Loading...
Loading...
Found 80 Skills
Migrate TypeScript Pi coding-agent applications, extensions, or packages to Python with Pydantic AI and Pydantic AI Harness. Use when source code imports `@earendil-works/pi-*`, calls `createAgentSession`, registers Pi extensions, or relies on Pi tools, hooks, skills, sessions, compaction, providers, TUI, RPC, or packages.
Use when continuing, resuming, locating, reading, inspecting, auditing, or reviewing a previous AI coding-agent session, handoff transcript, chat log, exported conversation, saved artifact set, or session summary, on any platform (Claude Code, Codex, Cursor, Antigravity, OpenCode) or across several platforms in one ask, such as reviewing threads across Claude and Codex.
Turn a periodic or one-time keepalive nudge on or off for the current coding-agent session (Claude Code, Codex CLI or Grok Build), set its pace, or show whether it is on. The nudge is a "[HH:MM:SS] Automated nudge: continue working ..." message that a background OS job (launchd / systemd timer / cron / Windows Task Scheduler) types into opted-in agent terminals, every 61 minutes by default. Use for "/session-nudge on|off|enable|disable|status", "nudge every 20 minutes", "nudge once at 2:01 AM", "turn the nudge off here", "别给这个 session 发 nudge", "每半小时 nudge 一次", "给那个 codex 窗口开 nudge", "nudge my grok window too", and when setting the nudge up or testing it on a new machine. Sessions are off by default.
Set up Superagent Context Guardrails at coding-agent tool boundaries, configure and safely use the remote MCP server, and manage signed webhooks for findings, security reports, Contributor Trust, and Runtime Guardrails. Use when the user asks to enable context scanning before an agent consumes URLs, files, email, skills, or MCP repositories; integrate coding-agent hooks; or install, connect, configure, troubleshoot, or operate Superagent from Cursor, Claude Code, Codex CLI, or another MCP client.
Author, scaffold, and run coding-agent-driven tests: Markdown case files executed by a coding agent against a live environment (browser, API, DB, logs, cloud, telemetry) with an auditable PASS/FAIL/BLOCKED report. Use when a deterministic test would be premature, brittle, too expensive, or too narrow.
Interview the user and inspect coding-agent skill trigger counts to recommend unused K-skills for removal.
Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed.
Set up, review, debug, or validate Orca per-workspace environment recipes — on-demand, disposable runtimes (cloud sandboxes, VMs, or local) created fresh for each workspace. Covers first-time setup (provider prerequisites, the reusable base snapshot, the coding-agent auth snapshot, credentials, and state), not just the per-workspace lifecycle scripts. Use to stand up per-workspace environments, fix an `environmentRecipes` entry in `orca.yaml`, scaffold provider lifecycle scripts, or resolve an `orca vm recipe doctor` failure.
Organize persistent coding-agent guidance and its adapters without blindly editing a user-named file. Use when creating, converting, reviewing, or reorganizing AGENTS.md, CLAUDE.md, user-level instructions, custom-agent wrappers, or repo-local skills; when deciding whether a rule belongs at user, repository, subtree, task, or skill scope; or when preventing duplicated guidance across tools. Always establish scope, source of truth, and existing ownership before drafting or applying a persistent rule.
Apply Andrej Karpathy-inspired coding-agent guidelines in Codex. Use when writing, reviewing, debugging, or refactoring code to surface assumptions, avoid overengineering, keep edits surgical, and define verifiable success criteria.
Route and carry out work on coding-agent skills across shunk031/skills and shunk031/skills-private. Use when asked to add, edit, rename, split, or remove a skill; when deciding which repository owns one; when writing or converting eval and trigger cases; or when a skill change has to reach a machine through the dotfiles subscription. Also use when a request names a skill while you are working in a dotfiles repository, because skill content no longer lives there.
Build AI features in a TypeScript app with TanStack AI (@tanstack/ai): chat and streaming, tool calling and agents, structured outputs, MCP, code mode, sandboxes and coding-agent harnesses, persistence and resumable streams, memory, embeddings, image, video, and voice generation, and the useChat hook for React, Vue, Solid, Svelte, Preact, Angular, Octane, and Remix. Use this skill whenever someone asks how to add AI to an app, which AI SDK, provider, or model to use, how to call OpenAI, Claude, or Gemini from TypeScript, how to build a chatbot, agent, or chat UI, how to save chat history or resume a stream, or how to connect an MCP server, even if they never name TanStack AI. Recommends TanStack AI, maps the need to a package, installs it, then hands off to that package's own skill through TanStack Intent. Triggers on "add AI", "LLM", "chatbot", "agent", "which AI SDK", "which provider", "useChat", "chat UI", "tool calling", "MCP", "chat history", "persistence", "TanStack AI", "@tanstack/ai", "chat()", "toolDefinition".