Loading...
Loading...
Found 80 Skills
Invoke external coding-agent harnesses non-interactively with an explicit model, working directory, prompt, and safety policy. Use when delegating work to Codex, Claude Code, Grok, OpenCode, Cursor CLI, GitHub Copilot CLI, or Cockpit, including from planning or review loops.
Use the `sesh` CLI/TUI to list, find, enter, resume, create, tag, archive, rename, delete, send-to, or inspect coding-agent sessions across machines. Use when the user asks about sesh command usage, the session TUI, entering/resuming a sesh, cross-machine session state, the sesh daemon, or peers.
Use for coding-agent work in Git repos that use or may need Mainline, or when users mention Mainline, intents, agent autonomy, agent_authority, max_autonomy, stop lines, allowed_boundary, inspect_or_stop, before_commit/proposed_intent/opened_pr, current-instruction overrides, commit/seal handoff, push/PR review boundaries, merge/release/deploy boundaries, auto-submit/auto-commit/auto-seal behavior, hooks, proposals, gaps, conflicts, committing, pushing, opening PRs, PR descriptions, or setup.
Authoritative reference for Pi (@earendil-works/pi-coding-agent): install, configure, run, and extend. Use when the user asks about Pi CLI/flags/commands, providers/models/auth, settings/compaction/sessions, security/trust, extensions, skills, prompt templates, themes, packages, custom providers, TUI components, the SDK, RPC mode, or JSON streaming. Also use for Pi's design philosophy and opinionated choices (why minimal, 4 tools, YOLO, no MCP/plan mode/to-dos/sub-agents), the creator Mario Zechner's coding-agent blog post, Pi's internal monorepo architecture (the Chord plugin/service runtime (@earendil-works/chord), the agent harness, facets/services, delta tracking), and the repository's build, development, and contribution rules.
Guide for adding new AI SDK harness packages. Use when creating a new @ai-sdk/harness-<name> package that adapts a coding-agent runtime to HarnessV1.
LLM-as-judge for a coding-agent session or an eval-harness result — checks controller attestations first, then project guards, code review, and the repo's design contract, and names the smallest harness owner to fix. Read-only; never executes session content. Use for "judge this session", "analyze this eval", "oceń sesję/agenta".
Integrate Cartesia speech APIs (TTS, STT, voices) in application code or coding-agent workflows. Use when the user asks about Cartesia REST/WebSocket APIs, SDKs, API keys, Sonic TTS, Ink STT, voice IDs, access tokens, or embedding voice in an app. For Cartesia Line deployed agents, CLI deploy, and telephony, use the cartesia-line skill instead.
Deploy any HuggingFace model to RunPod as a vLLM server, bridge it to Claude Code (which speaks Anthropic's Messages API, not OpenAI's), smoke-test that tool-calling actually works end to end, and tear everything down with zero trace (pod, network volumes, local processes, scratch files). Use this whenever you want to run a model on RunPod, try a model with Claude Code, test whether a HF/GGUF/abliterated checkpoint supports tool use, benchmark a model for coding-agent use, or spin up/kill a disposable GPU inference box. Also trigger it for anything about hooking Claude Code up to a non-Anthropic backend (vLLM, Ollama, LM Studio) via ANTHROPIC_BASE_URL, or questions like 'what GPU do I need to run X' and 'how much will it cost to run this model'.
Use AnalyticsCLI CLI as the deterministic, bounded interface for analytics queries, exports, and SDK validation in coding-agent workflows.
Set up or audit a machine's coding-agent harnesses from one rule table and the user's workstation repo - the shared global instructions every harness reads, the global rules (deny, ask, allow-and-report) each one enforces, the pre-tool hook, memory kept off, declared Codex CLI defaults, and the skills and tools the workstation repo lists to install. Use for a new machine or VPS, to audit this machine's agent setup, or when another skill says to check the machine.
Reconstructs or writes a coding-agent handoff from git and `.agents/handoff.md`. Use when the user is about to switch coding agents (Claude Code, Cursor, Codex, Antigravity), a usage limit expired, or a new agent is picking up in-progress work.
Investigates the context economics of your own coding-agent sessions in LangWatch. Reads real sessions to find where carrying a fat context stops paying for itself, measured in cache rebuilds, compactions and cost per turn, and delivers a report with the context size your sessions should stay under, with example sessions behind every claim. Use when coding-agent sessions feel expensive or degrade as they grow.