dotfiles

Use when building, reviewing, debugging, or documenting Python applications that use the OpenAI Codex Python SDK, especially the openai-codex package, openai_codex imports, Codex or AsyncCodex clients, threads, turns, streaming, login flows, sandbox access, SDK examples, or the openai-codex-cli-bin runtime package. Use this skill for Codex Python SDK questions even when the user only says "Codex SDK" in a Python context.

Use when the user asks Codex to teach, quiz, review, or build mastery from a prior session, topic, transcript, file, or work artifact. Run a Socratic teaching loop that sources the real material, creates a progress checklist, asks one question at a time, confirms understanding item by item, and does not finish until every concept is confirmed.

Use when building, reviewing, debugging, or documenting Python Temporal SDK code or Python Temporal applications, especially Workflows, Activities, Workers, Temporal Clients, task queues, Workflow Streams, LLM output streaming, Signals, Queries, Updates, schedules, retries, error handling, data conversion, observability, testing, sandbox determinism, sync-vs-async Activity choices, or code using the `temporalio` Python package.

Use when Codex needs to crawl, inspect, or summarize a documentation website, GitHub docs tree, or local docs folder and produce a relevance-ranked page index, doc-map, source guide, or shortlist of important documentation pages. Trigger for documentation discovery, docs indexing, source-map creation, llms.txt alternatives, docs skill scaffolding, or choosing the most relevant pages from standalone docs sites or repository documentation folders.

Use when building, reviewing, debugging, or migrating Effect TypeScript code and needing idiomatic implementation guidance backed by current official docs. Trigger for Effect, effect/Schema, Effect.gen, pipe, Runtime, ManagedRuntime, Layer, Context.Tag, Config, Scope, Schedule, Stream, Sink, Queue, PubSub, Fiber, Cause, Exit, Option, Either, Effect AI, @effect/platform, Micro, or TypeScript imports from the `effect` ecosystem.

Use when answering TiDB documentation questions or locating official PingCAP docs for TiDB Self-Managed, TiDB Cloud adjacency, architecture, deployment, migration, TiCDC, DM, TiUP, TiFlash, SQL/reference, performance tuning, troubleshooting, monitoring, backup/restore, vector search, MySQL compatibility, or best practices. Fetch current docs.pingcap.com pages or llms.txt before precise claims; hand off to tidb-sql, tidb-query-tuning, or tidb-mysql for task-specific SQL, query-plan, or MySQL-compatible implementation work.

Design, build, review, or debug article and web demos across the full range from static to live: semantic HTML/CSS layouts, responsive components, design systems, Grid/Flexbox, accessibility AND interactive Canvas 2D, SVG, WebGL/Three.js, physics/mechanical simulations, sliders, scrubbers, requestAnimationFrame loops, React/MDX/Deno/TanStack embeds. Use when building a non-interactive figure or page layout, a live model-driven explainer (Bartosz Ciechanowski style), or anything between. Keywords: demo, graphics, canvas, WebGL, Three.js, animation, simulation, HTML, CSS, layout, Grid, Flexbox, semantic markup, responsive, accessibility, interactive explainer.

Design, build, review, or debug article-embedded interactive graphics demos: Canvas 2D, SVG, WebGL/Three.js, mechanical/spatial simulations, physics explainers, sliders, scrubbers, requestAnimationFrame loops, React/MDX embeds, and Deno/TanStack Start prerender-safe blog integrations. Use when Codex needs to create Bartosz Ciechanowski-style visual explanations, live model-driven diagrams, or custom graphics engines for blog posts.

Use for guarded stacked pull request workflows with kitlangton/stack in GitHub squash-merge repos, especially PR-base sync, root merges, undo, and stacked PR repair.

Use when Codex is building, styling, or reviewing frontend UI where motion, micro-interactions, component feel, animation performance, or interaction polish matters. Triggers include animation timing/easing, popovers, dialogs, drawers, toasts, tabs, tooltips, hover/active states, drag or swipe gestures, reduced-motion behavior, Framer Motion or CSS transition choices, and requests to make an interface feel more polished or responsive.

Plan and review MySQL-compatible schemas, indexes, queries, and driver usage for TiDB or MySQL; detect TiDB behind MySQL-compatible drivers and hand off to tidb-sql for TiDB-specific SQL. Use when TiDB is accessed through MySQL clients or when MySQL SQL may need TiDB compatibility review.

Diagnose and optimize slow TiDB queries using optimizer hints, session variables, join strategy selection, subquery optimization, and index tuning. Use when a query is slow, produces a bad plan, or needs performance guidance on TiDB.

Write, review, and adapt SQL for TiDB with correct handling of TiDB-vs-MySQL differences (VECTOR type + vector indexes/functions, full-text search, AUTO_RANDOM, optimistic/pessimistic transactions, foreign keys, views, DDL limitations, and unsupported MySQL features like procedures/triggers/events/GEOMETRY/SPATIAL). Use when generating SQL that must run on TiDB, migrating MySQL SQL to TiDB, or debugging TiDB SQL compatibility errors.

Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.

Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use Swift Testing.

Writes, reviews, and improves SwiftData code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use SwiftData.

Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or reviewing SwiftUI projects.

Answer questions about how the pi coding agent itself works by reading pi's bundled offline docs and citing the file. Use when asked how pi does X, how to configure pi (settings.json, models.json, providers, keybindings), what a pi flag/mode/feature does, or where a pi feature is documented. Keywords pi docs, how does pi, configure pi, pi settings, models.json, pi providers, pi extensions, pi sessions, pi modes, pi skills.

Author Agent-Skills-standard SKILL.md files designed to be executed by the pi coding agent — often a small local model (llama.cpp/Qwen). Covers pi skill anatomy and discovery, writing low-freedom procedures with machine-checkable validators for small executors, the author-pilot-refine distillation loop driving pi headlessly, and optional Codex co-authoring. Use when writing or refining a skill that pi will run, or when asked to make a skill work well on a local model. Keywords pi skill, SKILL.md, pi coding agent, local model, llama.cpp, qwen, skill distillation, /skill, pilot, refine.

Use the pi coding agent CLI (@earendil-works/pi-coding-agent) and navigate its docs and source. Covers interactive/print/json/rpc modes, model & tool flags, sessions, custom models.json (local llama.cpp/Ollama/vLLM), skills, extensions, and the pi-mono monorepo layout. Use when running `pi`, driving it headlessly/programmatically, configuring local models, writing pi extensions/skills, or answering "how does pi do X". Keywords pi, pi.dev, pi coding agent, earendil, pi-mono, llamacpp, models.json, rpc mode, json mode, qwen.

Reference for Claude Code features and best practices: writing CLAUDE.md, skills, hooks, sub-agents, agent teams, headless mode, scheduled tasks, worktrees, batch, frontend verification. Use when authoring/auditing CLAUDE.md, configuring Claude Code, writing skills, or orchestrating agents. Keywords CLAUDE.md, skill, hook, sub-agent, agent team, headless, worktree, /loop.

Design, build, review, or debug article and web demos across the full range from static to live: semantic HTML/CSS layouts, responsive components, design systems, Grid/Flexbox, accessibility AND interactive Canvas 2D, SVG, WebGL/Three.js, physics/mechanical simulations, sliders, scrubbers, requestAnimationFrame loops, React/MDX/Deno/TanStack embeds. Use when building a non-interactive figure or page layout, a live model-driven explainer (Bartosz Ciechanowski style), or anything between. Keywords: demo, graphics, canvas, WebGL, Three.js, animation, simulation, HTML, CSS, layout, Grid, Flexbox, semantic markup, responsive, accessibility, interactive explainer.

Use when explaining, designing, reviewing, or debugging general Temporal concepts from docs.temporal.io, including Temporal Platform architecture, Workflows, Workflow Execution, Activities, Workers, Event History, failure detection, Workflow message passing, Child Workflows, Temporal Service, Namespaces, Task Queues, durable execution, replay, determinism, Signals, Queries, Updates, retries, and timeouts. Fetch current official Temporal docs and inspect embedded page links before giving precise guidance; use SDK-specific skills only when exact language APIs or code semantics are the main task.

Write, run, debug, package, and make reproducible standalone Python scripts with uv. Use when authoring uv scripts, adding PEP 723 inline metadata, choosing uv run/init/add --script forms, building shebang executables, locking scripts for reproducibility, handling uv cache or CI cache behavior, or picking lightweight script dependencies. Keywords: uv, uv run, uv script, PEP 723, inline metadata, standalone python script, requires-python, uv lock --script, uv add --script, shebang, hook script.

Author and run a dynamic workflow — orchestrate many parallel subagents via the Workflow tool to be comprehensive, confident, or to take on scale one context can't hold. Use for codebase audits, large migrations, multi-source research, high-stakes verification, or any task worth fanning out across dozens of agents. Keywords dynamic workflow, Workflow tool, fan out, orchestrate subagents, parallel agents, migration, audit, multi-agent.

Use when structuring, styling, reviewing, or teaching HTML and CSS for components, layouts, responsive pages, design systems, semantic markup, Grid, Flexbox, cascade architecture, accessibility, visual hierarchy, or clean frontend design. Browse current official HTML, CSS, MDN, web.dev, W3C, WCAG, and ARIA docs before giving precise guidance or making layout decisions.

Use when running a bounded, metric-driven improvement loop in Codex: define a goal, scope, metric, verify command, guard command, and stopping rule, then iterate with one focused change at a time, keeping only verified improvements. Trigger for autoresearch, scored improvement loops, modify-verify-keep/discard, benchmark-driven fixes, iterative debugging, experiment logs, or evals over prior run artifacts.

Browser-based job application workflow using Codex app Computer Use. Use when the user asks Codex to help apply to a job posting, fill a Greenhouse/Lever/Ashby/Workday-style application, upload a resume, navigate a job board form, or submit an application through a local browser while preserving sensitive-data and final-submit confirmation boundaries.

Use when explaining, designing, reviewing, or debugging general Temporal concepts from docs.temporal.io, including Temporal Platform architecture, Workflows, Workflow Execution, Activities, Workers, Event History, failure detection, Workflow message passing, Child Workflows, Temporal Service, Namespaces, Task Queues, durable execution, replay, determinism, Signals, Queries, Updates, retries, and timeouts. Fetch current official Temporal docs and inspect embedded page links before giving precise guidance; use SDK-specific skills only when exact language APIs or code semantics are the main task.

Allows you to view the user's screen as well as several hours of history. Use when the user makes a reference to their recent work, for which it'd be helpful to see the screen. This skill MUST be used whenever you need to resolve ambiguity in a user request, where the user hasn't specified enough context to do the task. Examples include disambiguating the specific user/app/document/error the user is referring to. You must also use this skill if the user asks about any question regarding Chronicle or asks what you can see from the screen.

Use when studying, explaining, designing, reviewing, or implementing data systems concepts including stream processing, replication, partitioning, transactions, isolation, consistency, consensus, failure detection, gossip, CRDTs, storage engines, pages, slotted pages, B-Trees, WAL, ARIES, MVCC, LSM trees, SSTables, compaction, Bloom filters, Merkle trees, checksums, compression, columnar storage, and database testing.

Create, edit, validate, and explain Mermaid diagrams and .mmd files, including flowcharts, architecture-beta diagrams with Iconify software icons, sequence diagrams, state diagrams, ERDs, C4-style views, data pipelines, event streams, and system architecture diagrams. Use when Codex needs Mermaid syntax, markdown fenced mermaid blocks, standalone .mmd examples, renderer guidance, or real software icon guidance for tools such as Postgres, MySQL, Temporal, Kafka, Redis, DragonflyDB, Redpanda, TiDB, Flink, Spark, and HDFS.

Strict maintainability and structural code review. Use when Codex is asked to review code, review a PR or current branch, perform a deep code quality audit, run a harsh or thermonuclear review, evaluate abstraction quality, detect spaghetti growth, or push for simpler implementation structure.

Use when driving browser sessions with the `playwright-cli` command, inspecting pages through snapshots and element refs, debugging or generating Playwright tests, recording traces or video, mocking requests, managing storage state, or attaching to `npx playwright test --debug=cli` sessions.

Use when configuring, debugging, or documenting Portless for local development: stable named .localhost URLs, portless CLI usage, HTTPS/local CA setup, custom TLD or LAN mode, Tailscale sharing, monorepo or git worktree routing, package.json/portless.json configuration, static aliases, hosts cleanup, or replacing localhost port numbers in dev scripts.

Brainstorm useful Codex skills for this repository from real project context. Use when identifying recurring workflows, drafting project-local or global skills, or replacing ad hoc prompts with durable skills.

Route dotfiles configuration changes to the right project-local skill. Use for fish, Ghostty, lazygit, Neovim, Starship, Zed, Zellij, or cross-platform config edits in this repository.

Ensure cross-platform compatibility across macOS (Intel/ARM), Ubuntu, and Fedora for this dotfiles repository. Detects and auto-fixes hardcoded paths, platform-specific assumptions, package availability issues, and test coverage gaps. Use when adding features, updating configs, bumping Nix flake, or investigating platform-specific bugs. Keywords: cross-platform, compatibility, macOS, Linux, Ubuntu, Fedora, platform, portability, Nix flake, Docker test, CI

Expert Fish shell configuration including config files, functions, abbreviations, prompts, environment variables, and scripting. Use when setting up Fish, creating aliases/functions, writing Fish scripts, configuring prompts, or migrating from bash. Keywords: fish shell, fish config, alias, abbr, function, prompt, fish script, config.fish, autoload

Configure and optimize Ghostty terminal with themes, fonts, keybindings, and performance settings. Use when setting up Ghostty, creating terminal configs, customizing keybinds, or troubleshooting terminal behavior. Keywords: ghostty, terminal, config, keybind, theme, font, terminal config, ghostty.conf