Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

help帮助指南

Agent Skill

help 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,569

周安装

106

GitHub Stars

160

下载量

840
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:help(帮助指南)
来源仓库:https://github.com/yonatangross/orchestkit
仓库路径:skills/help
安装命令:
npx skills add https://github.com/yonatangross/orchestkit --skill help
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yonatangross/orchestkit --skill help

简介

用于获取技能使用指南和相关资源链接。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

  • 适合快速了解各技能的功能边界和调用方式。
  • 可结合来源仓库查阅完整文档说明。help 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 安装前建议确认是否启用联网获取最新帮助内容。
  • 注意离线环境下可能无法访问远程资源。

SKILL.md

OrchestKit Skill Directory

Dynamic skill discovery — reads from source at runtime so listings are never stale.

Quick Start

/ork:help           # Show all categories
/ork:help build     # Show BUILD skills only
/ork:help git       # Show GIT skills only
/ork:help all       # List every user-invocable skill

Argument Resolution

CATEGORY = "$ARGUMENTS[0]"  # Optional: build, git, memory, quality, config, explore, plan, media, all
# If provided, skip AskUserQuestion and show that category directly.
# $ARGUMENTS is the full string (CC 2.1.59 indexed access)

STEP 0: Dynamic Skill Discovery

ALWAYS run this first to get accurate, up-to-date skill data:

# Scan all user-invocable skills from source
Grep(pattern="user-invocable:\\s*true", path="src/skills", output_mode="files_with_matches")

For each matched file, extract name and description from frontmatter:

# For each SKILL.md found, read first 15 lines to get name + description
Read(file_path="src/skills/{name}/SKILL.md", limit=15)

Build the skill list dynamically. Never hardcode counts or skill names.


STEP 1: Category Selection

If CATEGORY argument provided, skip to STEP 2 with that category.

Otherwise, present categories interactively:

AskUserQuestion(
  questions=[{
    "question": "What type of task are you working on?",
    "header": "Category",
    "options": [
      {"label": "BUILD", "description": "Implement features, brainstorm, verify", "markdown": "```\nBUILD — Feature Development\n───────────────────────────\n/ork:implement     Full-power implementation\n/ork:brainstorm    Design exploration\n/ork:verify        Test & grade changes\n```"},
      {"label": "GIT", "description": "Commits, PRs, issues, branches", "markdown": "```\nGIT — Version Control\n─────────────────────\n/ork:commit        Conventional commits\n/ork:create-pr     PR with validation\n/ork:review-pr     6-agent PR review\n/ork:fix-issue     Debug + fix + PR\n```"},
      {"label": "PLAN", "description": "PRDs, plan visualization, assessment", "markdown": "```\nPLAN — Design & Strategy\n────────────────────────\n/ork:visualize-plan  ASCII plan rendering\n/ork:write-prd       Product requirements\n/ork:assess          Rate 0-10 + report\n```"},
      {"label": "MEMORY", "description": "Store decisions, search, recall", "markdown": "```\nMEMORY — Knowledge Persistence\n──────────────────────────────\n/ork:remember  Store decisions/patterns\n/ork:memory    Search, recall, visualize\n```"},
      {"label": "QUALITY", "description": "Assess, review, diagnose", "markdown": "```\nQUALITY — Assessment & Health\n─────────────────────────────\n/ork:assess     Rate quality 0-10\n/ork:review-pr  6-agent PR review\n/ork:doctor     Plugin health check\n```"},
      {"label": "CONFIG", "description": "Setup, diagnostics", "markdown": "```\nCONFIG — Setup & Operations\n───────────────────────────\n/ork:setup         Onboarding wizard\n/ork:doctor        Health diagnostics\n/ork:configure     Plugin settings\n```"},
      {"label": "EXPLORE", "description": "Codebase exploration and analysis", "markdown": "```\nEXPLORE — Codebase Analysis\n───────────────────────────\n/ork:explore  Multi-angle exploration\n              4 parallel agents\n              Architecture visualization\n```"},
      {"label": "Show all", "description": "List every user-invocable skill"}
    ],
    "multiSelect": false
  }]
)

STEP 2: Render Category

For the selected category, render the skill table from the data gathered in STEP 0.

Category-to-Skill Mapping

CategorySkills
BUILDimplement, brainstorm, verify
GITcommit, create-pr, review-pr, fix-issue
PLANvisualize-plan, write-prd, assess
MEMORYremember, memory
QUALITYassess, review-pr, doctor
CONFIGsetup, doctor, configure
EXPLOREexplore

For each skill in the category, render:

/ork:{name}  v{version}  {complexity}
  {description}
  Example: /ork:{name} {argument-hint example}

"Show all" — Full Listing

If user picks "Show all", render ALL user-invocable skills grouped by category from STEP 0 data.


CC Built-in Commands (2.1.72+)

Not OrchestKit skills — these are Claude Code built-ins:

CommandDescriptionSince
/simplifyReview changed code for quality, then fixCC 2.1.63
/helpClaude Code built-in helpCC 2.1.0+
/configClaude Code configurationCC 2.1.0+
/clearClear conversation (preserves background agents)CC 2.1.72
/fastToggle fast mode (same model, faster output)CC 2.1.59+
/loopRecurring interval (e.g. /loop 5m /foo)CC 2.1.71
/effortReasoning effort: low/medium/high/autoCC 2.1.72
/planEnter plan modeCC 2.1.72
/team-onboardingGenerate teammate ramp-up guideCC 2.1.101
/ultraplanRemote-session deep planningCC 2.1.101
/recapSession context restoration after idleCC 2.1.108
/undoAlias for /rewindCC 2.1.108

Performance Tips

  • ENABLE_PROMPT_CACHING_1H=1 — Extends prompt cache TTL from 5 min to 1 hour. Set this for long sessions with multi-phase skills (brainstorm, implement, cover). Available on API key, Bedrock, Vertex, Foundry.
  • /recap — Restores session context after stepping away. Complements OrchestKit's checkpoint-resume for chain recovery.

Keyboard Shortcuts

ShortcutAction
Ctrl+FFind in session output
EscCancel / dismiss
Shift+EnterNewline in input
Ctrl+CCancel operation

Pro Tip

You don't need to memorize skills. Just describe your task naturally:

"I need to implement user login"     → /ork:implement
"Show me the payment architecture"   → /ork:explore
"Review PR 123"                      → /ork:review-pr
"Is this code good?"                 → /ork:assess
"Plan out the billing redesign"      → /ork:visualize-plan

Related Skills

  • /help — Claude Code built-in help
  • /ork:doctor — OrchestKit health check
  • /ork:setup — Full onboarding wizard

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.53%
按下载量换算298

Claude

31.11%
按下载量换算261

Cursor

17.57%
按下载量换算148

Gemini CLI

8.68%
按下载量换算73

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills