skill-portability-compiler
Port an agent Skill across ChatGPT, Codex, Claude, API agents, or another compatible host without losing its decision logic, evidence gates, activation…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,660 results
ifc-agents-migration-orchestrator
Use when asked to migrate an IFC file to another schema version, upgrade an IFC2x3 model to IFC4 or IFC4.3, downgrade an IFC4 model, or plan a schema-version…
ifc-agents-model-author
Use when authoring a complete, coordinated IFC model from scratch and you need the correct build order, or when an IFC file you produced is rejected, opens…
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.…
llm-models
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3…
northstar-agents-review
Review a Northstar AGENTS instruction surface.
northstar-readiness-review
Review whether Northstar planning is ready to proceed.
make-functions-v2
Guides authoring, testing, publishing and operating Make Functions v2 through the Make MCP connection. Covers TypeScript Functions, Endpoint contracts, version…
isaaclab-preparing-assets-for-newton
Migrates PhysX-compatible robot, object, and scene assets to Isaac Lab's Newton backend with MJWarp. Use when handling existing Isaac Lab assets or new…
skill-smith
The skill that builds skills. Watches for workflows the user repeats manually, drafts a new skill for the pattern, tests it, and submits it to the Bouncer —…
llm-app-development
Build LLM applications: RAG, embeddings, agents, structured outputs, evaluations, fine-tuning, and local inference.
j5ik2o-gh-pr-review-follow-up
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not…
j5ik2o-git-commit
Commit working-tree changes using Conventional Commits. Stage changes in meaningful units, write commit messages in English, and avoid co-author or agent…
codex-app-server
Build rich Codex integrations with the Codex App Server across Electron, Swift, Next.js, and other host apps. Use when embedding Codex into a product, adding…
brain-load
Load project context from the Claude Brain Logseq graph into the current session. Triggers: "load brain", "load <project>", "resume <project>", "continue work…
meta-workflow-graph-refresh
Entry point for refreshing the DH workflow graph. Use when skills, agents, Mermaid flowcharts, MCP tools, or artifact flows change and…
drafter-axi
Drive a community-drafter document from the shell — create it, publish revisions, invite and track signers, export the pending-feedback bundle for an LLM…
idea
Puts an idea on the board as a ticket and frames it, so it waits in Shaping with its tier and open questions. Run it with /idea <the idea>.
agent-file-specs
Contains the complete specifications for AI coding assistant customization files including agents, skills, prompts, and instructions. Works with GitHub…
generate-agent-docs
Generates documentation and usage guides for agents, skills, prompts, and instructions. Works with GitHub Copilot, Claude Code, Codex, OpenCode, and other…
validate-agent-files
Validates AI coding assistant customization files (agents, skills, prompts, instructions) for correct format and structure. Works with GitHub Copilot, Claude…
codebase-exploration
Map an unfamiliar codebase by delegating narrow recon to subagents and building a key-files map before you read source — keep the orchestrator's context clean.…
sus-task
Split a ready Suspec spec into collision-proof task packets. Use when spec-governed work must be divided into independent parallel slices, repository or…
ask-user
Intercept every agent-originated question and unresolved ambiguity that requires user input. ALWAYS use before asking for clarification, confirmation,…