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-policy-guardrails
description: 'Implement Canva Connect API lint rules, policy enforcement, and automated
guardrails.
Use when setting up code quality rules for Canva integrations, implementing
pre-commit hooks, or configuring CI policy checks.
Trigger with phrases like "canva policy", "canva lint",
"canva guardrails", "canva best practices check", "canva eslint".
'
allowed-tools: Read, Write, Edit, Bash(npx:*)
version: 1.5.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- design
- canva
compatibility: Designed for Claude CodeAutomated policy enforcement for Canva Connect API integrations — prevent token leaks, enforce rate limit handling, require error handling, and validate OAuth configuration.
// eslint-rules/no-canva-credentials.js
module.exports = {
meta: {
type: 'problem',
docs: { description: 'Disallow hardcoded Canva OAuth credentials' },
},
create(context) {
return {
Literal(node) {
if (typeof node.value !== 'string') return;
const val = node.value;
// Canva client IDs start with "OCA"
if (/^OCA[A-Za-z0-9]{10,}/.test(val)) {
context.report({ node, message: 'Hardcoded Canva client ID detected. Use environment variable.' });
}
// Canva access tokens start with "cnvat_"
if (/^cnvat_[A-Za-z0-9]{20,}/.test(val)) {
context.report({ node, message: 'Hardcoded Canva access token detected. Use environment variable.' });
}
},
};
},
};
// eslint-rules/require-canva-retry.js
module.exports = {
meta: {
type: 'suggestion',
docs: { description: 'Canva API calls should handle 429 responses' },
},
create(context) {
return {
CallExpression(node) {
// Check for fetch calls to api.canva.com
if (node.callee.name === 'fetch' &&
node.arguments[0]?.value?.includes('api.canva.com')) {
// Check if parent is try-catch or has .catch()
const parent = node.parent;
if (parent.type !== 'AwaitExpression' ||
parent.parent?.type !== 'TryStatement') {
context.report({
node,
message: 'Canva API calls should be wrapped in try-catch with 429 handling',
});
}
}
},
};
},
};
# .pre-commit-config.yaml
repos:
- repo: local
hooks:
- id: canva-no-tokens
name: Check for Canva tokens
entry: bash -c 'git diff --cached --name-only | xargs grep -lE "(cnvat_|OCA[A-Z0-9]{10})" 2>/dev/null && echo "ERROR: Canva credentials found" && exit 1 || exit 0'
language: system
pass_filenames: false
- id: canva-no-raw-urls
name: Check for hardcoded Canva API URLs
entry: bash -c 'git diff --cached --name-only | xargs grep -lE "api\.canva\.com/rest/v1" --include="*.ts" --include="*.js" 2>/dev/null | while read f; do grep -n "api\.canva\.com" "$f" | grep -v "const.*BASE\|const.*URL\|import\|from\|//" && echo "WARNING: Direct Canva URL in $f — use client wrapper" && exit 1; done; exit 0'
language: system
pass_filenames: false
# .github/workflows/canva-policy.yml
name: Canva Policy Check
on: [push, pull_request]
jobs:
policy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Check for hardcoded credentials
run: |
if grep -rE "(cnvat_[a-zA-Z0-9]{20,}|OCA[A-Z0-9]{10,})" \
--include="*.ts" --include="*.js" --include="*.json" \
--exclude-dir=node_modules .; then
echo "ERROR: Hardcoded Canva credentials found"
exit 1
fi
- name: Check for unhandled API calls
run: |
# Warn if raw fetch to Canva without error handling
DIRECT_CALLS=$(grep -rn "fetch.*api\.canva\.com" \
--include="*.ts" --include="*.js" \
--exclude="*client.ts" --exclude="*test*" \
. 2>/dev/null | wc -l)
if [ "$DIRECT_CALLS" -gt 0 ]; then
echo "WARNING: $DIRECT_CALLS direct Canva API calls found outside client wrapper"
grep -rn "fetch.*api\.canva\.com" --include="*.ts" --include="*.js" \
--exclude="*client.ts" --exclude="*test*" .
fi
- name: Validate .env.example
run: |
if [ -f .env.example ]; then
for var in CANVA_CLIENT_ID CANVA_CLIENT_SECRET CANVA_REDIRECT_URI; do
if ! grep -q "^${var}=" .env.example; then
echo "WARNING: ${var} missing from .env.example"
fi
done
fi
// Prevent dangerous operations and enforce patterns at runtime
class CanvaGuardrails {
// Block requests without proper authorization header
static validateRequest(init: RequestInit): void {
const authHeader = (init.headers as Record<string, string>)?.['Authorization'];
if (!authHeader || !authHeader.startsWith('Bearer ')) {
throw new Error('Canva API call missing Bearer token');
}
}
// Enforce token is not expired before making call
static validateToken(expiresAt: number): void {
if (Date.now() > expiresAt) {
throw new Error('Canva access token expired — refresh before calling');
}
}
// Block sensitive operations based on environment
static validateEnvironment(operation: string): void {
const blocked = ['deleteAsset', 'deleteFolder'];
if (process.env.NODE_ENV !== 'production' && blocked.includes(operation)) {
// Allow in dev for testing
return;
}
// In production, require explicit confirmation
if (process.env.NODE_ENV === 'production' && blocked.includes(operation)) {
console.warn(`[guardrail] Destructive operation: ${operation}`);
}
}
// Rate limit self-check — don't send if we know we'll get 429
static checkRateLimit(
endpoint: string,
tracker: Map<string, { count: number; resetAt: number }>
): void {
const window = tracker.get(endpoint);
if (window && window.count <= 0 && Date.now() < window.resetAt) {
const waitMs = window.resetAt - Date.now();
throw new Error(`Rate limit exhausted for ${endpoint}. Wait ${(waitMs / 1000).toFixed(0)}s`);
}
}
}
Guardrails produce an allow/deny decision, policy version, opaque subject/scope identifiers, and a redacted audit result. They never convert a missing policy or failed validation into an implicit allow.
Before publishing an export, check the tenant, asset rights, approved destination, and retention policy against the reviewed allowlist. If anything is unknown, deny the request and require owner approval rather than bypassing the guardrail in CI or runtime.
| Issue | Cause | Solution |
|---|---|---|
| ESLint rule not firing | Wrong config path | Check plugin registration |
| Pre-commit skipped | --no-verify used | Enforce in CI |
| False positive on "OCA" | String matches pattern | Narrow regex or add allowlist |
| Guardrail blocks valid op | Too strict | Add environment-based exceptions |
For architecture blueprints, see canva-architecture-variants.
评论 (0)
暂无评论,成为第一个评论者吧!