
* `wolffish_performance` — Task success rates, most used tools, error rates
* `wolffish_memory` — Recent conversation topics and knowledge areas
Read-only — never modifies the workspace. Ask "how are you doing?" for real data, not pleasantries. Wolffish checks `channel_status` before sending you an out-of-band message — Telegram and WhatsApp are connected channels reached through their own tools, never desktop apps to launch.
## Task Execution (Motor Runtime)
The motor cortex executes all tool calls with these defaults:
* **Output buffer:** 100KB per tool result — the LLM sees substantial output without truncation
* **Retries:** Up to 10 attempts for retryable errors (network, timeout). Non-retryable errors (permission, validation, not-found) bail immediately. Backoff scales up to 60s between attempts.
* **No global timeout:** Tools run until they complete or the user stops them
## Customizing Capabilities
Built-in capabilities are managed and updated by Wolffish — don't edit them directly, as your changes will be overwritten on the next update. Instead:
* **Disable** a built-in capability from Settings if you don't need it
* **Fork** it — copy the folder to a new name, then edit the copy however you like
* **Create your own** from scratch following the same structure
Changes to custom capabilities take effect on the next message — no restart needed.
Custom capabilities are not backed up automatically. If you delete a capability you created, it's gone — Wolffish has no copy of it. Use git or keep a manual backup of your `brain/cerebellum/` folder. Built-in capabilities are always restored automatically on launch.
Start by reading the SKILL.md of any built-in capability to understand the pattern. Then create your own following the same structure. See [Creating Capabilities](/capabilities/creating-capabilities) for a step-by-step guide.