provider
Use when Claude Code should run ON bro — `bro provider serve` is the host-level Messages-API listener (ANTHROPIC_BASE_URL target), `bro provider ensure`…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,314 results
providers
Use when configuring or debugging bro's provider registry — `providers` in bro.config.json, provider kinds (api/acp/cli), model wire selection,…
pulse
Use when a session needs its own watchdog cadence — 'arm the pulse', 'wake me every N', keeping an eye on long-running fleet/loop/convoy work without blind…
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn…
watch
Use when supervising parallel convoys/agents — 'watch the fleet', 'what needs attention', a monitor loop over mols/PRs. Thin wrapper over the bro CLI: `bro…
wtf
Use when the user invokes /wtf or vents sharp frustration at the agent's own work. Thin wrapper over the bro CLI — `bro wtf` captures the complaint as a bead,…
feedback
Prepare consent-gated anonymous feedback for monskills when the agent is stuck, hits the same error repeatedly, finds incorrect or missing information in a…
prompt-improver
Transforms vague or unstructured prompts into specific, actionable Claude Code prompts with clear objectives, constraints, and verification steps. Use when the…
mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type…
openai-tts
Text-to-speech via OpenAI Audio Speech API.
skills-hub
Use the ThinkFleet Skills Hub CLI to search, install, update, and publish agent skills. Use when you need to fetch new skills on the fly, sync installed skills…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
levelup-boot
Use when a task matches CDR descriptors and full context module bodies (personas, rules, examples) from team-ai-directives are needed, or a reusable team…
subagent-creator
Guide for creating effective subagents (custom agents). Use when users want to create a new subagent that can be dispatched via Task tool for autonomous work.…
arena
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the…
automate-me
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the…
principle-never-block-on-the-human
Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation…
swarm
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
copilot-harness
Drive the GitHub Copilot CLI (`copilot` / `copilot.exe`) from another agent: winget install, one-shot -p/--prompt, continue/resume sessions, models, skills.…
ralph-wiggum-pattern
A Python-focused implementation of the Ralph Wiggum technique for AI-assisted software development
tinyfish-web
Pick the right TinyFish tool for a web task. Use when a request involves the live web — searching, reading pages, extracting data, filling forms, automating a…
agent-worktrees
Isolate parallel AI agents on one git repo via branch+worktree, shared env symlinks, auto-ported previews, status lines, claims, and a land-from-main ritual.…
ea
Route routine agent work to deterministic tools and bounded JEV decisions through the user’s preferred connection. Use when the user requests an executive…
behavior-contracts
Keep multi-platform products behaviorally one product: write platform-neutral behavior contracts per form/primitive, let each kit satisfy them natively, audit…