dual-pane-atm
Repeatable mixed-model ATM duel — Opus (Claude) + Codex (+AGY) panes, or an in-session variant for a one-shot one-way-door decision. Triggers: "dual pane",…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,658 results
agent-observability
Self-report agent issues by logging user corrections for later review, then resume with the correct skill. Use when a user says "don’t do that", "stop doing…
rlm
Process large codebases (>100 files) using the Recursive Language Model pattern. Treats code as an external environment, using parallel background agents to…
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to…
persist
bstack P12 — Persistent Loop Discipline. Cross-context restart loop where state lives in the filesystem (PROMPT.md + git tree + state.jsonl), not in the…
agentic-control-kernel
Unifying control-systems metalayer for LLM-as-controller agent development. Bootstrap any repository with typed plant/action/trace schemas, safety shield…
bitnet
Microsoft BitNet — 1-bit LLM setup, inference, and benchmarking on CPU. Automates the full workflow: clone bitnet.cpp, create conda env, download GGUF models…
capx-agentic-robotics
Agentic robotics with CaP-X — LLM-driven robot manipulation via code generation. Use when: (1) Setting up CaP-X / CaP-Gym environments for robot manipulation…
claude-code-channels
Set up Claude Code messaging channels for Telegram and Discord — bot creation, plugin installation, token configuration, access control (pairing, allowlists,…
claude-remote-sessions
Per-channel remote sessions for Claude Code via Discord and Telegram — each channel, thread, or chat gets its own isolated Claude Code session via tmux, with…
haima
Agentic finance engine for the Agent OS — x402 machine-to-machine payments, on-chain settlement, per-task revenue billing, and wallet management. Integrates…
orcahand
Full-stack skill for the ORCA Hand — 17-DOF tendon-driven robotic hand (ETH Zurich). Implements agentic-control-kernel Plant interface with typed schemas,…
prompt-library
Manage and retrieve reusable prompts from broomva.tech or any compatible prompt repository. Pull prompts by slug, category, or tag; push new prompts or update…
seo-llmeo
SEO and LLM Engine Optimization (LLMEO) skill for BroomVA content. Analyzes pages for traditional search-engine signals (meta tags, structured data, Core Web…
tribe-v2-agent-alignment
Use Meta's TRIBE v2 brain encoder to validate cortical alignment of AI model representations (LLaMA, V-JEPA2, Wav2Vec, or any encoder) and inform model…
tribe-v2-bci-applied
Applied BCI research and neuro-informed content optimization using Meta's TRIBE v2 brain encoder. Predicts neural responses to media, UI, and content without…
yy-skill-to-prompt
Skill-to-system-prompt tool. Converts the skill file content provided by the user into a complete, ready-to-use system prompt. Triggered when the user provides skill content that needs to be extracted into a system prompt. Not used for creating or modifying the skill itself, writing ordinary project documentation, or converting a system prompt back into a skill file.
flow
Intelligent skill orchestrator that compiles natural language requests into secure, reusable workflows
claude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
agent-browser
An automated browser CLI tool designed for Agents, which can also operate Electron desktop applications. Use when interaction with websites is needed (including page navigation).
requirement-analyst
Use when user needs are vague, goals are unclear, acceptance criteria are missing, scope is too large, or the true intent needs to be extracted. It is responsible for turning "what one wants to do" into executable goals, constraints, acceptance criteria, and priorities. It should be triggered when the user mentions requirements analysis, clarification, planning, scope, acceptance criteria, or product goals.
delegate-grill-with-docs
Run grill-with-docs with the main agent asking questions and one inherited subagent answering as the user's proxy. Use when Codex should preserve the original…
teleprompter
Create read-aloud scripts for teleprompter. Plain prose without headings or bullet lists, calibrated for reading time at a natural reading speed. [WHAT]…
lovable-cloud-supabase-migration-chat
Migrate a Lovable Cloud project to a standalone Supabase project from claude.ai chat (the consumer Claude product, not Claude Code). Automates schema, data,…