一键在 Manus 中运行任何 Skill

pi-cli-workspace

星标19

分支4

更新时间2026年4月13日 20:49

Pi terminal agent workspace — install, /commands, sessions, compaction, settings.json, AGENTS.md, skill discovery, precedence, session JSONL, /tree, providers/auth, models.json, credential resolution, platform setup, editor (@file, Tab, images, !bash), message queue (steering, follow-up), built-in tools (read/bash/edit/write/grep/find/ls, --tools, --no-tools), print mode (-p, piped stdin), SYSTEM.md/APPEND_SYSTEM.md, CLI flags (-c, -r, --session, --fork, --no-session), @files args, resource flags (--no-extensions, --no-skills), model shorthand (provider/id, name:thinking), all slash commands, env vars, philosophy (no MCP/sub-agents/plan-mode by design). Use for pi config, skills, sessions, compaction, providers, models, tmux, Termux, Windows, tools, modes, system prompt, message queue, or "does pi support X".

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

romiluz13

romiluz13/pi-agent-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

软件开发工程师计算机与数学类职业·SOC 15-1252

文件资源管理器

2 个文件

SKILL.md

readonly

同仓库更多 Skills

同仓库

pi-customization

romiluz13/pi-agent-skills

Pi coding agent customization — Themes, Keybindings, Prompt Templates, System Prompt overrides, and Settings. Use when configuring or modifying the visual appearance, UI colors, keyboard shortcuts, prompt templates, or the default system prompt behavior of the pi terminal agent. Use for "custom theme pi", "change keybindings", "modify system prompt", "SYSTEM.md", "APPEND_SYSTEM.md", "settings.json", "keybindings.json", "prompt template", even if pi-cli-workspace is already active.

2026-04-1319

pi-extension-authoring

romiluz13/pi-agent-skills

Authoring Pi TypeScript extensions — ExtensionAPI, custom tools, commands, UI hooks, resources_discover, `registerProvider()`, and how extendResources merges skill paths after base reload. Use when the user builds or debugs pi extensions, registers tools, adds /commands, hooks events, integrates TUI components, or ships extension examples. Use for "how do I extend pi", "extension API", "registerTool", "registerProvider", even if pi-mono is not mentioned.

2026-04-1319

pi-mom

romiluz13/pi-agent-skills

@mariozechner/pi-mom — Slack bot Master Of Mischief (Mom), self-managing agent, Docker sandbox, and events system. Use when setting up Mom in Slack, debugging data/ workspace issues, managing context.jsonl/log.jsonl memory, or creating periodic/immediate events. Use for "mom slack bot", "docker sandbox", "mom events", "artifacts server", "cloudflare tunnel", "custom tools", "MomCustomTool", "multi-platform", "v86 sandbox", even if pi-coding-agent is not mentioned.

2026-04-1319

pi-rpc-sdk

romiluz13/pi-agent-skills

Pi headless RPC JSONL over stdin/stdout, strict LF framing, --mode json event streaming, and Node SDK alternatives (AgentSession). Use when integrating pi --mode rpc, pi --mode json, writing a client that speaks the protocol, reading JSON event streams, or choosing RPC vs in-process SDK. Use for "pi rpc client", "JSONL framing", "readline rpc", "--mode json", "json events", "embed pi without subprocess", "createAgentSession", "AgentSessionRuntime", "ModelRegistry", "embed pi", "SDK factory", even if the user only pasted JSON lines.

2026-04-1319

pi-agent-embedding

romiluz13/pi-agent-skills

@mariozechner/pi-agent-core Agent runtime — message flow, tool execution modes, event sequence for prompt() and continue(), embedding in apps. Use when building on Agent class, wiring subscribers, or debugging tool loops beside pi-ai. Use for "pi agent events", "beforeToolCall", "agent.subscribe", even if coding-agent CLI is not involved.

2026-04-1319

pi-ai-library

romiluz13/pi-agent-skills

@mariozechner/pi-ai — unified LLM streaming API, tools, providers, thinking events, and cross-provider handoffs as implemented in pi-mono. Use when integrating or debugging pi-ai, adding providers, using stream/complete, TypeBox tools, or token usage. Use for "pi-ai stream", "getModel", "new provider in pi", even if the user only says OpenRouter or Anthropic APIs.

2026-04-1319

name	pi-cli-workspace
description	Pi terminal agent workspace — install, /commands, sessions, compaction, settings.json, AGENTS.md, skill discovery, precedence, session JSONL, /tree, providers/auth, models.json, credential resolution, platform setup, editor (@file, Tab, images, !bash), message queue (steering, follow-up), built-in tools (read/bash/edit/write/grep/find/ls, --tools, --no-tools), print mode (-p, piped stdin), SYSTEM.md/APPEND_SYSTEM.md, CLI flags (-c, -r, --session, --fork, --no-session), @files args, resource flags (--no-extensions, --no-skills), model shorthand (provider/id, name:thinking), all slash commands, env vars, philosophy (no MCP/sub-agents/plan-mode by design). Use for pi config, skills, sessions, compaction, providers, models, tmux, Termux, Windows, tools, modes, system prompt, message queue, or "does pi support X".
compatibility	Host agent with read access to workspace files and the pi-mono corpus; Pi includes available_skills in the system prompt only when the read tool is among selected tools (see pi-mono/packages/coding-agent/src/core/system-prompt.ts).

Pi CLI and workspace

Answer only from pi-mono/ sources listed below. If something is not in the tree, say you cannot confirm from the corpus.

Grounding (read in order)

pi-mono/packages/coding-agent/README.md — product surface, commands, customization.
pi-mono/packages/coding-agent/docs/skills.md — skill locations, /skill:name, frontmatter, collisions.
pi-mono/packages/coding-agent/docs/settings.md — settings locations and keys.
pi-mono/AGENTS.md — maintainer rules when editing pi-mono itself.
pi-mono/packages/coding-agent/docs/compaction.md — auto-compaction triggers, cut-point algorithm, reserveTokens/keepRecentTokens settings, chained compactions, branch summarization.
pi-mono/packages/coding-agent/docs/session.md — JSONL session format, ~/.pi/agent/sessions/ paths, entry types (message, compaction, branch_summary, custom, label), buildSessionContext() assembly.
pi-mono/packages/coding-agent/docs/tree.md — /tree vs /fork, branch navigation, summarization options, tree UI keybindings.
pi-mono/packages/coding-agent/docs/providers.md — subscription OAuth (/login), API-key providers, auth.json, env-var credential table, cloud providers (Azure, Bedrock, Vertex).
pi-mono/packages/coding-agent/docs/models.md — models.json for Ollama/vLLM/LM Studio, compat flags, modelOverrides, provider-level config.
pi-mono/packages/coding-agent/docs/custom-provider.md — extension-registered providers via registerProvider(), OAuth flows, proxy patterns.
pi-mono/packages/coding-agent/docs/terminal-setup.md — Kitty keyboard protocol, Ghostty/iTerm/terminal keybinding caveats.
pi-mono/packages/coding-agent/docs/tmux.md — tmux extended-keys / csi-u so modified keys work inside pi.
pi-mono/packages/coding-agent/docs/windows.md — Windows bash discovery order (shellPath setting, Git Bash, PATH).
pi-mono/packages/coding-agent/docs/termux.md — running pi on Android via Termux (install, clipboard, storage).
pi-mono/packages/coding-agent/docs/shell-aliases.md — non-interactive bash and shellCommandPrefix to expand aliases from dotfiles.
pi-mono/packages/coding-agent/docs/development.md — local development setup, pi-test.sh, fork/rebrand via piConfig, test commands.
Implementation (for precedence and prompt wiring):
- pi-mono/packages/coding-agent/src/core/package-manager.ts — resourcePrecedenceRank comment block (ordering intent).
- pi-mono/packages/coding-agent/src/core/resource-loader.ts — reload() skill path merge (cliEnabledSkills, enabledSkills, additionalSkillPaths).
- pi-mono/packages/coding-agent/src/core/skills.ts — loadSkills, formatSkillsForPrompt, name collision handling.
- pi-mono/packages/coding-agent/src/core/system-prompt.ts — default harness text and hasRead gate for skills XML.
- pi-mono/packages/coding-agent/src/core/agent-session.ts — _expandSkillCommand inlines /skill:name body.
pi-mono/packages/coding-agent/README.md §Editor — @ fuzzy-search, Tab completion, Ctrl+V image paste, !/!! bash commands.
pi-mono/packages/coding-agent/README.md §Message Queue — steering (Enter) vs follow-up (Alt+Enter), steeringMode/followUpMode/transport settings.
pi-mono/packages/coding-agent/README.md §Modes, §CLI Reference — interactive, -p/--print, --mode json, --mode rpc, piped stdin.
pi-mono/packages/coding-agent/README.md §CLI Reference — full flag table, @files, --tools, --no-tools, --no-extensions, --no-skills, --no-prompt-templates, --no-themes, resource control.
pi-mono/packages/coding-agent/README.md §Environment Variables — PI_CODING_AGENT_DIR, PI_PACKAGE_DIR, PI_SKIP_VERSION_CHECK, PI_CACHE_RETENTION, VISUAL/EDITOR.
pi-mono/packages/coding-agent/README.md §Philosophy — what core intentionally omits (no MCP, no sub-agents, no permission popups, no plan mode, no built-in todos, no background bash); everything buildable via extensions.

Invariants

Skill name collisions: first registered name wins; later paths emit collision diagnostics (pi-mono/packages/coding-agent/src/core/skills.ts). Path order is assembled in resource-loader.ts then fed to loadSkills.
Resource precedence rank (lower = earlier in sorted package-manager lists): project local (0), project auto (1), user local (2), user auto (3), package (4) — pi-mono/packages/coding-agent/src/core/package-manager.ts.
Merged skill paths: mergePaths([...cliEnabledSkills, ...enabledSkills], additionalSkillPaths) — CLI paths appear before package-manager lists; see pi-mono/packages/coding-agent/src/core/resource-loader.ts.
<available_skills> is appended to the system prompt only when the read tool is among selected tools — pi-mono/packages/coding-agent/src/core/system-prompt.ts.
Default system prompt already points models at packaged docs paths (readmePath, docsPath, examples) — pi-mono/packages/coding-agent/src/core/system-prompt.ts. This skill adds workspace and precedence detail, not a duplicate README.
Session format version is v3 (tree-based id/parentId); buildSessionContext assembles compaction summary + branch summary + messages after the compaction point — see pi-mono/packages/coding-agent/docs/session.md.
Compaction cut-point selection avoids splitting tool results; firstKeptEntryId links chained compactions — see pi-mono/packages/coding-agent/docs/compaction.md.
Credential resolution order: --api-key flag > auth.json > environment variables > models.json custom keys — see pi-mono/packages/coding-agent/docs/providers.md.
SYSTEM.md / APPEND_SYSTEM.md: Replace the default system prompt with .pi/SYSTEM.md (project) or ~/.pi/agent/SYSTEM.md (global). Append without replacing via APPEND_SYSTEM.md at the same locations. Context files and skills are still appended after override — pi-mono/packages/coding-agent/README.md §Context Files.
Message queue: Enter queues a steering message (delivered between tool calls); Alt+Enter queues a follow-up (delivered after the agent finishes all work). Escape aborts; Alt+Up retrieves queued messages. Settings: steeringMode and followUpMode ("one-at-a-time" default vs "all"); transport ("sse", "websocket", "auto") — pi-mono/packages/coding-agent/README.md §Message Queue, pi-mono/packages/coding-agent/docs/settings.md.
Built-in tools: Default four: read, bash, edit, write. Additional available: grep, find, ls. Control via --tools <list> (e.g., --tools read,grep,find,ls for read-only) and --no-tools (disables all built-in; extension tools still work) — pi-mono/packages/coding-agent/README.md §Tool Options.
Editor features: @ fuzzy-searches project files; Tab completes paths; Ctrl+V pastes images (Alt+V on Windows); !command runs and sends output to LLM; !!command runs without sending — pi-mono/packages/coding-agent/README.md §Editor, pi-mono/packages/coding-agent/docs/keybindings.md.
Print mode: -p/--print for non-interactive stdout output. Reads piped stdin: cat README.md | pi -p "Summarize". Combine with --mode json for JSON-line output — pi-mono/packages/coding-agent/README.md §Modes.
CLI session flags: -c/--continue (most recent session), -r/--resume (browse/select), --session <path> (specific file or partial UUID), --fork <path> (fork from CLI), --no-session (ephemeral), --session-dir <dir> (custom storage) — pi-mono/packages/coding-agent/README.md §Session Options.
@files CLI arguments: Prefix files with @ on CLI: pi @screenshot.png "What's in this?", pi @code.ts @test.ts "Review". Included as part of the initial message — pi-mono/packages/coding-agent/README.md §File Arguments.
Resource control flags: --no-extensions, --no-skills, --no-prompt-templates, --no-themes disable auto-discovery. -e/--extension, --skill, --prompt-template, --theme for explicit loading. Combine --no-* with explicit flags for exact control (e.g., --no-extensions -e ./my-ext.ts) — pi-mono/packages/coding-agent/README.md §Resource Options.
Model shorthand: --model provider/id (e.g., openai/gpt-4o), --model name:thinking (e.g., sonnet:high), --models <patterns> for Ctrl+P cycling, --list-models — pi-mono/packages/coding-agent/README.md §Model Options.
Slash commands (full interactive list): /login, /logout, /model, /scoped-models, /settings, /resume, /new, /name, /session, /tree, /fork, /compact, /copy, /export, /share, /reload, /hotkeys, /changelog, /quit. Extensions register custom commands; skills expose /skill:name; prompt templates expand via /templatename — pi-mono/packages/coding-agent/README.md §Commands.
Environment variables: PI_CODING_AGENT_DIR (override config dir), PI_PACKAGE_DIR (override package dir), PI_SKIP_VERSION_CHECK, PI_CACHE_RETENTION (long for extended prompt cache), VISUAL/EDITOR (external editor for Ctrl+G) — pi-mono/packages/coding-agent/README.md §Environment Variables.
Philosophy (what pi intentionally omits): No MCP (use CLI tools or extensions), no sub-agents (use tmux or extensions), no permission popups (use container or extension), no plan mode (use files or extension), no built-in to-dos, no background bash (use tmux). Everything is buildable via extensions — pi-mono/packages/coding-agent/README.md §Philosophy.

Workflows

Find where a skill is discovered: Walk docs/skills.md locations, then cross-check package-manager.ts auto-discovery and settings.json skills arrays.
Explain shadowing: Combine resourcePrecedenceRank ordering with mergePaths / loadSkills "first name wins" using file citations only.
User forced load: /skill:name expansion — pi-mono/packages/coding-agent/src/core/agent-session.ts.
Debug compaction: Read compaction.md algorithm; check reserveTokens / keepRecentTokens in settings.json; trace chained compactions via firstKeptEntryId.
Add custom model: Follow models.md minimal example for Ollama/vLLM/LM Studio; check compat flags for non-standard OpenAI-compatible servers.
Session archaeology: Parse .jsonl using the switch example in session.md; navigate branches via /tree per tree.md.
Configure providers: Check providers.md for subscription OAuth (/login) vs API-key flow; see auth.json layout and env-var table.
Platform setup: For tmux, read tmux.md (extended-keys); for Windows, windows.md (shellPath); for Android, termux.md; for terminal quirks, terminal-setup.md.
Shell aliases: Read shell-aliases.md for shellCommandPrefix to make pi's bash tool see dotfile aliases.
Develop pi from source: Read development.md for clone/build/test and pi-test.sh runner.
Control tools: Use --tools read,grep,find,ls for read-only mode; --no-tools to disable all built-in tools (extension tools still work). Default is read,bash,edit,write.
Non-interactive mode: pi -p "prompt" or cat file | pi -p "Summarize" for CI/scripts. Combine with --mode json for machine-readable JSON-line output.
Custom system prompt: Place .pi/SYSTEM.md in a project or ~/.pi/agent/SYSTEM.md globally to replace the default prompt. Use APPEND_SYSTEM.md at the same locations to append without replacing.

Anti-patterns

Do not invent MCP or sub-agent behavior as "built into core"; check pi-mono/packages/coding-agent/README.md philosophy section for what core omits.
Do not claim exact merge behavior without citing resource-loader.ts and skills.ts.
Do not describe compaction cut-point behavior from memory; cite compaction.md algorithm section.
Do not guess credential resolution order; cite providers.md for the exact precedence.