Heavybit Skills collection
Your AI product, in production.
Skills for evaluating and monitoring systems whose output changes from run to run, structuring the team that ships them, and governing an AI product responsibly. Built from what operators at Humanloop, Honeycomb, Smol AI, Deepchecks, and PlayerZero shared in the Heavybit Library.
Five skills
- 01Agentic Engineering
- 02Agent Infrastructure
- 03AI Product Operations
- 04AI Observability
- 05AI Governance & Responsible AI
Built from eighty library resources
What a skill is
A skill is a set of working instructions your agent loads when you need it, built from the strategies operators shared in the Heavybit Library. It guides the work and you still do it. Heavybit reads and approves every skill before it ships, and keeps updating skills as new content enters the Library. Skills are plain text, so you or your agent can read any skill in full before acting on it. Your agent decides how to apply a skill, so check its work; if a skill gets something wrong, ask your agent to report it or email platform@heavybit.com.
Connect your agent
- Add the endpoint below to your harness: Claude Code, Codex, Claude, Cursor, ChatGPT, or another that supports MCP.
- Sign in to your Heavybit account with Google or GitHub when your agent asks. It's free, and your first sign-in creates the account.
- Tell your agent what you're working on. It finds the right skill, or you can ask for one by name.
MCP endpointhttps://crucible.heavybit.com/mcp
Heavybit Skill
Agentic Engineering
Built from nineteen library resources
How teams build software when AI coding agents write the code: directing agents, what code review and validation become when code is nearly free, durable systems with disposable code, orchestrating many agents, keeping them safe inside an organization, and how roles change. Drawn from practitioners at HumanLayer, Sentry, Honeycomb, Google DeepMind, and others.
Built from what these operators shared
- +15
Heavybit Skill
Agent Infrastructure
Built from thirteen library resources
The runtime substrate for AI agents: the machine an agent runs on, sandboxes and isolation, agent memory and learning, durable execution and harness design, and the performance and cost of running agents. Drawn from practitioners at exe.dev, Daytona, Letta, Glean, and others.
Built from what these operators shared
- +13
Heavybit Skill
AI Product Operations
Built from twelve library resources
The emerging operational discipline for AI in production. Covers the guardrails, metrics, and team structures that differ from classic software: reasoning systems, evaluation frameworks, prompt engineering workflows, and scaling AI products reliably. Drawn from practitioners at Smol AI, Humanloop, Remyx AI, and others.
Built from what these operators shared
- +7
Heavybit Skill
AI Observability
Built from twenty-one library resources
Continuous validation and production monitoring for AI systems. Covers the unique challenges of observing non-deterministic outputs, bridging technical and business metrics, and connecting observability data to code and user experience. Drawn from practitioners at Deepchecks, PlayerZero, and others.
Built from what these operators shared
- +16
Heavybit Skill
AI Governance & Responsible AI
Built from seventeen library resources
Governance frameworks, ethical principles, and practical safeguards for building and deploying AI products responsibly. Covers bias detection, prompt injection security, trust architecture, regulatory compliance, and the organizational structures needed for responsible AI. Drawn from practitioners at Humanloop, Equality AI, Deepchecks, and others.
Built from what these operators shared
- +11
Connect your agent to Crucible, Heavybit's MCP server
One endpoint gives your agent every Heavybit Skill, a search of the Heavybit Library, and a direct line to Heavybit. Sign in free with Google or GitHub. Skills load when your agent needs them, so there is nothing to download or update.