investigate-run
Post-mortem analysis of a PhysicsIntern workspace run (Claude Code, Pi, Codex, or OpenCode host). Reconstructs the trajectory from the session record — JSONL…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,653 results
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
iblai-api-agent-access
Manage role-based access to an ibl.ai agent via the platform API — list role policies, search users/groups, and grant/revoke editor, chat, or analytics_viewer…
iblai-api-agent-create
Create a new ibl.ai agent from a template via the platform API — set name, display name, description, system prompt, and LLM provider; returns the new agent's…
iblai-api-login
Connect an ibl.ai organization for API access. Gets the user signed in (ibl.ai/join if new, login.iblai.app/me if returning), captures their org key and…
agent development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…
mcp integration
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol",…
iii-sandbox
Ephemeral microVM sandboxes for running untrusted or agent-generated code in isolation — a one-call run path, a create/exec/stop lifecycle, and a set of…
pi
Run headless Pi coding-agent turns over the iii bus — file edits, shell, and search against any host directory — with verbatim event streaming, session resume,…
fable-watchdog
Supervisor watchdog and circuit breaker protocol for autonomous agent loops.
axum-agents-scaffold
Use when the request is to build a complete Axum service from scratch rather than to fix one isolated piece: "build me an Axum API", "scaffold a Rust web…
axum-impl-sse
Use when an Axum handler must push a one-way server-to-client stream over plain HTTP: live notifications, log tailing, progress updates, an LLM token feed, or…
thatopen-agents-model-analyzer
Use when analyzing an IFC model's contents, generating reports on element counts, properties, or spatial structure. Prevents inefficient model queries and…
thatopen-agents-viewer-builder
Use when scaffolding a complete ThatOpen BIM viewer application from scratch, including project setup, package installation, and working code. Prevents…
thatopen-errors-loading
Use when IFC loading fails, WASM initialization errors occur, or fragment worker initialization problems arise. Prevents common loading failures by documenting…
thatopen-impl-highlighting
Use when implementing element selection, hover effects, outline visualization, or converting fragments to meshes in a ThatOpen viewer. Prevents missing…
ray-diagnose
Enterprise knowledge base / pre-diagnosis for AI implementation. Use the GROUND six-dimension model to assess readiness, conduct requirements archaeology to see through the "real problem", match pathology patterns, and output a maturity level + red/yellow/green feasibility rating + conditions for turning green. When a user wants to assess whether an enterprise can implement a knowledge base/AI...
ai-rag-pipeline
Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via…
agent-ui
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in.…
session-handoff
Write an agent session handoff with current state, decisions, unfinished work, verification, and next steps.
j5ik2o-takt-facet-builder
Individual creation/editing skill for TAKT facets (Persona/Policy/Instruction/Knowledge/Output Contract). Generates standalone files compliant with the style guide for each facet. Uses the style guides and built-in facet set in references/takt as reference materials, and…
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through…
chinese-grandpa
Compresses long, repeated sub-agent instructions by translating them into Mandarin (more meaning per character) to slash the token bill, then dispatches the…
issue-pool-progression
Use to select and advance one eligible issue from an authorized pool through claim, review, release, and live verification.