David Ondrej
Agent research tools
Skills for subagents, code reviews, worktrees, handoffs, and research.
Featured skills
distribute-skill-to-all-agents
Distribute global skills across Codex, Claude Code, Pi, Hermes, and Cursor.
nagent
Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree,...
adr-verbatim
Used to write a new ADR whose body is the user's exact words, nothing added.
browser-harness
Direct browser control via CDP.
codex-subagent
Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key).
deep-research
Used to run a deep, source-backed research query via DeepAPI (go to deepapi.co to get an API key) POST...
effective-agent-skills
How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns,...
git-worktree
Use git worktrees to run multiple coding agents in parallel on one repo without collisions.
global-agent-guardrails
One shared denylist of catastrophic shell commands (rm -rf on / or ~, dd/mkfs, sudo rm, fork bombs, curl|sh, git push...
goal-loop
Explain and write effective instructions for the `/goal` feature — the persistent self-checking agent loop (plan → act...
gpt-review
Launch a GPT 5.6 Sol Max subagent to do a deep, neutral senior-developer review of the current work and report its...
handoff
Compact the current conversation into a single, detailed handoff message — everything that happened, why it happened,...
Dean Peters
Product strategy and discovery
Product management workflows for discovery, positioning, prioritization, roadmaps, and product leadership.
Deck
Product discovery and planning
Skills for Deck competitor analysis, customer feedback, initiative briefs, and prioritization.
Deque
Accessibility testing and remediation
Skills for accessibility analysis and remediation using Deque tooling and guidance.