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: customerio-cost-tuning
description: 'Optimize Customer.io costs and usage efficiency.
Use when reducing profile count, cleaning inactive users,
deduplicating events, or right-sizing your plan.
Trigger: "customer.io cost", "reduce customer.io spend",
"customer.io billing", "customer.io pricing", "customer.io cleanup".
'
allowed-tools: Read, Write, Edit, Bash(npm:*), Bash(npx:*), Glob, Grep
version: 1.14.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- customer-io
- cost-optimization
- billing
compatibility: Designed for Claude Code| Condition | Safe response |
|---|---|
| Spend rises unexpectedly | Verify configuration, rate, and authorized campaigns; pause unsafe scale changes and investigate aggregate signals. |
| Optimization risks delivery or consent | Do not apply it until the service/data owner approves a safe test. |
| Data is missing or misallocated | Repair attribution before making a budget decision. |
Compare aggregate event volume and message spend for a development/staging campaign, reduce unnecessary duplicate events through an idempotency fix, and observe the agreed window. Revert if delivery errors, latency, or consent checks regress; do not suppress customer messages solely to make a dashboard look cheaper.
Optimize Customer.io costs by managing profile count (the primary billing driver), suppressing/deleting inactive users, deduplicating events, reducing unnecessary API calls, and monitoring usage trends.
Customer.io bills based on profile count (number of identified people in your workspace) and email/SMS volume. Key cost drivers:
| Factor | Impact | Optimization Strategy |
|---|---|---|
| Total profiles | Primary cost driver | Delete inactive profiles |
| Email sends | Per-email cost above tier | Suppress unengaged users |
| SMS sends | Per-SMS cost | Only send to opt-in users |
| Overidentification | Creates unnecessary profiles | Don't identify users who'll never receive messages |
| Event volume | Can increase processing costs | Deduplicate and sample |
// scripts/cio-profile-audit.ts
// Audit your Customer.io integration for cost optimization opportunities
import { TrackClient, RegionUS } from "customerio-node";
const cio = new TrackClient(
process.env.CUSTOMERIO_SITE_ID!,
process.env.CUSTOMERIO_TRACK_API_KEY!,
{ region: RegionUS }
);
// Check: Are you identifying users who'll never receive messages?
const AUDIT_RULES = {
// Users without email can't receive email campaigns
noEmail: "Don't identify users without email unless using push/SMS",
// Test users should be cleaned up
testUsers: "Suppress and delete test-*, ci-*, dev-* prefixed users",
// Anonymous users that never convert inflate profile count
staleAnonymous: "Delete anonymous profiles older than 90 days without conversion",
// Inactive users who haven't opened email in 6+ months
unengaged: "Suppress users with no email opens in 180+ days",
};
console.log("=== Customer.io Cost Audit Rules ===\n");
for (const [rule, action] of Object.entries(AUDIT_RULES)) {
console.log(`${rule}: ${action}`);
}
console.log("\nRun these checks in Customer.io dashboard:");
console.log("1. People > Segments > Create 'Inactive 90 days' segment");
console.log("2. People > Segments > Create 'No email attribute' segment");
console.log("3. People > Filter by created_at < 90 days ago AND email_opened = 0");
// scripts/cio-cleanup-inactive.ts
import { TrackClient, RegionUS } from "customerio-node";
const cio = new TrackClient(
process.env.CUSTOMERIO_SITE_ID!,
process.env.CUSTOMERIO_TRACK_API_KEY!,
{ region: RegionUS }
);
interface CleanupTarget {
userId: string;
reason: string;
}
async function cleanupInactiveUsers(
targets: CleanupTarget[],
dryRun: boolean = true
): Promise<void> {
let suppressed = 0;
let deleted = 0;
let errors = 0;
for (const target of targets) {
if (dryRun) {
console.log(`[DRY RUN] Would suppress+delete: ${target.userId} (${target.reason})`);
continue;
}
try {
// Step 1: Suppress — stops all messaging immediately
await cio.suppress(target.userId);
suppressed++;
// Step 2: Destroy — removes from billing
await cio.destroy(target.userId);
deleted++;
// Rate limit to 50/sec for bulk operations
await new Promise((r) => setTimeout(r, 20));
} catch (err: any) {
errors++;
console.error(`Failed ${target.userId}: ${err.message}`);
}
if ((suppressed + errors) % 100 === 0) {
console.log(`Progress: ${suppressed} deleted, ${errors} errors`);
}
}
console.log(`\nResult: ${suppressed} suppressed, ${deleted} deleted, ${errors} errors`);
}
// Usage: Build target list from your database
// const inactiveUsers = await db.query(`
// SELECT id FROM users
// WHERE last_login_at < NOW() - INTERVAL '180 days'
// AND email_verified = false
// `);
// lib/customerio-dedup-events.ts
// Prevent sending duplicate events that inflate volume
import { createHash } from "crypto";
import { TrackClient, RegionUS } from "customerio-node";
const cio = new TrackClient(
process.env.CUSTOMERIO_SITE_ID!,
process.env.CUSTOMERIO_TRACK_API_KEY!,
{ region: RegionUS }
);
// Simple LRU dedup (use Redis in production)
const recentEvents = new Map<string, number>();
const MAX_CACHE = 50_000;
const DEDUP_WINDOW_MS = 60 * 1000; // 1 minute window
function isDuplicate(userId: string, eventName: string, data?: any): boolean {
const hash = createHash("sha256")
.update(`${userId}:${eventName}:${JSON.stringify(data ?? {})}`)
.digest("hex")
.substring(0, 12);
const last = recentEvents.get(hash);
if (last && Date.now() - last < DEDUP_WINDOW_MS) {
return true;
}
recentEvents.set(hash, Date.now());
// Prevent unbounded growth
if (recentEvents.size > MAX_CACHE) {
const cutoff = Date.now() - DEDUP_WINDOW_MS;
for (const [key, time] of recentEvents) {
if (time < cutoff) recentEvents.delete(key);
}
}
return false;
}
export async function trackDeduped(
userId: string,
name: string,
data?: Record<string, any>
): Promise<void> {
if (isDuplicate(userId, name, data)) {
return; // Skip duplicate
}
await cio.track(userId, { name, data });
}
// lib/customerio-sampling.ts
// Sample high-volume events to reduce API calls
const EVENT_SAMPLE_RATES: Record<string, number> = {
page_viewed: 0.1, // Sample 10% of page views
button_clicked: 0.25, // Sample 25% of clicks
search_performed: 0.5, // Sample 50% of searches
signed_up: 1.0, // Always track signups
checkout_completed: 1.0, // Always track purchases
subscription_cancelled: 1.0, // Always track cancellations
};
export function shouldTrack(eventName: string): boolean {
const rate = EVENT_SAMPLE_RATES[eventName] ?? 1.0;
return Math.random() < rate;
}
// Usage
if (shouldTrack("page_viewed")) {
await cio.track(userId, {
name: "page_viewed",
data: { url: "/pricing", sampled: true },
});
}
// scripts/cio-usage-monitor.ts
// Track your Customer.io usage trends
interface UsageMetrics {
identifyCalls: number;
trackCalls: number;
transactionalSends: number;
broadcastTriggers: number;
webhooksReceived: number;
}
class UsageMonitor {
private metrics: UsageMetrics = {
identifyCalls: 0,
trackCalls: 0,
transactionalSends: 0,
broadcastTriggers: 0,
webhooksReceived: 0,
};
increment(metric: keyof UsageMetrics): void {
this.metrics[metric]++;
}
report(): void {
console.log("\n=== Customer.io Usage Report ===");
console.log(`Period: ${new Date().toISOString()}`);
for (const [key, value] of Object.entries(this.metrics)) {
console.log(` ${key}: ${value.toLocaleString()}`);
}
const total = Object.values(this.metrics).reduce((a, b) => a + b, 0);
console.log(` TOTAL API calls: ${total.toLocaleString()}`);
}
reset(): void {
for (const key of Object.keys(this.metrics)) {
this.metrics[key as keyof UsageMetrics] = 0;
}
}
}
export const usageMonitor = new UsageMonitor();
| Optimization | Typical Savings | Implementation Effort |
|---|---|---|
| Delete inactive profiles (180+ days) | 15-30% profile cost | Low |
| Event deduplication | 5-15% event volume | Low |
| Event sampling (analytics events) | 50-80% event volume for sampled events | Low |
| Suppress bounced emails | 2-5% email cost | Low |
| Don't identify email-less users | 5-20% profile cost | Medium |
| Annual billing | 10-20% total cost | None |
After cost optimization, proceed to customerio-reference-architecture for enterprise patterns.
评论 (0)
暂无评论,成为第一个评论者吧!