Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Author Hermes Agent skills (SKILL.md) for `~/.hermes/skills/` or dotfiles-tracked external dirs. Covers frontmatter, conditional activation via toolset fallbacks, progressive disclosure with references/templates, and the hermes skills CLI. Keywords hermes skill, SKILL.md, ~/.hermes/skills, skill_manage, external_dirs, fallback_for_toolsets.
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.
Claude Agent SDK (Python/TypeScript) — building programmatic agents with claude-agent-sdk. Covers query(), ClaudeSDKClient, custom tools, hooks, permissions, sessions, subagents, structured outputs, file checkpointing, skills, slash commands. Auto-loads on claude_agent_sdk imports. Keywords claude-agent-sdk, query, ClaudeSDKClient, custom tools, mcp server, subagents.
Create global Codex skills distributed through this dotfiles repository. Use when adding reusable Codex workflows under config/codex/skills or adapting a project-local skill for global use.
Manage Hermes Agent profiles — isolated `~/.hermes/profiles/<name>/` envs with per-profile config, SOUL.md, memory, sessions, gateway. Use for create/clone/switch/export/import profiles or configuring per-profile messaging gateways. Keywords hermes profile, -p, --profile, HERMES_HOME, gateway install.
Manage local LLMs on Apple Silicon (M5 Max). Start/stop inference servers, pull models, benchmark, configure coding-agent harnesses, troubleshoot. Keywords ollama, mlx, mlx-lm, llama.cpp, gguf, local llm, inference, quantization, apple silicon, hermes agent, opencode, aider, MoE, prefill.
Define or audit a safe Codex loop contract: observable baseline, bounded action, one-writer ownership, evidence ledger, verification, budgets, plateau rules, terminal states, and final proof. Use for monitoring, optimization, repair, research, recurring automation, or supervisor/worker loops. This is a baseline reference, not a task runner.
Convert a reusable command idea into a global Codex skill in config/codex/skills. Legacy name for users who ask to create global slash commands; create skills instead.
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.
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.