AgentSkills library: reusable skills for AI coding agents (AI SDK, Codex, LangGraph, Supabase, Docker, Vitest, pytest, Streamlit, Zod).
This repository also configures its own agents. See what dev-skills tells them →
Skill Codex
Architect-level development, audit, and migration of multi-agent systems using LangGraph (v1+) and LangChain (v1+). Use when building or refactoring supervisor/subagent architectures, orchestrator-worker workflows, routing/hand-offs, agentic RAG, memory (short + long-term), state + context engineering, guardrails +…
Skill Codex
Motion/CSS animation for React, Vue, Base UI, and vanilla JS via the Motion AI Kit: transitions, springs, easing curves, CSS spring generation, Motion API docs search, and MotionScore performance audits. Use to implement web animation or to grade and fix animation jank. Covers motion mcp, MotionScore, spring bounce…
Skill Codex
Pre-PR multi-model review, parallel opus and codex exec adversarial lanes, then adversarial verification of merged findings. Read-only. Use before shipping nontrivial diffs.
Skill Codex
Create and switch to a conventional-commit branch before any work starts, then present the branch and PR plan in chat before implementing. Use when the user wants the branch prepared first and the plan agreed up front.
Skill Codex
Expert guidance for auditing, refactoring, and designing machine learning Jupyter notebooks with production-quality patterns. Use when: (1) Analyzing notebook structure and identifying anti-patterns, (2) Detecting data leakage and reproducibility issues, (3) Refactoring messy notebooks into modular pipelines, (4)…
Skill Claude CodeCodex
Inspect package/upstream source with opensrc: internals, exact paths, version diffs, and upgrade audits for npm, PyPI, crates, and Git; not general web.
Skill Claude Code
Use the Parallel CLI for web data work: URL extraction, deep research, data enrichment, entity discovery (findall), memory recall, and web monitoring. Web search goes to the parallel-search MCP server (free); escalate to parallel-cli search only when MCP is insufficient. Use for deep research, exhaustive…
Skill Codex
Architect and implement modern full-stack web/native platform work across Next.js, Expo, Convex, and monorepo tooling. Use when the task needs stack detection, platform-level planning, cross-cutting architecture, or repo-native verification workflows. Route general web UI review to repo-local web-design-guidelines and…
Skill Codex
Stress-test one-way-door plans by surfacing risky assumptions, irreversible bets, and unvalidated dependencies.
Skill Codex
World-class pytest engineer for Python: write/refactor tests, fix flakiness, design fixtures/markers, add coverage, speed up suites (collection/runtime), and optimize CI (GitHub Actions sharding, xdist parallelism, caching). Use when asked about pytest best practices, pytest 9.x features (subtests, strict mode, TOML…
Skill Codex
Sync repo docs (AGENTS, README, ADRs, specs, runbooks, doc comments) ↔ code/workflow. Triggers—big change, drift, docs-align/AGENTS prompts, plan, governance. Repo-native tools, any stack.
Skill Codex
Repo/monorepo modernization: dependency upgrades, security fixes, deprecation cleanup, framework migrations, dependency-native refactors, and verified hard-cut simplification.
Skill Codex
Fix local review (Codex, Zen, notes) w/ verify. Not gh-pr-review-fix or passive PR monitoring.
Skill Codex
Rust command-line apps with clap: derive and builder APIs, subcommands, flags, config and env precedence, stdout, stderr and JSON contracts, exit codes, completions, and binary distribution.
Skill Codex
Core Rust engineering. Use for implementation, debugging, review, compiler errors, ownership and lifetimes, traits and generics, async and concurrency, typed errors, Cargo and MSRV, crate choice, tests, performance, unsafe and security. Excludes focused product surfaces owned by narrower Rust skills.
Skill Claude CodeCodex
Explicit-only Rust architecture orchestrator. Use only when the user explicitly invokes rust-mega-eng for broad Rust ecosystem architecture, multi-crate workspace strategy, large refactors, release engineering, crate selection portfolios, or end-to-end Rust product planning across CLI, TUI, Tauri, services, libraries…
Skill Codex
Implicit Rust Tauri v2 skill. Use for Tauri apps, Rust commands, invoke contracts, app state, plugins, capabilities and permissions, secure IPC, filesystem and shell access, sidecars, updater, bundling, desktop and mobile distribution, and Rust frontend bridge design.
Skill Codex
Implicit Rust TUI and Ratatui skill. Use for terminal UIs, ratatui widgets and layouts, crossterm or termion event loops, terminal rendering architecture, async input, app state machines, keybindings, terminal UX, snapshot tests, and TUI performance.
Skill Codex
Implicit Rust web service skill. Use for Axum, Tokio, Tower, Hyper, REST APIs, middleware/layers, request extractors, typed errors, tracing, config, graceful shutdown, SQLx, background jobs, service tests, and production Rust HTTP architecture.
Skill Codex
Fix production Sentry issues from CLI evidence, using the issue, event, trace, replay, log and explore commands. Use for Sentry errors, performance regressions, noisy groups, source-map failures and crashes.
Skill Codex
Sentry CLI atoms for safe issues, traces, releases, projects, sourcemaps, and deliberate mutations.
Skill Codex
Commit + push relevant files, split conventional commits, open PR to main with title/body. Triggers—commit, push, open PR, scaffold PR/release defaults.
Skill Codex
Expert guidance for Vercel's Streamdown library - a streaming-optimized react-markdown replacement for AI applications. Use when: (1) Rendering AI-generated markdown from useChat/streamText, (2) Building chat UIs with streaming responses, (3) Migrating from react-markdown to streaming-friendly rendering, (4)…
Skill Codex
Architect-level Streamlit development for building, refactoring, debugging, testing, and deploying Streamlit apps (single-page or multipage) with correct rerun/state/caching/fragments, AppTest-based testing, custom components v2, safe theming/CSS, security-by-default, and Playwright MCP end-to-end automation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: