复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
A model-agnostic agent-skills platform.
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
来源文件:README.md
A model-agnostic agent-skills platform. The canonical layer is harness-free by construction; Claude Code is currently the verified-native harness. Other harnesses remain engineering candidates until their native-path integration is verified; source research alone is never presented as public support.
Version semantics: the release badge is this marketplace's display version. npm packages, including the
ccpiCLI and publishable plugins, retain their own package versions; they are intentionally not expected to equal the display version. The version-surface checker governs the display surfaces without rewriting package semver.
Inside Claude Code, one command installs the whole marketplace:
/plugin marketplace add jeremylongshore/claude-code-plugins
Or use the CLI:
pnpm add -g @intentsolutionsio/ccpi
ccpi install devops-automation-pack
Browse the marketplace · Explore plugins · Download bundles
Killer Skill of the Week — no-ai-slop by Peter Yang
Strip AI slop from any draft — named-pattern edits that keep the writer's real voice
no-ai-slop does two jobs and refuses to fake a third. In Edit mode it makes the minimum effective edit — cutting throat-clearing, weak verbs, and abstract nouns while deliberately preserving the writer's cadence, bluntness, humor, and honest admissions, so a rough draft still sounds like the same person afterward. In Detect mode it names each AI-slop pattern it finds, quotes the offending line, and gives the fix in a few words — and pointedly does NOT score the draft or guess whether an AI wrote it. That restraint is the whole point: AI detectors guess; named patterns are evidence the reader can check. MIT-licensed, single focused skill, actively maintained by Peter Yang.
"AI detectors guess. Named patterns are evidence the user can check." — Peter Yang
Grade: A | Week of July 22, 2026 (W30) | View on GitHub
Previous picks: tonone, mnemos, databricks-pack, kobiton-automate, skyvern, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.
Every number below names the cohort it counts and the command that reproduces it — an unlabeled count is how a corpus ends up with five contradictory answers to "how many skills."
| Count | Cohort | Reproduce with |
|---|---|---|
| 442 | catalog plugins (catalog-entry cohort) | node scripts/generate-readme-toc.mjs over marketplace.extended.json |
| 3,067 | marketplace-visible skills (distinct) | node -e "import('./scripts/corpus-resolver.mjs').then(m=>console.log(m.resolveCorpus('marketplace-visible').length))" |
| 347 | agent definitions in plugins | git ls-files 'plugins/**' | grep '/agents/.*\.md' |
| 19 | plugin categories | ls -d plugins/*/ |
Across 396 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.
| Window | All packages | Established (>30d) |
|---|---|---|
| Last 24 hours | 962 | 962 |
| Last 7 days | 2,920 | 2,916 |
| Last 30 days | 12,868 | 12,779 |
"Established" excludes packages first published within the last 30 days, so a bulk-publish event doesn't dominate the headline.
Top 10 by last 30 days:
Last refreshed 2026-08-19T03:03:05.709Z.
Five real questions, five doors — each resolves to a live, generated surface, never a hand-maintained list:
The 19 categories below link into the live marketplace. Plugin counts are the catalog-entry cohort — regenerated from marketplace.extended.json by this generator; the catalog itself lives on tonsofskills.com, never in this file (§ 6A of the platform blueprint).
| Category | Plugins | |
|---|---|---|
| 🤖 | AI & Machine Learning | 36 |
| 🎭 | AI Agents & Agency | 10 |
| 🔌 | API Development | 26 |
| 💼 | Business Tools | 6 |
| 👥 | Community | 21 |
| ₿ | Crypto & Web3 | 27 |
| 💾 | Database | 26 |
| 🎨 | Design | 2 |
| 🔧 | DevOps & Infrastructure | 36 |
| 📚 | Examples & Templates | 5 |
| 🧩 | MCP Servers | 16 |
| 📦 | Packages | 5 |
| ⚡ | Performance | 25 |
| ✅ | Productivity | 30 |
| 🎁 | SaaS Skill Packs | 106 |
| 🔐 | Security | 27 |
| ✨ | Skill Enhancers | 9 |
| 🧪 | Testing | 28 |
| 📁 | Analytics | 1 |
Four artifact classes live in this repository, distinguished on sight and never blurred — provenance is a truth requirement here, not a UX nicety:
| Class | What it is | How the reader can tell |
|---|---|---|
| Canonical skill | First-party, harness-free, the source of truth | No .source.json in its plugin directory |
| Generated adapter | A thin, machine-produced harness projection | Lives under a generated path with a "generated — do not edit" header |
| First-party package | An Intent Solutions distribution (npm, cowork zip) | @intentsolutionsio scope, IS-authored license |
| Upstream mirror | Somebody else's work, hosted mirror-by-default | .source.json present — upstream author, license, and pinned commit recorded |
Not yet certified. The certification program (tiers T0–T4 with retained, hash-matched evidence) is a later epic of the platform blueprint; until its report exists, no artifact on this surface claims a tier. This line is rendered from the absence of certification-report.json — honestly, not cosmetically.
Start with the contribution guide, then the intake and review standards every submission passes through:
External plugins are hosted mirror-by-default: the contributor's repository stays the source of truth, every mirrored source is pinned in a content lockfile, and upstream credit — author, license, resolved commit — is recorded in the mirror itself. Improvements flow by upstreaming to the author's repository, never by silently editing the mirror. The full decision record is the external-sync model.
MIT for the repository scaffolding and first-party tooling; each plugin carries its own license in its manifest, and mirrored plugins keep their upstream license verbatim.
name: clerk-debug-bundle
description: 'Collect comprehensive debug information for Clerk issues.
Use when troubleshooting complex problems, preparing support tickets,
or diagnosing intermittent issues.
Trigger with phrases like "clerk debug", "clerk diagnostics",
"clerk support ticket", "clerk troubleshooting".
'
allowed-tools: Read, Write, Edit, Bash(npm:*), Bash(node:*), Grep
version: 1.14.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- clerk
- debugging
compatibility: Designed for Claude Code!node --version 2>/dev/null || echo 'N/A'
!npm list @clerk/nextjs @clerk/clerk-react @clerk/express 2>/dev/null | grep clerk || echo 'No Clerk packages found'
Collect all necessary debug information for Clerk troubleshooting and support tickets. Generates an environment report, runtime health check, client-side debug panel, and support bundle.
// scripts/clerk-debug.ts
import { createClerkClient } from '@clerk/backend'
async function collectDebugInfo() {
const info: Record<string, any> = {
timestamp: new Date().toISOString(),
nodeVersion: process.version,
platform: process.platform,
env: {
hasPK: !!process.env.NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY,
hasSK: !!process.env.CLERK_SECRET_KEY,
pkPrefix: process.env.NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY?.slice(0, 8) + '...',
nodeEnv: process.env.NODE_ENV,
},
}
// Test API connectivity
try {
const clerk = createClerkClient({ secretKey: process.env.CLERK_SECRET_KEY! })
const users = await clerk.users.getUserList({ limit: 1 })
info.apiConnectivity = { status: 'ok', userCount: users.totalCount }
} catch (err: any) {
info.apiConnectivity = { status: 'error', message: err.message, code: err.status }
}
// Check package versions
try {
const pkg = require('./package.json')
info.packages = Object.entries(pkg.dependencies || {})
.filter(([k]) => k.includes('clerk'))
.reduce((acc, [k, v]) => ({ ...acc, [k]: v }), {})
} catch {
info.packages = 'Could not read package.json'
}
console.log(JSON.stringify(info, null, 2))
return info
}
collectDebugInfo()
Run with:
npx tsx scripts/clerk-debug.ts
// app/api/clerk-health/route.ts
import { auth, clerkClient } from '@clerk/nextjs/server'
export async function GET() {
const checks: Record<string, { status: string; detail?: string }> = {}
// Check 1: SDK loaded
checks.sdk = { status: 'ok', detail: 'Clerk SDK loaded' }
// Check 2: Auth function works
try {
const { userId } = await auth()
checks.auth = { status: 'ok', detail: userId ? `Authenticated as ${userId}` : 'Not authenticated (expected for health check)' }
} catch (err: any) {
checks.auth = { status: 'error', detail: err.message }
}
// Check 3: Backend API connectivity
try {
const client = await clerkClient()
await client.users.getUserList({ limit: 1 })
checks.backendApi = { status: 'ok', detail: 'API reachable' }
} catch (err: any) {
checks.backendApi = { status: 'error', detail: err.message }
}
// Check 4: Environment variables
checks.envVars = {
status: process.env.CLERK_SECRET_KEY ? 'ok' : 'error',
detail: process.env.CLERK_SECRET_KEY ? 'Secret key configured' : 'CLERK_SECRET_KEY missing',
}
const allOk = Object.values(checks).every((c) => c.status === 'ok')
return Response.json({ healthy: allOk, checks }, { status: allOk ? 200 : 503 })
}
'use client'
import { useAuth, useUser, useSession } from '@clerk/nextjs'
import { useState } from 'react'
export function ClerkDebugPanel() {
const { userId, isLoaded: authLoaded, getToken } = useAuth()
const { user, isLoaded: userLoaded } = useUser()
const { session } = useSession()
const [tokenPreview, setTokenPreview] = useState<string | null>(null)
if (process.env.NODE_ENV === 'production') return null // Hide in prod
const inspectToken = async () => {
const token = await getToken()
if (token) {
const payload = JSON.parse(atob(token.split('.')[1]))
setTokenPreview(JSON.stringify(payload, null, 2))
}
}
return (
<details style={{ position: 'fixed', bottom: 10, right: 10, background: '#1a1a2e', color: '#eee', padding: 12, borderRadius: 8, fontSize: 12, zIndex: 9999 }}>
<summary>Clerk Debug</summary>
<pre>
Auth loaded: {String(authLoaded)}{'\n'}
User loaded: {String(userLoaded)}{'\n'}
User ID: {userId || 'null'}{'\n'}
Email: {user?.primaryEmailAddress?.emailAddress || 'N/A'}{'\n'}
Session ID: {session?.id || 'null'}{'\n'}
Session status: {session?.status || 'N/A'}{'\n'}
Last active: {session?.lastActiveAt ? new Date(session.lastActiveAt).toISOString() : 'N/A'}
</pre>
<button onClick={inspectToken}>Inspect JWT</button>
{tokenPreview && <pre>{tokenPreview}</pre>}
</details>
)
}
// middleware.ts — add debug logging (development only)
import { clerkMiddleware } from '@clerk/nextjs/server'
export default clerkMiddleware(async (auth, req) => {
if (process.env.CLERK_DEBUG === 'true') {
const { userId, sessionId } = await auth()
console.log(`[Clerk Debug] ${req.method} ${req.nextUrl.pathname}`, {
userId: userId || 'anonymous',
sessionId: sessionId?.slice(0, 8) || 'none',
cookies: req.cookies.getAll().map((c) => c.name).filter((n) => n.startsWith('__clerk')),
})
}
})
#!/bin/bash
# scripts/clerk-support-bundle.sh
set -euo pipefail
BUNDLE_DIR="clerk-debug-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE_DIR"
# Package versions
npm list --depth=0 2>/dev/null | grep clerk > "$BUNDLE_DIR/packages.txt" || true
# Environment check (redacted)
echo "NODE_ENV: ${NODE_ENV:-not set}" > "$BUNDLE_DIR/env.txt"
echo "Has PK: $([ -n "${NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY:-}" ] && echo yes || echo no)" >> "$BUNDLE_DIR/env.txt"
echo "Has SK: $([ -n "${CLERK_SECRET_KEY:-}" ] && echo yes || echo no)" >> "$BUNDLE_DIR/env.txt"
echo "PK prefix: ${NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY:0:8}..." >> "$BUNDLE_DIR/env.txt"
# Middleware check
[ -f middleware.ts ] && cp middleware.ts "$BUNDLE_DIR/" || echo "No middleware.ts found" > "$BUNDLE_DIR/middleware-missing.txt"
# Health check
curl -s http://localhost:3000/api/clerk-health > "$BUNDLE_DIR/health.json" 2>/dev/null || echo '{"error":"app not running"}' > "$BUNDLE_DIR/health.json"
# Bundle it
tar czf "${BUNDLE_DIR}.tar.gz" "$BUNDLE_DIR"
rm -rf "$BUNDLE_DIR"
echo "Support bundle: ${BUNDLE_DIR}.tar.gz"
/api/clerk-health endpoint for runtime health checks| Issue | Debug Action |
|---|---|
| Auth not working | Hit /api/clerk-health, check backendApi status |
| Token issues | Use debug panel "Inspect JWT" to view claims and expiry |
| Middleware not running | Enable CLERK_DEBUG=true, check console for request logs |
| Session not persisting | Check debug panel for __clerk cookies, verify domain |
# Verify Clerk API connectivity from CLI
curl -s -H "Authorization: Bearer $CLERK_SECRET_KEY" \
https://api.clerk.com/v1/users?limit=1 | jq '.total_count'
Proceed to clerk-rate-limits for understanding Clerk rate limits.
评论 (0)
暂无评论,成为第一个评论者吧!