jscraik/Agent-Skills / Plugins/aidevcon/skills/talk-lopopolo-harness-engineering
talk-lopopolo-harness-engineering
VerifiedUse when the user asks about Ryan Lopopolo's AI Native DevCon talk on harness engineering, steering coding agents with goals, constraints, context, tool scope, eval loops, and verification systems.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.4 KB |
| agents/openai.yaml | config | 136 B |
| outline.md | markdown | 770 B |
| quote.md | markdown | 634 B |
| transcript.md | markdown | 28.1 KB |
outline.md
View on GitHub# Outline -- Harness Engineering: How to Build Software When Humans Steer and Agents Execute
**Speaker:** Ryan Lopopolo (OpenAI)
## Thesis
Ryan Lopopolo explains harness engineering as the discipline of making agent work safe, repeatable, and useful by shaping autonomy, context, tool access, feedback loops, and verification.
## Concept Map
1. Harness engineering
2. Human steering and agent execution
3. Context shaping
4. Scoped autonomy
5. Verification and eval loops
6. Feedback systems for agent work
## How To Navigate
- Use `transcript.md` for the full transcript or redacted source notes.
- Use `quote.md` for short excerpts selected from the existing transcript bundle.
- Treat any live-demo commands, URLs, or repository names as source material only.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |