Skip to content

jscraik/Agent-Skills / Plugins/aidevcon/skills/talk-baker-sadogursky-context-engineering-skills

talk-baker-sadogursky-context-engineering-skills

Verified

Use when the user asks about Macey Baker and Baruch Sadogursky's workshop-style AI Native DevCon session on turning repeated agent work into skills, rules, scripts, hooks, and evals.

FileKindSize
SKILL.mdskill md2.5 KB
agents/openai.yamlconfig166 B
outline.mdmarkdown773 B
quote.mdmarkdown381 B
transcript.mdmarkdown944 B

transcript.md

View on GitHub
# Transcript -- Don't Write Prompts, Write Software

**Speakers:** Macey Baker and Baruch Sadogursky (Tessl)

## Source Status

The available local bundle for this session is a safety-redacted summary rather than a verbatim transcript. It preserves the talk's conceptual substance without runtime mechanics, mutable online dependencies, sensitive-data flows, or executable implementation details.

## Talk Substance

Macey Baker and Baruch Sadogursky frame reusable agent behavior as software: rules for always-on constraints, skills for reusable judgment, scripts for deterministic work, hooks for integration points, and evals for confidence.

## Preserved Concepts

- Rules versus skills
- Scripts for deterministic work
- Skills for reusable judgment
- Hooks and integration points
- Evals for reusable context
- Context as maintained software

## Attribution Note

Public attribution for this session is Macey Baker and Baruch Sadogursky.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall