A collection of AI agent skills following the Agent Skills open format
This repository also configures its own agents. See what dot-skills tells them →
Skill Claude CodeCodex
Search and recommendation system planning for a two-sided trust marketplace built on OpenSearch — user-intent framing, product-surface architecture, index design, query understanding, retrieval strategy, ranking, search-plus-recs blending, measurement, and a dashboard-and-alerting layer for ongoing decision making.…
Skill Claude CodeCodex
Empirically validates a software metric before trusting or optimizing it — point it at any candidate metric (a command that takes a path and prints one number) plus a corpus, and it runs experiments that try to falsify each property a good metric must have. Checks determinism (same input, same number across runs and…
Skill Claude CodeCodex
Migrating a JavaScript codebase to TypeScript — converting .js files to .ts, adding types to existing JS, or tightening a loosely-typed TS project toward strict mode. Covers tsconfig and allowJs strategy, incremental strict-flag ratcheting (noImplicitAny, strictNullChecks, noUncheckedIndexedAccess), typing public…
Skill Claude CodeCodex
MLflow 3 (open-source, pinned to 3.15) for classic-ML MLOps — logging and registering models, promoting versions across dev/staging/prod, standing up a tracking server, evaluating with gates, and serving. Corrects the MLflow 2-era defaults a model reaches for (artifactpath, registry stages and getlatestversions…
Skill Claude Code
Guided workflow for taking any ML codebase — including one with no experiment tracking at all, or one full of MLflow 2-era idioms — to a production-grade open-source MLflow 3 setup with dev/staging/prod environments, registry-based promotion, and served models. Walks seven phases with a developer who may have zero…
Skill Claude CodeCodex
Next.js 16 bundle-size and build-time optimization — runs a data-driven iteration loop: measure baseline → analyze top offenders → apply ONE recipe → re-measure → verify nothing broke (build + types + tests + no regression) → commit or revert. Built for Next.js 16 with Turbopack default, and falls back to webpack-mode…
Skill Claude CodeCodex
Next.js 16 App Router pages mixing static and dynamic content — Partial Prerendering (PPR) under the Cache Components model. Covers enabling it with cacheComponents (the removed experimental.ppr / experimentalppr flags), the dynamic-by-default rendering inversion, the Suspense static-shell/dynamic-hole boundary, the…
Skill Claude CodeCodex
Comprehensive debugging guide for nginx C modules, derived from the official nginx development documentation and production debugging experience. Contains 45 rules across 8 categories, prioritized by impact to guide systematic diagnosis of crashes, memory bugs, and behavioral issues in nginx modules.
Skill Claude CodeCodex
Comprehensive directive design guide for nginx C module authors, focused on creating clear, consistent, and admin-friendly configuration interfaces. Contains 46 rules across 8 categories, prioritized by impact to guide decisions about what to expose, how to name it, and how to evolve it safely.
Skill Claude CodeCodex
Comprehensive performance optimization and reliability guide for nginx C modules, derived from the official nginx development documentation and production engineering experience. Contains 43 rules across 8 categories, prioritized by impact to guide automated optimization and resilience improvements.
Skill Claude CodeCodex
Comprehensive development guide for nginx C modules, derived from the official nginx development documentation and community expertise. Contains 49 rules across 8 categories, prioritized by impact to guide correct module implementation and prevent common crashes, memory leaks, and undefined behavior.
Skill Claude CodeCodex
OpenAI Codex Rust coding patterns distilled from the codex-rs workspace. Use this skill whenever writing, reviewing, or refactoring Rust code — especially for async agents, CLI tools, sandboxing, secret handling, Ratatui TUIs, JSON-RPC protocols, tokio-based services, or any codebase that needs defensive panic…
Skill Claude CodeCodex
Write and refactor TypeScript code in repos that use Effect-TS services, Effect Schema, event-sourced persistence, and barrel-module architecture. Use this skill when implementing features, fixing bugs, writing tests, or refactoring in opencode or any TypeScript codebase built on the same stack (Effect DI via…
Skill Claude CodeCodex
Search relevance and ranking on OpenSearch/Elasticsearch for a two-sided marketplace — candidate retrieval (hybrid BM25 + kNN, RRF, two-tower EBR), base relevance (BM25F, multimatch, LambdaMART), quality signals (Wilson lower bound, Bayesian average, rankfeature saturation/sigmoid), personalization…
Skill Claude CodeCodex
Caching strategies in front of AWS OpenSearch (Elasticsearch) or AWS Personalize — search, recommenders, multi-recommender pages, anon vs logged-in traffic. Covers ROI decision (TPS/minProvisionedTPS, Zipf, amplification), key design (canonicalisation, cohort vs user, solution-version pinning, bucketing)…
Skill Claude CodeCodex
Opinionated, backend-agnostic Next.js 16 (App Router) architecture — authorization at the data layer, server-side loading with cache()+Promise.all, mutations through next-safe-action + typed route handlers, client/server boundaries ('use client' at leaves + TanStack Query), forms with RHF + Zod, UI via shadcn/ui +…
Skill Claude CodeCodex
Orval OpenAPI TypeScript client generation best practices. This skill should be used when configuring Orval, generating TypeScript clients from OpenAPI specs, setting up React Query/SWR hooks, creating custom mutators, or writing MSW mocks. Triggers on tasks involving orval.config.ts, OpenAPI codegen, API client…
Skill Claude CodeCodex
Portuguese personal income tax (IRS / Código do IRS) and Modelo 3 filing — determining tax residency (Art. 16), classifying income by category (rental/Anexo F, capital gains/Anexo G, employment/Anexo A, self-employment/Anexo B, pensions, foreign income/Anexo J), choosing the right annexes, applying current Art. 72…
Skill Claude CodeCodex
Pulumi infrastructure as code performance and reliability guidelines. This skill should be used when writing, reviewing, or refactoring Pulumi code to ensure optimal deployment performance and infrastructure reliability. Triggers on tasks involving Pulumi stacks, components, state management, secrets configuration…
Skill Claude CodeCodex
Drafting Python Enhancement Proposals (PEPs) — proposing a Python language feature, a standard library change, an interoperability standard, or an informational/process document for the Python community. Covers all three PEP types (Standards Track, Informational, Process): choosing the right type, scaffolding a valid…
Skill Codex
Compose new Rails backend pages and refactor existing Rails UI to use premium blocks from templates/application-ui. Use when requests mention ERB views, Rails partials, admin/dashboard screens, Tailwind UI assembly, or replacing custom markup with existing premium blocks while preserving behavior, accessibility, and…
Skill Claude CodeCodex
Ruby on Rails design system guidelines for building consistent, maintainable UI with minimal abstraction. This skill should be used when creating or refactoring Rails views, partials, components, form builders, helpers, Stimulus controllers, Turbo Frames, Turbo Streams, or design tokens. Triggers on tasks involving…
Skill Claude CodeCodex
Ruby on Rails Hotwire best practices for building interactive applications with Turbo Drive, Turbo Frames, Turbo Streams, Turbo 8 morphing, and Stimulus controllers. This skill should be used when writing, reviewing, or refactoring Hotwire-powered Rails code to ensure optimal patterns for navigation, partial page…
Skill Claude CodeCodex
LLM workloads on open-source Ray (pinned to 2.57) — OpenAI-compatible serving with ray.serve.llm (vLLM-backed LLMConfig + buildopenaiapp) and batch inference with ray.data.llm (buildprocessor). Corrects the stale defaults a model produces — the archived ray-llm repo and its YAML configs, hand-rolled vLLM engines…
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: