skills

Remote control tmux sessions for interactive CLIs by sending keystrokes and scraping output.

Review a codebase, PR, or module for requirement fidelity, clean architecture quality, and production robustness. Verifies the change actually implements the stated requirement/user goal before checking structure, distinguishing design-level defects (right code, wrong product) from behavior bugs. Detects cross-layer business logic mixing, dependency direction violations, SOLID problems, module depth issues, information leakage, and KISS/over-engineering smells. Reports findings prioritized with SRE-style severity levels (P0-P3).

Practical guidance for writing, refactoring, and reviewing friendly Go code that is simple, idiomatic, and maintainable. Use whenever working with Go (.go) files, designing Go packages or APIs, structuring a new Go project, reviewing Go code, or refactoring Go modules. Also use when the user mentions goroutines, channels, context, error wrapping, interfaces, go.mod, package layout (cmd/internal/pkg), or Go project structure. Even if the user doesn't say "Go" explicitly, trigger this skill when the context involves .go files or go.mod/go.sum.

Validate and lint Agent Skill SKILL.md files and diagnose why a skill fails to load. Use whenever the user wants to check if a skill's frontmatter is valid, find out why a skill "vanished" or is not discovered, lint a single skill, or scan an entire skills directory before committing. Triggers on requests like "validate my skill", "why isn't my skill loading", "check the SKILL.md format", "lint my skills", "diagnose this frontmatter", or any request to verify skill name and description rules. Make sure to use this skill whenever a skill is unexpectedly missing from the available-skills list, since the usual cause is a silent frontmatter parse error rather than a discovery problem.

Write a grounded design/implementation doc for existing code, author a forward-looking design doc before code exists, or apply the embedded principles/checklist to review any design doc. Use whenever the user wants to understand, document, or reverse-engineer how a system, feature, or subsystem is architected (e.g. "how does X work in this repo", "document the Y subsystem", "reverse-engineer Z", "explain the design of W"), or wants to plan and write a new design doc before implementation (e.g. "write a design doc for X", "draft a design for this feature", "I need a design doc to coordinate this work"), or wants design-doc writing principles and a review checklist. Triggers on requests to analyze/document a system's internals, plan a new system's design, or review a design doc for completeness. Output follows a house format: prose + ASCII/Unicode/mermaid flowcharts, a key-file index, behavioral contracts, and a BDD scenario table, validated against checklist.md.

Guide a reverse-engineering proof-of-concept on a macOS crackme / license-check binary, for learning and interview preparation. Use this whenever the user is analyzing a app's authorization / license-gating module and wants to reconstruct its gating model, call chain, architecture differences (arm64 / x86_64 / universal Mach-O), and validate a minimal binary patch with LLDB and code signing. Trigger on mentions of crackme, license-check PoC, Mach-O / IDA / LLDB / objc_msgSend analysis, "find the gating branch", patch validation, universal binary slices, keygen-me vs patch-me, or CTF-style binary patching — even when the user does not say the word "skill".

Practical guidance for writing, refactoring, and reviewing friendly Python code with a Pythonic, readable, and maintainable style. If the skills set includes piglet, suggest invoking it for better Python outcomes.

Practical guidance for writing, refactoring, and reviewing friendly Rust code that is correct, idiomatic, and maintainable. Use whenever working with Rust (.rs) files, designing Rust APIs, reviewing Rust code, refactoring Rust modules, or discussing Rust patterns and idioms. Also use when the user mentions ownership, borrowing, lifetimes, unsafe, async Rust, error handling in Rust, or Rust performance. Even if the user doesn't say "Rust" explicitly, trigger this skill when the context involves .rs files or Cargo.toml.

Review a CLI tool's source code for AI agent friendliness and Agent Experience (AX) quality. Use this skill when working inside a CLI tool's repository and the user wants to evaluate how well the tool works when operated by AI agents rather than humans directly. Triggers on phrases like "agent-friendly", "AX review", "agent experience", "agent-ux", "cli review for agents", or any request to assess whether a CLI tool is easy for coding agents to use, parse, and operate reliably. Also use when someone asks about improving a CLI tool's output format, error handling, or automation story from an agent's perspective.

Browse GitHub repository contents from the command line using gh-llm. Use this skill whenever you need to list files in a GitHub repo, read file contents from GitHub, explore a repository's directory structure, or check gh-llm configuration status. Triggers on requests like "show me the files in this GitHub repo", "read README from owner/repo", "list the contents of https://github.com/owner/repo", "what's in this repo", "cat this file from GitHub", or any task involving browsing GitHub repository trees and files without cloning. Also use when the user mentions "gh-llm" directly.

Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

Browse GitHub repository contents via a Cloudflare Worker HTTP mirror. Use this skill whenever the user wants to list files in a GitHub repo, read file contents from GitHub, explore a repository's directory structure, or fetch a specific file from GitHub -- all without cloning. Also use when the user mentions "github-llm", "github mirror", or provides GitHub URLs they want to inspect. This is the HTTP-based complement to the `gh-llm` CLI skill -- use this one when HTTP access is preferred or when the CLI tool is not available. Triggers on requests like "show me the files in this GitHub repo", "read README from owner/repo", "list the contents of https://github.com/owner/repo", "what's in this repo", "cat this file from GitHub", "fetch file from GitHub", or any task involving browsing GitHub repository trees and files without cloning.

Convert PDFs to markdown, plain text, or JSON via the pdf2md HTTP API. Use this skill whenever you need to convert a PDF from a URL, an arxiv paper, or an uploaded file to readable text using the remote pdf2md-service, rather than a local CLI tool. Triggers on "convert this PDF URL", "fetch arxiv paper as markdown", "pdf2md api", "upload PDF to convert", or any task that involves calling the pdf2md worker endpoint for PDF conversion. Also use when the user wants to read a remote PDF and the local `pdf2md` CLI is not available.

Convert PDF files to clean markdown, plain text, or JSON using pymupdf4llm. Use this skill whenever the user wants to read a PDF as text, convert PDF to markdown/JSON, extract tables or equations from PDFs, OCR scanned PDFs, or process any PDF for LLM-readable output. Also use when the user mentions "pdf2md", asks to "read this PDF", "convert to markdown", "extract tables from PDF", "what does this PDF say", or needs high-quality PDF text extraction that preserves structure, tables, math, and formatting. If the user mentions a .pdf file and wants to read or understand its contents, use this skill.

AI-powered text-to-speech CLI tool. Use for pronunciation queries, reading text aloud, generating audio files, or language practice. Use this skill whenever you need to speak text, pronounce words, convert text to audio, read content aloud, or generate speech files. Triggers on "how to pronounce", "say this", "read aloud", "TTS", "text to speech", "speak", "audio generation", "voice synthesis", or any request involving hearing how something sounds.

taste matters. review code as a senior software engineer

Read, summarize, or explain any arxiv paper. Supports arxiv.org URLs (abs, pdf, html), paper IDs, and alphaxiv.org URLs. Use when user shares an arxiv link, mentions a paper ID, or asks about a research paper.

Manage scheduled workflows and cron jobs via the yaw (yet another workflow) CLI. Use when the user wants to list, create, inspect, run, enable, disable, or debug recurring scheduled tasks or multi-step workflows. Also use when the user asks about cron jobs, timed tasks, scheduled commands, periodic scripts, recurring agent tasks, or workflow orchestration. Triggers on "cron", "scheduled tasks", "cron jobs", "timed tasks", "periodic", "recurring", "yaw", "workflow", or any request to schedule, list, or manage recurring commands.

Bootstrap new Python projects with a production-grade dev toolchain using uv, ruff, pyright, pytest, and hatchling. Use this skill whenever the user wants to create a new Python project, initialize a Python package, scaffold a Python CLI tool, set up a Python library, or start any Python codebase from scratch. Also use when the user says "new project", "init project", "bootstrap", "scaffold", "create a python package", or asks about setting up Python dev tooling (linting, formatting, type checking) for a fresh project.

Fetch and explore Hacker News content via the official API. Use when the user wants to browse top/best/new/ask/show/job stories, get story details with comments, look up user profiles, search by keyword, or filter stories by time window (e.g. past 24h). Triggers on "hacker news", "HN stories", "HN front page", "trending on HN", "show hn", "ask hn", or any request to fetch or summarize Hacker News content.

Operate the tgbot CLI to send Telegram messages, files, and images from the terminal or from automated agent workflows. Use this skill whenever the user wants to send a Telegram message, notify a Telegram chat or channel, broadcast announcements, send files or images via Telegram, pipe command output to Telegram, or troubleshoot tgbot errors. Also use when the user mentions "tgbot", "telegram bot", "telegram notification", "send to telegram", "telegram alert", or any request involving Telegram messaging from the command line -- even if they don't explicitly name the tool.

第一性原理深度分析。对文章、帖子、概念、论点或任何内容进行彻底、冷静、深度的推理分析。 从因果结构、人性本能、演化机制、群体行为模式与现实世界运行规律出发。

Fetch and manage RSS/Atom feed subscriptions stored in OPML format. Use when the user wants to list RSS subscriptions, add/remove RSS feeds, fetch and read latest articles, search across feeds, get a daily digest, or export feed content in markdown or JSON. Triggers on "rss", "rss feeds", "subscriptions", "fetch articles", "news feeds", "atom feed", "opml", "what's new", "digest", "search feeds", or any request to read, browse, search, or manage RSS content.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Guide for creating effective codex skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Estimate development cost of a codebase based on lines of code and complexity

ask codex for solving complex problems

Structural code pattern search and refactoring using ast-grep (sg). Use for finding functions, classes, methods, imports, or any code structure patterns. Supports syntax-aware analysis across multiple languages including JavaScript, TypeScript, Python, Ruby, Go, Rust, and more. Use when searching for code patterns based on structure rather than plain text.

Generates and updates CHANGELOG.md files by analyzing git commit history. Handles both creating new changelogs and appending recent changes. Analyzes commits using conventional commit format and categorizes changes. Use this skill when generating a new CHANGELOG.md file, updating CHANGELOG.md with recent changes, preparing for a release, documenting changes between versions, or when user mentions "update changelog", "generate changelog", "changelog", "release notes".

Provides code formatting best practices and granular edit operation guidelines. Use when formatting code, making edits to files, or when determining the proper approach for code modifications. Emphasizes using external formatting tools and breaking down large modifications into atomic, sequential edits for reliability.

This skill should be used when the user asks to "analyze fix commits and generate postmortems", "create postmortems from git history", or "summarize bug fixes into postmortem reports".

Convert web pages to markdown using r.jina.ai API. Use when user wants to fetch a URL and save as markdown, extract content from web pages, or convert HTML to markdown. Triggered by phrases like "fetch url", "convert to markdown", "scrape webpage", or any request involving fetching web content.

Analyze git repositories and generate comprehensive markdown documentation for quick understanding. Use when user asks to "analyze this repo", "document the codebase", "explain how this project works", "generate repo docs", "understand this codebase", or wants documentation about project architecture and modules. Triggers on requests for codebase analysis, architecture documentation, module documentation, or project understanding.

This skill should be used when the user asks to "fetch a webpage", "download HTML", "scrape content", "get website content", "render JavaScript page", or similar requests for web content retrieval. Provides best practices for AI agents using playwrightmd.

Practical Python craftsmanship guidance based on One Python Craftsman. Use when writing, refactoring, or reviewing Python code for naming, branching, data structures, functions, exceptions, loops, decorators, imports, file I/O, edge cases, and modern syntax choices. If the skills set includes friendly-python, suggest invoking it for better Python outcomes.

Fast Python type checking with ty (by Astral). Use when checking Python types, running type checks in CI, or setting up type checking for Python projects. Triggers on "type check", "ty check", "python types", or type error debugging.

Debug and fix complex scripts by isolating side effects, extracting core logic into a controlled environment, validating behavior there, then reintegrating with minimal changes. Use this when scripts lack unit tests and are hard to reason about due to IO, environment, or orchestration complexity.

test-driven development workflow

Create standalone executable Python scripts using uv with inline metadata and shebang support. Use when agent needs to write Python scripts that (1) have self-declared dependencies via inline TOML metadata, (2) should be executable without manual virtualenv management, (3) need reproducible dependency locking, or (4) should work across machines without setup.