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, 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 |
|---|---|---|
| 440 | catalog plugins (catalog-entry cohort) | node scripts/generate-readme-toc.mjs over marketplace.extended.json |
| 2,984 | 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 | 37 |
| 🎭 | AI Agents & Agency | 9 |
| 🔌 | API Development | 26 |
| 💼 | Business Tools | 6 |
| 👥 | Community | 20 |
| ₿ | Crypto & Web3 | 27 |
| 💾 | Database | 26 |
| 🎨 | Design | 2 |
| 🔧 | DevOps & Infrastructure | 36 |
| 📚 | Examples & Templates | 5 |
| 🧩 | MCP Servers | 17 |
| 📦 | Packages | 5 |
| ⚡ | Performance | 25 |
| ✅ | Productivity | 29 |
| 🎁 | SaaS Skill Packs | 105 |
| 🔐 | 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: canva-reliability-patterns
description: "Implement reliability patterns for Canva Connect API \u2014 circuit\
\ breakers, idempotency, graceful degradation.\nUse when building fault-tolerant\
\ Canva integrations, implementing retry strategies,\nor adding resilience to production\
\ Canva services.\nTrigger with phrases like \"canva reliability\", \"canva circuit\
\ breaker\",\n\"canva resilience\", \"canva fallback\", \"canva fault tolerance\"\
.\n"
allowed-tools: Read, Write, Edit
version: 1.5.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- design
- canva
compatibility: Designed for Claude CodeProduction-grade reliability patterns for the Canva Connect API. The API has async operations (exports, uploads, autofills) that can fail or timeout, OAuth tokens that expire every 4 hours, and rate limits that require backoff.
import CircuitBreaker from 'opossum';
const canvaBreaker = new CircuitBreaker(
async (fn: () => Promise<any>) => fn(),
{
timeout: 30000, // 30s before failure
errorThresholdPercentage: 50, // Open after 50% failure rate
resetTimeout: 60000, // Try again after 60s
volumeThreshold: 5, // Min 5 requests before evaluating
}
);
canvaBreaker.on('open', () => {
console.warn('[canva] Circuit OPEN — Canva API unreachable, failing fast');
});
canvaBreaker.on('halfOpen', () => {
console.info('[canva] Circuit HALF-OPEN — testing Canva recovery');
});
canvaBreaker.on('close', () => {
console.info('[canva] Circuit CLOSED — Canva API recovered');
});
// Usage
async function createDesignSafe(body: object, token: string) {
return canvaBreaker.fire(async () => {
return canvaAPI('/designs', token, {
method: 'POST',
body: JSON.stringify(body),
});
});
}
// When Canva is down, degrade gracefully instead of breaking the entire app
async function getDesignWithFallback(
designId: string,
token: string,
cache: LRUCache<string, any>
): Promise<{ data: any; source: 'live' | 'cache' | 'placeholder' }> {
try {
const data = await canvaBreaker.fire(async () =>
canvaAPI(`/designs/${designId}`, token)
);
cache.set(designId, data);
return { data, source: 'live' };
} catch {
// Try cached version
const cached = cache.get(designId);
if (cached) {
return { data: cached, source: 'cache' };
}
// Return placeholder
return {
data: {
design: {
id: designId,
title: 'Design temporarily unavailable',
urls: { edit_url: '#', view_url: '#' },
},
},
source: 'placeholder',
};
}
}
// Export, upload, and autofill jobs can fail — wrap with retry
async function resilientExport(
designId: string,
format: object,
token: string,
maxRetries = 2
): Promise<string[]> {
for (let attempt = 0; attempt <= maxRetries; attempt++) {
try {
// Start export
const { job } = await canvaAPI('/exports', token, {
method: 'POST',
body: JSON.stringify({ design_id: designId, format }),
});
// Poll with timeout
const urls = await pollWithTimeout(job.id, token, 60000);
return urls;
} catch (error: any) {
if (attempt === maxRetries) throw error;
// Don't retry on client errors (400, 403, 404)
if (error.status && error.status < 500 && error.status !== 429) throw error;
const delay = 5000 * Math.pow(2, attempt);
console.warn(`Export attempt ${attempt + 1} failed, retrying in ${delay / 1000}s`);
await new Promise(r => setTimeout(r, delay));
}
}
throw new Error('Unreachable');
}
async function pollWithTimeout(
exportId: string,
token: string,
timeoutMs: number
): Promise<string[]> {
const deadline = Date.now() + timeoutMs;
while (Date.now() < deadline) {
const { job } = await canvaAPI(`/exports/${exportId}`, token);
if (job.status === 'success') return job.urls;
if (job.status === 'failed') throw new Error(`Export failed: ${job.error?.code}`);
await new Promise(r => setTimeout(r, 2000));
}
throw new Error('Export polling timeout');
}
// Token refresh is critical — handle every failure mode
async function resilientTokenRefresh(
refreshToken: string,
config: { clientId: string; clientSecret: string }
): Promise<{ accessToken: string; refreshToken: string; expiresAt: number } | null> {
const basicAuth = Buffer.from(`${config.clientId}:${config.clientSecret}`).toString('base64');
for (let attempt = 0; attempt < 3; attempt++) {
try {
const res = await fetch('https://api.canva.com/rest/v1/oauth/token', {
method: 'POST',
headers: {
'Authorization': `Basic ${basicAuth}`,
'Content-Type': 'application/x-www-form-urlencoded',
},
body: new URLSearchParams({
grant_type: 'refresh_token',
refresh_token: refreshToken,
}),
signal: AbortSignal.timeout(10000),
});
if (res.ok) {
const data = await res.json();
return {
accessToken: data.access_token,
refreshToken: data.refresh_token,
expiresAt: Date.now() + data.expires_in * 1000,
};
}
if (res.status === 400 || res.status === 401) {
// Invalid refresh token — user must re-authorize
console.error('[canva] Refresh token invalid — user must re-authorize');
return null; // Signal caller to initiate new OAuth flow
}
// 5xx — retry
} catch {
// Network error — retry
}
await new Promise(r => setTimeout(r, 2000 * Math.pow(2, attempt)));
}
console.error('[canva] Token refresh failed after 3 attempts');
return null;
}
interface FailedOperation {
id: string;
operation: 'export' | 'autofill' | 'upload';
payload: any;
userId: string;
error: string;
attempts: number;
lastAttempt: Date;
}
class CanvaDeadLetterQueue {
constructor(private db: Database) {}
async add(op: Omit<FailedOperation, 'id' | 'lastAttempt'>): Promise<void> {
await this.db.dlq.insert({
...op,
id: crypto.randomUUID(),
lastAttempt: new Date(),
});
}
async processNext(getToken: (userId: string) => Promise<string | null>): Promise<boolean> {
const entry = await this.db.dlq.findOne({ attempts: { $lt: 5 } });
if (!entry) return false;
const token = await getToken(entry.userId);
if (!token) {
console.warn(`DLQ: User ${entry.userId} has no valid token — skipping`);
return false;
}
try {
await this.retryOperation(entry, token);
await this.db.dlq.delete(entry.id);
return true;
} catch {
await this.db.dlq.update(entry.id, {
attempts: entry.attempts + 1,
lastAttempt: new Date(),
});
return false;
}
}
private async retryOperation(entry: FailedOperation, token: string) {
switch (entry.operation) {
case 'export': return canvaAPI('/exports', token, { method: 'POST', body: JSON.stringify(entry.payload) });
case 'autofill': return canvaAPI('/autofills', token, { method: 'POST', body: JSON.stringify(entry.payload) });
}
}
}
Reliability controls emit redacted operation status, retry/circuit state, aggregate latency, and reconciliation result. They do not record tokens, design contents, signed asset URLs, or raw webhook payloads.
For a timed-out export, retain the idempotency key, check the existing job status within the approved scope, and retry only if no completed result exists. If the circuit opens, pause new exports and alert the owner; do not fan out retries or recreate designs blindly.
| Issue | Cause | Solution |
|---|---|---|
| Circuit stays open | Threshold too low | Increase volumeThreshold |
| Token refresh fails | Single-use refresh token reused | Always store new token |
| Export retries waste quota | Re-starting export | Track export job IDs |
| DLQ growing | Persistent issue | Investigate root cause |
For policy enforcement, see canva-policy-guardrails.
评论 (0)
暂无评论,成为第一个评论者吧!