设置口径
- 作者仓库星标 0
- 作者仓库 skills-registry
- 领域
- 人工智能
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @tomevault-io · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部接口密钥
- 需要 · OpenAI / Anthropic / GitHub
- 兼容的系统
- Linux
- 运行环境要求
- Node.js >=20
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 网络行为
- 允许外网请求
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
如果打印版本 → Calibre 已全局安装。设置 `CALIBER="caliber"` 并转到步骤 2。如果 NOT_INSTALLED → 全局安装(日常使用速度更快,因为预提交挂钩在每次提交时运行):设置 `CALIBER="caliber"`。如果 npm 失败(权限、无 sudo 等),则回退到 npx:如果 npx 有效 → 设置 `CALIBER="npx @rely-ai/caliber"`。这可行,但每次调用会增加约 500 毫秒。
如果 HOOK_ACTIVE → 告诉用户:“预提交挂钩处于活动状态 - 每次提交时都会同步配置。”转到步骤 3。如果 NO_HOOK → 告诉用户:“我将安装预提交挂钩,以便您的代理配置在每次提交时自动同步。”
首先,检测此项目中配置了哪些编码代理:如果未检测到代理,则询问用户他们使用哪些编码代理(Claude Code、Cursor、Codex、GitHub Copilot)。根据他们的答案以逗号分隔的字符串形式构建代理列表(例如“claude,cursor”)。然后检查代理配置是否存在:如果检测到的代理存在配置→告诉用户存在哪些配置。转到步骤 4。
如果分数为 80+ → 告诉用户:“您的配置状况良好(分数:X/100)。”如果分数低于 80 → 告诉用户:“您的配置可以改进(分数:X/100)。需要我运行刷新吗?”如果是:
询问用户:“您是只为自己设置,还是也为您的团队设置?”如果单独 → 继续单独设置: 检查会话学习是否已启用: 如果学习已启用 → 在摘要中注明。如果未启用→询问用户:“Calibre 可以从您的编码会话中学习 - 当您纠正错误或修复模式时,它会记住下次。启用会话学习吗?”
# Setup Caliber
Dynamic onboarding for Caliber — automatic AI agent context sync.
Run all diagnostic steps below on every invocation to determine what's already
set up and what still needs to be done.
## Instructions
Run these checks in order. For each step, check the current state first,
then only act if something is missing.
### Step 1: Check if Caliber is installed
```bash
command -v caliber >/dev/null 2>&1 && caliber --version || echo "NOT_INSTALLED"
```
- If a version prints → Caliber is installed globally. Set `CALIBER="caliber"` and move to Step 2.
- If NOT_INSTALLED → Install it globally (faster for daily use since the pre-commit hook runs on every commit):
```bash
npm install -g @rely-ai/caliber
```
Set `CALIBER="caliber"`.
If npm fails (permissions, no sudo, etc.), fall back to npx:
```bash
npx @rely-ai/caliber --version 2>/dev/null || echo "NO_NODE"
```
- If npx works → Set `CALIBER="npx @rely-ai/caliber"`. This works but adds ~500ms per invocation.
- If NO_NODE → Tell the user: "Caliber requires Node.js >= 20. Install Node first, then run /setup-caliber again." Stop here.
### Step 2: Check if pre-commit hook is installed
```bash
grep -q "caliber" .git/hooks/pre-commit 2>/dev/null && echo "HOOK_ACTIVE" || echo "NO_HOOK"
```
- If HOOK_ACTIVE → Tell the user: "Pre-commit hook is active — configs sync on every commit." Move to Step 3.
- If NO_HOOK → Tell the user: "I'll install the pre-commit hook so your agent configs sync automatically on every commit."
```bash
$CALIBER hooks --install
```
### Step 3: Detect agents and check if configs exist
First, detect which coding agents are configured in this project:
```bash
AGENTS=""
[ -d .claude ] && AGENTS="claude"
[ -d .cursor ] && AGENTS="${AGENTS:+$AGENTS,}cursor"
[ -d .agents ] || [ -f AGENTS.md ] && AGENTS="${AGENTS:+$AGENTS,}codex"
[ -f .github/copilot-instructions.md ] && AGENTS="${AGENTS:+$AGENTS,}github-copilot"
echo "DETECTED_AGENTS=${AGENTS:-none}"
```
If no agents are detected, ask the user which coding agents they use (Claude Code, Cursor, Codex, GitHub Copilot).
Build the agent list from their answer as a comma-separated string (e.g. "claude,cursor").
Then check if agent configs exist:
```bash
echo "CLAUDE_MD=$([ -f CLAUDE.md ] && echo exists || echo missing)"
echo "CURSOR_RULES=$([ -d .cursor/rules ] && ls .cursor/rules/*.mdc 2>/dev/null | wc -l | tr -d ' ' || echo 0)"
echo "AGENTS_MD=$([ -f AGENTS.md ] && echo exists || echo missing)"
echo "COPILOT=$([ -f .github/copilot-instructions.md ] && echo exists || echo missing)"
```
- If configs exist for the detected agents → Tell the user which configs are present. Move to Step 4.
- If configs are missing → Tell the user: "No agent configs found. I'll generate them now."
Use the detected or user-selected agent list:
```bash
$CALIBER init --auto-approve --agent <comma-separated-agents>
```
For example: `$CALIBER init --auto-approve --agent claude,cursor`
This generates CLAUDE.md, Cursor rules, AGENTS.md, skills, and sync infrastructure for the specified agents.
### Step 4: Check if configs are fresh
```bash
$CALIBER score --json --quiet 2>/dev/null | head -1
```
- If score is 80+ → Tell the user: "Your configs are in good shape (score: X/100)."
- If score is below 80 → Tell the user: "Your configs could be improved (score: X/100). Want me to run a refresh?"
If yes:
```bash
$CALIBER refresh
```
### Step 5: Ask about team setup
Ask the user: "Are you setting up for yourself only, or for your team too?"
- If **solo** → Continue with solo setup:
Check if session learning is enabled:
```bash
$CALIBER learn status 2>/dev/null | head -3
```
- If learning is already enabled → note it in the summary.
- If not enabled → ask the user: "Caliber can learn from your coding sessions — when you correct a mistake or fix a pattern, it remembers for next time. Enable session learning?"
If yes:
```bash
$CALIBER learn install
```
Then tell the user:
"You're all set! Here's what happens next:
- Every time you commit, Caliber syncs your agent configs automatically
- Your CLAUDE.md, Cursor rules, and AGENTS.md stay current with your code
- Run `$CALIBER skills` anytime to discover community skills for your stack"
Then show the summary (see below) and stop.
- If **team** → Check if the GitHub Action already exists:
```bash
[ -f .github/workflows/caliber-sync.yml ] && echo "ACTION_EXISTS" || echo "NO_ACTION"
```
- If ACTION_EXISTS → Tell the user: "GitHub Action is already configured."
- If NO_ACTION → Tell the user: "I'll create a GitHub Action that syncs configs nightly and on every PR."
Write this file to `.github/workflows/caliber-sync.yml`:
```yaml
name: Caliber Sync
on:
schedule:
- cron: '0 3 * * 1-5'
pull_request:
types: [opened, synchronize]
workflow_dispatch:
jobs:
sync:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: caliber-ai-org/ai-setup@v1
with:
mode: sync
auto-refresh: true
comment: true
github-token: ${{ secrets.GITHUB_TOKEN }}
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
```
Now determine which LLM provider the team uses. Check the local Caliber config:
```bash
$CALIBER config --show 2>/dev/null || echo "NO_CONFIG"
```
Based on the provider, the GitHub Action needs the corresponding secret:
- **anthropic** → `ANTHROPIC_API_KEY`
- **openai** → `OPENAI_API_KEY`
- **vertex** → `VERTEX_PROJECT_ID` and `GOOGLE_APPLICATION_CREDENTIALS` (service account JSON)
Update the workflow env block to match the provider. For example, if using OpenAI:
```yaml
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
```
Then check if the `gh` CLI is available to set the secret:
```bash
command -v gh >/dev/null 2>&1 && echo "GH_AVAILABLE" || echo "NO_GH"
```
- If GH_AVAILABLE → Ask the user for their API key and set it:
```bash
gh secret set ANTHROPIC_API_KEY
```
(This prompts for the value securely via stdin)
- If NO_GH → Tell the user exactly what to do:
"Go to your repo on GitHub → Settings → Secrets and variables → Actions → New repository secret.
Name: ANTHROPIC_API_KEY (or OPENAI_API_KEY depending on provider)
Value: your API key"
Finally, offer to commit and push the workflow file:
```bash
git add .github/workflows/caliber-sync.yml
git commit -m "feat: add Caliber sync GitHub Action"
git push
```
### Summary
After completing all steps, show the user what's configured:
```
Caliber Setup Complete:
✓ Caliber installed (vX.X.X)
✓ Pre-commit hook — configs sync on every commit
✓ Agent configs — CLAUDE.md, Cursor rules, AGENTS.md
✓ Config score: X/100
✓ GitHub Action — nightly sync + PR checks (team only)
From now on, every commit keeps all your agent configs in sync automatically.
```
## When to trigger
- When a developer first opens this project
- When the user asks about keeping agent configs up to date
- When the user asks "how do I set up Caliber" or "what is Caliber"
- When the user sees a message saying "Run /setup-caliber to get set up"
## When NOT to trigger
- The user is in the middle of time-sensitive work
---
> Source: [caliber-ai-org/ai-setup](https://github.com/caliber-ai-org/ai-setup) — distributed by [TomeVault](https://tomevault.io).
<!-- tomevault:4.0:skill_md:2026-05-23 -->
按说明文件中的顺序排列。
使用说明
第1步:检查Calibre是否安装
步骤2:检查是否安装了预提交钩子
步骤 3:检测代理并检查配置是否存在
第 4 步:检查配置是否最新
文件/命令 -> CALIBER="caliber" · CALIBER="npx @rely-ai/caliber" · $CALIBER init --auto-approve --agent claude,cursor · $CALIBER skills · .github/workflows/caliber-sync.yml · ANTHROPIC_API_KEY · OPENAI_API_KEY · VERTEX_PROJECT_ID
内容校验值 -> ab9c47b89816
当前原文的自动摘译,尚未人工审校。
使用说明
按顺序运行这些检查。对于每个步骤,首先检查当前状态,然后仅在缺少某些内容时才采取行动。
第1步:检查Calibre是否安装
如果打印版本 → Calibre 已全局安装。设置
CALIBER="caliber"并移至步骤 2。如果 NOT_INSTALLED → 全局安装(日常使用速度更快,因为预提交挂钩在每次提交时运行):设置CALIBER="caliber"。如果 npm 失败(权限、无 sudo 等),则回退到 npx:如果 npx 有效 → 设置CALIBER="npx @rely-ai/caliber"。这可行,但每次调用会增加约 500 毫秒。