Agent skills for Zed

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch…

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics.

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM.

Activate multi-agent orchestration mode

Orchestrate herdr worker tabs for a spec (PRD).

Coordinate substantial work from one persistent orchestrator with narrowly scoped GPT-5.6 Luna collaboration subagents.

Plan and then actually run multi-agent work in a TypeScript / pnpm monorepo - decide which specialist does each piece (ts-implementer…

Read-only: calculates refund rate by product, collection, or period — identifies quality and listing issues.

Create algorithmic and generative art using mathematical patterns, noise functions, particle systems, and procedural generation.

Use when designing modules, APIs, and system architecture requiring independent, non-overlapping components where changes in one don't…

SME-facing front-door skill for Agentic OS ecosystem evolution.

Build and schedule a personalized Operator prompt that runs the user's second brain on a recurring cadence.

Find paid open-source work, OSS bounties, open source grants, or ways to get paid contributing to open source.

Apply this skill when managing external community engagement in unifi-mcp: setting up GitHub health files and issue routing…

Open source license compliance check for a dependency list, a single library, or outbound code.

Persistent file-based planning for multi-step AI-agent work.

Automatically converge from goal to A-grade Seed and execute it

Outcome KPI definition methodology - synthesizes Who Does What By How Much (Gothelf/Seiden), Running Lean (Maurya), and Measure What…

Transform output-based feature lists into outcome-driven Now/Next/Later roadmaps using the "so what?" technique.