experiment-provenance-ledger
Preserve experiment provenance across code, data, environment, parameters, metrics, artifacts, and human decisions. Use when an agent needs a judgment-heavy…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,658 results
Preserve experiment provenance across code, data, environment, parameters, metrics, artifacts, and human decisions. Use when an agent needs a judgment-heavy…
Create concise model risk and compliance memos for review, audit, launch, or executive approval. Use when an agent needs a judgment-heavy data science workflow…
Audit open-source packages, notebooks, model weights, datasets, licenses, and provenance used in data science work. Use when an agent needs a judgment-heavy…
List 3-5 comparable apps when planning a UX surface to test category fit and surface high-leverage refusals. Use for "what do other apps do", identity, sync…
Create, revise, evaluate, and validate Vercel-backed Agent Skills for this repository. Use when writing a new skill, improving an existing skill, tuning skill…
Reference for writing and editing any agent-facing artifact — the vocabulary and principles that make it predictable. Covers authoring a skill, agent…
Audit, generate, update, and lint AGENTS.md files across all projects. Use when asked to check project context files, scaffold AGENTS.md for new projects,…
Generate and safely maintain an AGENTS.md file (the cross-tool standard for guiding AI coding agents, backed by the Linux Foundation's Agentic AI Foundation…
Building Expo DevTools Plugins with CLI Interfaces for interacting with running Expo apps using agents.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
Use Library Skills to discover, install, refresh, repair, check, and manage agent skills from installed packages.
Drives a multi-turn conversation with a LiveKit agent running locally to see what it does. Use when the user says "test my agent", "try my agent", "does this…
Looks up current LiveKit facts (API signatures, CLI flags, config options, model and provider support, SDK changelogs, pricing) from the docs instead of…
Build and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real workflows as page tools, create…
Bootstrap a project CLAUDE.md from the template in docs/templates/. Detects stack signals, asks 5 focused questions, writes a compliant file under the project…
Strategic dispatcher role — reads dashboards, optimizes throughput, dispatches work to crew; does not write code or review diffs
Architectural authority role — decomposes goals into engineer tasks, verifies process, guards architecture; does not write code or fill gaps directly
Create a new account on a web service using Navvi — generates credentials in gopass, fills signup form, handles CAPTCHAs, registers the account. Use when asked…
Use when the user wants to ask DeepSeek a question through Frevana using the user's logged-in Chrome Extension session.
Use when the user wants high-speed, cost-effective inference, rapid code generation, data extraction, high-throughput summarization, or conversational tasks…
Automated CLI-based parallel agent execution that spawns subagents via Gemini CLI, coordinates through MCP Memory, monitors progress, and runs verification
Strategic product gate: challenge the brief, find the 10-star product hiding inside the request, before writing any code