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: clay-local-dev-loop
description: 'Set up a local development loop for building and testing Clay integrations.
Use when iterating on Clay webhook handlers, testing enrichment pipelines,
or building scripts that push data into Clay tables.
Trigger with phrases like "clay local dev", "clay development setup",
"clay testing locally", "clay dev workflow", "iterate clay integration".
'
allowed-tools: Read, Write, Edit, Bash(curl:*), Bash(npm:*), Bash(npx:*), Bash(node:*),
Bash(python3:*)
version: 1.14.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- clay
- development
- testing
compatibility: Designed for Claude CodeClay is a web-based platform with no local runtime. Your local dev loop consists of: (1) scripts that push data into Clay via webhooks, (2) Clay enrichment running in the cloud, and (3) HTTP API columns pushing enriched data back to your local endpoint via ngrok. This skill sets up that feedback loop.
clay-install-auth setupnpm install -g ngrok or ngrok.com)Clay's HTTP API enrichment columns need a public URL to call your local endpoints.
# Start ngrok tunnel to your local server
ngrok http 3000
# Copy the HTTPS forwarding URL (e.g., https://abc123.ngrok-free.app)
// src/clay-receiver.ts — receives enriched data from Clay HTTP API columns
import express from 'express';
const app = express();
app.use(express.json());
// Clay HTTP API column calls this endpoint
app.post('/api/clay/enriched', (req, res) => {
const enrichedData = req.body;
console.log('Enriched record received from Clay:', {
email: enrichedData.email,
company: enrichedData.company_name,
title: enrichedData.job_title,
enrichment_source: enrichedData._clay_source,
});
// Process the enriched data (save to DB, trigger outreach, etc.)
res.json({ status: 'received', timestamp: new Date().toISOString() });
});
// Health check for Clay HTTP API column testing
app.get('/api/health', (req, res) => {
res.json({ status: 'ok', service: 'clay-dev-receiver' });
});
app.listen(3000, () => {
console.log('Clay dev receiver listening on http://localhost:3000');
console.log('Configure Clay HTTP API column to POST to: <ngrok-url>/api/clay/enriched');
});
// src/send-test-leads.ts — push test data into Clay via webhook
const CLAY_WEBHOOK_URL = process.env.CLAY_WEBHOOK_URL!;
const testLeads = [
{ email: 'cto@stripe.com', domain: 'stripe.com', source: 'dev-test' },
{ email: 'vp@notion.so', domain: 'notion.so', source: 'dev-test' },
{ email: 'head@figma.com', domain: 'figma.com', source: 'dev-test' },
];
async function sendTestBatch() {
for (const lead of testLeads) {
const res = await fetch(CLAY_WEBHOOK_URL, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(lead),
});
console.log(`Sent ${lead.email}: ${res.status}`);
await new Promise(r => setTimeout(r, 200)); // Respect rate limits
}
console.log('\nCheck your Clay table — enrichment columns should auto-run.');
console.log('Enriched data will POST back to your ngrok endpoint.');
}
sendTestBatch();
In your Clay table:
https://your-ngrok-url.ngrok-free.app/api/clay/enriched{{column_name}} syntax:{
"email": "{{Email}}",
"company_name": "{{Company Name}}",
"job_title": "{{Job Title}}",
"employee_count": "{{Employee Count}}",
"linkedin_url": "{{LinkedIn URL}}"
}
# Terminal 1: Run ngrok
ngrok http 3000
# Terminal 2: Run your local receiver
npx tsx src/clay-receiver.ts
# Terminal 3: Send test data to Clay
npx tsx src/send-test-leads.ts
# Watch Terminal 2 for enriched data flowing back from Clay
Iteration cycle:
// tests/clay-webhook.test.ts — test without hitting Clay
import { describe, it, expect } from 'vitest';
const mockClayEnrichedPayload = {
email: 'jane@stripe.com',
company_name: 'Stripe',
employee_count: 8000,
industry: 'Financial Technology',
job_title: 'VP Engineering',
linkedin_url: 'https://linkedin.com/in/janedoe',
_clay_source: 'clearbit',
_clay_enriched_at: '2026-03-22T10:00:00Z',
};
describe('Clay enriched data handler', () => {
it('processes enriched lead correctly', async () => {
const res = await fetch('http://localhost:3000/api/clay/enriched', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(mockClayEnrichedPayload),
});
expect(res.status).toBe(200);
const body = await res.json();
expect(body.status).toBe('received');
});
});
| Issue | Cause | Solution |
|---|---|---|
| ngrok tunnel drops | Free tier session expired | Restart ngrok or upgrade to paid plan |
| Clay HTTP API column returns error | ngrok URL changed | Update the URL in Clay column settings |
| No data flows back | Auto-run disabled | Enable auto-run on the HTTP API column |
| Webhook returns 422 | Bad JSON in test data | Validate payload with jq . <<< '$JSON' |
| Enrichment columns empty | No provider configured | Add enrichment provider in Clay table |
The development loop returns a local test receipt with fixture version, callback result, validation status, and any sanitized correlation ID. Use synthetic or irreversibly redacted fixtures; never tunnel production lead data, live secrets, or CRM credentials into a developer workstation.
Start the local handler, submit the mocked payload shown above through a temporary tunnel, and assert that the response is accepted without writing a real contact to a database or CRM. If the tunnel URL changes or the test fails, update only the staging test configuration and revoke the temporary endpoint after the session.
Once your dev loop works, see clay-sdk-patterns for production-ready integration patterns.
评论 (0)
暂无评论,成为第一个评论者吧!