Analyzes every open GitHub issue and PR in parallel and writes permalink-backed triage reports without ever mutating the repository.
Runs a long-horizon experiment loop that improves a code/model/prompt artifact against an evaluator, using a persistent hypothesis tree and a held-out test merge gate to avoid overfitting.
Turns Claude into an explore-first planning consultant that grounds in your codebase, asks only the decisions you must own, and — only after your explicit okay — writes one decision-complete work plan.
A post-implementation review gate that spawns five parallel sub-agents — goal verification, hands-on QA, code quality, security, and context mining — and passes only if all five pass.
A four-language engineering constitution that forces reference reading before coding, then enforces strict types, TDD, and file-size discipline.
Scans a repository and auto-generates a hierarchical set of AGENTS.md files at the root and in complexity-scored subdirectories.
A planning-only skill that grounds in your codebase, asks just the decisions you must own, and writes one decision-complete work plan after your explicit approval.
Analyzes a repo in parallel and generates AGENTS.md at the root plus in complexity-scored subdirectories.
Explores and scores your repo in parallel, then generates hierarchical AGENTS.md docs at the root and in high-complexity subdirectories.
Guides Claude to read, write, and process DICOM files with pydicom 3.0.2 while enforcing PHI-safe output and a bounded de-identification preflight.
A version-pinned guide for building, simulating, transpiling, and running quantum circuits with Qiskit 2.x and IBM Quantum Runtime.
A practical guide for training, evaluating and customizing reinforcement learning agents with Stable Baselines3.
Design, review, and migrate MATLAB or Octave code with strict license gating, static-only safety checks, and reproducibility reporting.
A hands-on PyG skill covering node/link/graph tasks, custom message passing, heterogeneous graphs, and neighbor sampling for large graphs.
A skill for designing, simulating, and running quantum circuits with Google's Cirq framework.
Picks a multi-agent orchestration pattern from requirements, generates and validates provider-ready tool schemas, and evaluates run logs for cost, latency, and bottlenecks.
Fans out one background agent per open issue/PR to produce evidence-backed, permalink-cited triage reports in /tmp — with zero writes to GitHub.
Case-by-case QA of opencode itself — CLI, HTTP server, plugin hooks/events over SSE, tmux TUI smoke, and read-only session DB investigation.
QA the omo Codex plugin in a fully isolated CODEX_HOME with a mock model, proving hooks actually fire without ever touching the user's real ~/.codex.
Splits a task into atomic PRs, builds each in its own git worktree, and loops through CI and bot review gates until merged.