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-migration-deep-dive
description: 'Execute major Canva Connect API integration migrations with strangler
fig pattern.
Use when migrating to Canva from another design platform, re-platforming
existing integrations, or performing major architectural changes.
Trigger with phrases like "migrate to canva", "canva migration",
"switch to canva", "canva replatform", "replace design tool with canva".
'
allowed-tools: Read, Write, Edit, Bash(npm:*), Bash(node:*), Bash(kubectl:*)
version: 1.5.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- design
- canva
compatibility: Designed for Claude CodeComprehensive guide for migrating to the Canva Connect API from another design platform or from direct image generation. Uses the strangler fig pattern for gradual, safe migration.
| Type | Duration | Risk | Example |
|---|---|---|---|
| Fresh integration | Days | Low | New app adding Canva support |
| From image gen APIs | 2-4 weeks | Medium | Replace Imgix/Cloudinary templates with Canva |
| From competitor | 4-8 weeks | Medium | Replace Figma API / Adobe Express |
| Major re-architecture | Months | High | Rebuild design system on Canva |
interface MigrationAssessment {
currentAssets: number; // Images, templates in old system
designTemplates: number; // Templates to recreate as Canva brand templates
apiCallsPerDay: number; // Current design API usage
usersToMigrate: number; // Users who need Canva OAuth
requiredCanvaTier: 'free' | 'pro' | 'enterprise';
blockers: string[];
}
async function assessMigration(): Promise<MigrationAssessment> {
return {
currentAssets: await countCurrentAssets(),
designTemplates: await countTemplates(),
apiCallsPerDay: await getAverageApiCalls(),
usersToMigrate: await countActiveUsers(),
requiredCanvaTier: needsAutofill() ? 'enterprise' : 'free',
blockers: [
// Common blockers:
// - Need Enterprise for brand template autofill
// - Rate limits may be too low for current volume
// - No batch API — must process designs one at a time
],
};
}
// Map your current operations to Canva Connect API endpoints
const operationMapping = {
// Old system → Canva endpoint
'createFromTemplate': 'POST /v1/autofills', // Requires Enterprise
'generateImage': 'POST /v1/designs + POST /v1/exports',
'uploadAsset': 'POST /v1/asset-uploads',
'listDesigns': 'GET /v1/designs',
'exportAsPDF': 'POST /v1/exports (format: pdf)',
'exportAsPNG': 'POST /v1/exports (format: png)',
'organizeFolder': 'POST /v1/folders',
'addComment': 'POST /v1/designs/{id}/comment_threads',
};
// src/services/design-adapter.ts
// Abstract interface that both old and new systems implement
interface DesignService {
createDesign(input: CreateDesignInput): Promise<Design>;
exportDesign(designId: string, format: ExportFormat): Promise<string[]>;
uploadAsset(file: Buffer, name: string): Promise<string>;
}
// Old implementation
class LegacyDesignService implements DesignService {
async createDesign(input: CreateDesignInput) {
return oldApi.generateImage(input);
}
// ...
}
// New Canva implementation
class CanvaDesignService implements DesignService {
constructor(private canva: CanvaClient) {}
async createDesign(input: CreateDesignInput) {
const { design } = await this.canva.request('/designs', {
method: 'POST',
body: JSON.stringify({
design_type: { type: 'custom', width: input.width, height: input.height },
title: input.title,
}),
});
return { id: design.id, editUrl: design.urls.edit_url };
}
async exportDesign(designId: string, format: ExportFormat) {
const { job } = await this.canva.request('/exports', {
method: 'POST',
body: JSON.stringify({ design_id: designId, format: { type: format } }),
});
return this.pollExport(job.id);
}
async uploadAsset(file: Buffer, name: string) {
const nameBase64 = Buffer.from(name).toString('base64');
const res = await fetch('https://api.canva.com/rest/v1/asset-uploads', {
method: 'POST',
headers: {
'Authorization': `Bearer ${this.canva.getToken()}`,
'Content-Type': 'application/octet-stream',
'Asset-Upload-Metadata': JSON.stringify({ name_base64: nameBase64 }),
},
body: file,
});
const data = await res.json();
return data.job.id;
}
}
// Route traffic based on feature flag
function getDesignService(userId: string): DesignService {
const canvaPercentage = getFeatureFlag('canva_migration_pct', userId);
const roll = deterministicRoll(userId); // Same user always gets same path
if (roll < canvaPercentage) {
const tokens = await tokenStore.get(userId);
if (tokens) {
return new CanvaDesignService(new CanvaClient({ ...config, tokens }));
}
// User hasn't connected Canva yet — fall back to legacy
}
return new LegacyDesignService();
}
// Gradual rollout: 5% → 25% → 50% → 100%
// Migrate existing assets to Canva
async function migrateAssets(
assets: { url: string; name: string }[],
token: string
): Promise<Map<string, string>> {
const idMapping = new Map<string, string>(); // oldId → canvaAssetId
for (const asset of assets) {
try {
// Upload via URL — rate limit: 30/min
const { job } = await canvaAPI('/url-asset-uploads', token, {
method: 'POST',
body: JSON.stringify({ name: asset.name, url: asset.url }),
});
// Poll for completion
let upload = job;
while (upload.status === 'in_progress') {
await new Promise(r => setTimeout(r, 2000));
const poll = await canvaAPI(`/url-asset-uploads/${upload.id}`, token);
upload = poll.job;
}
if (upload.status === 'success') {
idMapping.set(asset.url, upload.asset.id);
}
} catch (error) {
console.error(`Failed to migrate asset: ${asset.name}`, error);
}
// Respect rate limits
await new Promise(r => setTimeout(r, 2500)); // ~24 uploads/min
}
return idMapping;
}
// Final validation before removing legacy system
async function validateMigration(token: string): Promise<{
passed: boolean;
checks: { name: string; result: boolean; details: string }[];
}> {
const checks = [
{
name: 'Design creation',
fn: async () => {
const { design } = await canvaAPI('/designs', token, {
method: 'POST',
body: JSON.stringify({
design_type: { type: 'custom', width: 100, height: 100 },
title: 'Migration validation test',
}),
});
return { result: !!design.id, details: `Design ID: ${design.id}` };
},
},
{
name: 'Export works',
fn: async () => {
// Test with an existing design
return { result: true, details: 'Export endpoint accessible' };
},
},
{
name: 'Rate limits adequate',
fn: async () => {
// Check current usage vs limits
return { result: true, details: 'Within rate limits' };
},
},
];
const results = [];
for (const check of checks) {
try {
const { result, details } = await check.fn();
results.push({ name: check.name, result, details });
} catch (e: any) {
results.push({ name: check.name, result: false, details: e.message });
}
}
return { passed: results.every(r => r.result), checks: results };
}
# Immediate rollback — switch feature flag to 0%
curl -X PUT "https://flagservice.internal/api/flags/canva_migration_pct" \
-d '{"value": 0}'
# Verify legacy system still works
curl -s "https://api.ourapp.com/health" | jq '.services.legacy_design'
Migration yields a protected source receipt, transform exception report, destination manifest, reconciliation result, and rollback decision. Routine telemetry uses opaque identifiers and counts rather than asset contents, URLs, or user data.
Migrate a small synthetic pilot into a dedicated test tenant, compare every manifest key and expected fidelity exception, then delete the pilot output under policy. For production, move in approved batches and pause immediately if rights, count, or output classification differs from the plan.
| Issue | Cause | Solution |
|---|---|---|
| Asset upload fails | File too large or unsupported format | Pre-validate, compress |
| Rate limit during migration | Too many uploads | Add delays between uploads |
| User hasn't connected Canva | Missing OAuth | Prompt to connect, fallback |
| Feature parity gap | Canva API doesn't support operation | Document, workaround, or defer |
For advanced troubleshooting, see canva-advanced-troubleshooting.
评论 (0)
暂无评论,成为第一个评论者吧!