123 tagged pi agent, measured the same way as everything else here.
Browse within: coding-agent 50bun 44extensions 44npm 44npm-packages 44packages 44pi 39pi-coding-agent 39pi-package 18pi-dev 10pi-extension 8repoprompt 8lobehub 6skill 6
Skill Claude CodeCodex
A development guide for the pi-agent software kit, used to build and customize coding agents. It covers agents, tools, prompts, sessions, models, authentication, and connected files.
Skill Claude CodeCodex
A guide for adding a new external coding agent, called a harness, to the codexhost system. It explains how that agent should connect to the system's existing shared interfaces and capabilities.
Skill Claude CodeCodex
Diagnose whether a Codex Desktop update changed codexhost Composer/CDP bindings, private Renderer DOM or React state, Host bridges, routing, or injected UI. Use after an installed Codex update or when compatibility regresses and the affected surface is unknown.
Skill Claude CodeCodex
Automated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue end-to-end → review with /review-it → document with /note-it → ship with /ship-it → repeat. Persists state to .loop-state.json for crash recovery. Triggers on: loop-it, loop issues, auto…
Skill Claude CodeCodex
Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code"…
Skill Claude CodeCodex
Detect software architecture bad smells, algorithmic complexity hotspots, and anti-patterns in a codebase. Produces a detailed markdown report identifying violations of architectural principles, design patterns, code quality, and performance complexity. Triggers on: smell, code smell, architecture smell, find…
Skill Claude CodeCodex
A fixture skill proving Pi package skills are discoverable and loadable in DSH.
Skill Claude CodeCodex
Review prose written for others -- user-facing docs, prompts for other LLMs, inline comments, docstrings, and other-facing messages -- for local jargon leakage, orphaned references, missing grounding, and audience or genre misfit.
Skill Claude CodeCodex
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
Skill Claude CodeCodex
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
Skill Claude CodeCodex
Create or bootstrap an Elixir/Phoenix project or package with Igniter and VibeKit. Use only for new-project generation or applying initial quality/tooling setup; use elixir for an existing backend project and elixir-web for existing UI/frontend work.
Skill Claude CodeCodex
Existing Phoenix/LiveView UI and frontend work: HEEx/components, styling, assets, browser behavior, runtime UI feedback, PhoenixReplay, Volt, icons, Tailwind, and interactive verification. Use instead of elixir when UI/frontend behavior is the primary task; not for project creation.
Skill Claude CodeCodex
Existing Elixir application/library development and debugging. Use for .ex/.exs, Mix, OTP, Ecto, backend Phoenix, dependencies, docs, tests, or BEAM runtime state. Use elixir-web instead when the primary task is UI/LiveView/frontend work, and elixir-new-project instead for creation/bootstrap.
Firstp1ck/pi-coding-agent-forge
Skill Claude CodeCodex
Creates polished self-contained HTML explanation reports for complex, multi-step topics using overview tables, evidence cards, adaptive graphs or diagrams, meaningful SVG/media, and accessible tabs for long pages. Use when the user requests a browser-readable diagnostic report, technical guide, decision analysis…
Firstp1ck/pi-coding-agent-forge
Skill Claude CodeCodex
Delegation admissibility governance for a parent orchestrator. Use when deciding whether to launch, sequence, replace, or accept one or more delegated child runs while preserving role fit, plan-backed worker contracts, one-writer isolation, bounded retry safety, and reviewer finding disposition. Covers admissibility…
Firstp1ck/pi-coding-agent-forge
Skill Claude CodeCodex
Agents should invoke this skill for Tauri + Django + React desktop apps, especially backend lifecycle, CORS/auth, frontend integration, mandatory light/dark theming, German/English i18n, build packaging, dual desktop/web deployment, Rust commands, and platform-specific gotchas.
Skill Claude CodeCodex
Ask which skill or flow fits your situation. A router over the skills in this repo.
Skill Claude CodeCodex
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Skill Claude CodeCodex
Teach the user a new skill or concept, within this workspace.
Skill Claude CodeCodex
Explicit command-style skill for implementing approved SDD tasks from tasks.md with tight scope, tests, and verification evidence. Use only when the user explicitly asks to execute or implement a specific approved SDD task or feature. Do not auto-load for discussion, planning, review, or unapproved tasks.
Skill Claude CodeCodex
Explicit command-style skill for initializing or adopting SDD in a project by creating or preparing .ai/, .ai/steering/, and .ai/sdd/. Use only when the user explicitly asks to initialize, set up, adopt, or bootstrap SDD. Do not auto-load for general planning, feature specs, status checks, or implementation.
Skill Claude CodeCodex
Explicit command-style skill for inspecting .ai/sdd state and recommending the next safe action. Use only when the user explicitly asks for SDD status, progress, blockers, readiness, or next action. Do not auto-load for general SDD work; do not create specs or implement code.
Skill Claude CodeCodex
Work with Figma .fig design files and the running OpenPencil editor — inspect structure, query nodes, analyze design tokens, export PNG/SVG/PDF/JSX, and modify designs programmatically. Use when asked to open, inspect, export, analyze, or edit .fig files, or to control the running OpenPencil app.
Skill Claude CodeCodex
Use this skill to send a prompt to ChatGPT and get a response. Triggers when the user wants to query ChatGPT, use ChatGPT as an external AI worker, or when the web-ai-router directs a task to ChatGPT. Best for general QA, writing, coding, and creative tasks. Requires login — session is persisted in Chrome profile.