Talk Douglas Training AI on Your Own Code

Answers questions about Brian Douglas's talk on training AI on your own code. Use when a user asks about Brian Douglas's pipeline for capturing agent sessions, extracting skills from traces, fine-tuning small local models, tapes/steros tooling, SFT vs DPO decisions, or wants to apply his agent telemetry and training data approach to their own work with Claude Code, QLoRA, or parallel agents.

9 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jscraik/Agent-Skills --skill talk-douglas-training-ai-on-your-own-code
Manual install
git clone --depth 1 https://github.com/jscraik/Agent-Skills.git /tmp/Agent-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Agent-Skills/Plugins/aidevcon/skills/talk-douglas-training-ai-on-your-own-code ~/.claude/skills/talk-douglas-training-ai-on-your-own-code

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# The beginner's guide to training AI on your own code — Brian Douglas

Brian Douglas (founder of Paper Compute) walks through a pipeline — tapes (a telemetry proxy) + steros (an agent runtime) — that captures every agent session, extracts skills from the traces, and optionally fine-tunes small local models on the resulting data.

## Grounding rules — MUST follow when answering

1. Before answering any specific question, read `outline.md` to locate the relevant section, then read that section of `transcript.md`.
2. When attributing words, **quote short, non-sensitive excerpts** from `transcript.md` for all key claims, definitions, and framework explanations. Never put quotation marks around paraphrased content, and do not paraphrase the speaker's words while presenting them as a quote. This rule applies across all use cases below.
3. If a claim isn't in `transcript.md`, say so explicitly — do not speculate or invent details. Tell the user the topic wasn't covered in this talk.
4. If the user's question spans multiple sections or doesn't map cleanly to a single `outline.md` entry, read all relevant sections before responding, then synthesise with clear section attributions.

## Expected response format

**User question:** "How does Brian Douglas decide between SFT and DPO?"

**Good response:**
> Brian Douglas addresses this directly: [safe excerpts from transcript.md]. He frames the choice as…
Read the full skill on GitHub

Details

Skill name
talk-douglas-training-ai-on-your-own-code
Path
Plugins/aidevcon/skills/talk-douglas-training-ai-on-your-own-code/SKILL.md
License
Apache-2.0
Repo updated
16 November 2026

FAQ

What does the Talk Douglas Training AI on Your Own Code skill do?

Answers questions about Brian Douglas's talk on training AI on your own code. Use when a user asks about Brian Douglas's pipeline for capturing agent sessions, extracting skills from traces, fine-tuning small local models, tapes/steros tooling, SFT vs DPO decisions, or wants to apply his agent telemetry and training data approach to their own work with Claude Code, QLoRA, or parallel agents.

How do I install the Talk Douglas Training AI on Your Own Code skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jscraik/Agent-Skills --skill talk-douglas-training-ai-on-your-own-code. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Talk Douglas Training AI on Your Own Code popular?

It lives in jscraik/Agent-Skills, which has 9 GitHub stars and 4 forks.

Related skills

1password

9

jscraik/Agent-Skills

Plan, diagnose, and validate 1Password CLI workflows. Use when tasks need op CLI sign-in, secret references, op run, op inject, item reads, env injection, or service-account secret access.

Security

Agentation

9

jscraik/Agent-Skills

Audit, validate, and troubleshoot Agentation integrations in frontend apps. Use when annotations, MCP registration, endpoint sync, webhook delivery, or watch mode readiness are failing.

AI, LLMs & Agents

Agents Md

9

jscraik/Agent-Skills

Use when reviewing, creating, shrinking, or refactoring AGENTS.md and directly linked instruction guidance for stale or conflicting rules against current model documentation, scoped routing, deduplication, or progressive disclosure.

AI, LLMs & Agents

Talk Dubnov Merge Rate AI Adoption

9

jscraik/Agent-Skills

Answers questions about, applies frameworks from, and generates artifacts based on Tammuz Dubnov's talk "When Our PM Started Writing Code: What Merge Rate Taught Us About AI Adoption." Grounds every response in the bundled transcript and outline files. Use when a user asks about AI-native org design, merge rate measurement, non-technical contributors shipping PRs, harness engineering, zero-dev-touch rate, AI adoption ROI, or wants to audit their team against Tammuz's framework, apply his concepts to their situation, draft a measurement dashboard or checklist, or understand terms like Calamarou

AI, LLMs & Agents

Talk Debois Agent Enablement

9

jscraik/Agent-Skills

Use when the user asks about Patrick Debois's talk "Coding Agents Don't Scale Themselves. Neither Do Your Teams. The Rise of Agent Enablement." — including questions about agent enablement teams, the three pillars (Enablement, Platform, Governance), the Context Development Lifecycle applied to org charts, AI product engineers, agent KPIs like turns-per-task, harnesses and shared context libraries, fixing the system vs. fixing the code, the barrel mental model, continuous learning as the next CI/CD, or how VPs / team leads / platform teams should scale AI coding agents across an org.

AI, LLMs & Agents

Talk Firtman Web MCP Agentic Web

9

jscraik/Agent-Skills

Use when the user asks about Maximiliano Firtman's ("Maxi") AI Native DevCon talk on Web MCP and the agentic web — including questions about how Web MCP differs from MCP, exposing frontend tools to AI agents, the imperative vs declarative Web MCP APIs, tool design guidance (name/description/input schema/execute), the Chrome 149 origin trial, using Chrome DevTools MCP or Puppeteer as a bridge today, the Doom demo, or applying Firtman's "pick one high-value page state" adoption approach to current work.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.