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: cursor-compliance-audit
description: 'Compliance and security auditing for Cursor IDE usage: SOC 2, GDPR,
HIPAA assessment, evidence
collection, and remediation. Triggers on "cursor compliance", "cursor audit", "cursor
security review",
"cursor soc2", "cursor gdpr", "cursor data governance".
'
allowed-tools: Read, Write, Edit, Bash(cmd:*)
version: 1.18.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- cursor
- security
- compliance
- audit
compatibility: Designed for Claude CodeAssess a Cursor deployment against approved privacy, identity, source-code, and audit controls. This is an evidence-backed configuration review, not legal certification.
.cursorignore settings to the approved baseline.Compliance and security auditing framework for Cursor IDE usage. Covers SOC 2, GDPR, and HIPAA assessment with audit checklists, evidence collection, and remediation guidance.
| Certification | Status | Notes |
|---|---|---|
| SOC 2 Type II | Certified | Annual audit, report available on request |
| Penetration testing | Annual | Results shared under NDA (Enterprise) |
| Encryption at rest | AES-256 | All stored data |
| Encryption in transit | TLS 1.2+ | All API communications |
| Zero data retention | Available | Via Privacy Mode |
| GDPR compliance | Yes | EU data processing supported |
| HIPAA BAA | Not available (as of early 2026) | See HIPAA section |
Developer Machine
│
├─► Cursor Client ──► Cursor API (US/EU) ──► Model Provider
│ (local) (routing + auth) (OpenAI/Anthropic)
│ │
│ └─► Zero retention agreement
│
├─► Codebase Index ──► Embedding API ──► Turbopuffer (vectors)
│ (no plaintext stored)
│
└─► Local Settings (API keys, preferences)
(never transmitted)
[ ] SSO (SAML/OIDC) configured and enforced
[ ] MFA enabled at Identity Provider level
[ ] RBAC roles assigned: Owner, Admin, Member
[ ] Inactive users deprovisioned (SCIM or manual)
[ ] Access review completed (quarterly)
Evidence:
- SSO configuration screenshot from admin dashboard
- IdP MFA policy documentation
- User list export from Cursor admin
- SCIM sync logs (if applicable)
[ ] Privacy Mode enforced at team level
[ ] .cursorignore configured for sensitive files
[ ] Data classification aligned with .cursorignore patterns
[ ] Model provider data retention agreements documented
[ ] BYOK configuration documented (if applicable)
Evidence:
- Privacy Mode enforcement screenshot
- .cursorignore file contents (committed to git)
- Cursor data use policy acceptance
- API key provider agreements
[ ] All Cursor API calls use TLS 1.2+
[ ] Corporate proxy configured with valid certificates
[ ] No self-signed certificates or TLS bypasses
[ ] Network firewall rules documented
Evidence:
- Network architecture diagram showing Cursor data flows
- Firewall rules for cursor.com domains
- Proxy configuration settings
[ ] Admin dashboard usage analytics reviewed monthly
[ ] Anomalous usage patterns investigated
[ ] Seat utilization tracked for access reviews
Evidence:
- Monthly usage report screenshots
- Incident response log for anomalies
- User activity summary
Data Category: Source code snippets
Processing Purpose: AI-assisted code generation
Legal Basis: Legitimate interest (developer productivity)
Data Location: In-transit only (zero retention with Privacy Mode)
Sub-processors: OpenAI, Anthropic, Turbopuffer (embeddings)
Retention: None (Privacy Mode) or per provider policy (no Privacy Mode)
| Right | Cursor Support |
|---|---|
| Right to access | Account settings at cursor.com/settings |
| Right to erasure | Account deletion removes all server-side data |
| Right to portability | Settings export (settings.json) |
| Right to restriction | Privacy Mode limits processing |
| Right to object | Privacy Mode + .cursorignore |
[ ] Data Processing Agreement (DPA) signed with Cursor (Enterprise)
[ ] Privacy Mode enabled for all EU team members
[ ] Sub-processor list reviewed (cursor.com/privacy)
[ ] Data protection impact assessment (DPIA) completed
[ ] Team briefed on not pasting PII into Chat/Composer
Evidence:
- Signed DPA
- Privacy Mode enforcement confirmation
- DPIA document
- Team training records
Current status: Cursor does not offer a Business Associate Agreement (BAA) as of early 2026.
If your organization handles PHI:
1. Enable Privacy Mode (mandatory)
2. Configure .cursorignore to exclude ALL PHI-containing files:
.cursorignore:
**/patient-data/
**/medical-records/
**/hl7/
**/fhir-resources/
**/*.hl7
**/*.ccda
3. Consider BYOK through Azure with BAA:
- Azure OpenAI has HIPAA BAA option
- Route Cursor AI requests through Azure
- Azure handles data governance
4. Train developers: NEVER paste PHI into Chat or Composer
5. Code review policy: verify no PHI in AI-generated code
6. CRITICAL: Consult your compliance team before any Cursor
usage with systems that process PHI
Severity: High
Risk: Code may be retained by model providers for training
Remediation:
1. Admin Dashboard > Privacy > Enable enforcement (immediate)
2. Notify all team members (email)
3. Verify enforcement: check each member's status in dashboard
4. Document: date of enforcement, approval authority
Severity: Medium
Risk: Sensitive files may be included in AI context
Remediation:
1. Create .cursorignore at project root
2. Add patterns for: .env*, secrets/, credentials/, PII directories
3. Commit to git (PR review required)
4. Verify: Cursor Settings > Codebase Indexing > View included files
5. Confirm sensitive files absent from indexed list
Severity: Medium
Risk: Shared or unrotated API keys
Remediation:
1. Audit which team members use BYOK keys
2. Verify keys are personal (not shared team keys)
3. Implement quarterly key rotation schedule
4. Document key management policy
5. Consider centralizing through Azure gateway (Enterprise)
Severity: Medium
Risk: Former employees retaining Cursor access
Remediation:
1. Export current member list from admin dashboard
2. Cross-reference with HR active employee list
3. Deactivate accounts for departed employees
4. Enable SCIM for automatic deprovisioning
5. Schedule quarterly access reviews
| Condition | Safe response |
|---|---|
| Admin evidence is incomplete | Mark the control unverified; do not infer compliance from plan level or screenshots alone. |
| Sensitive code may have been exposed | Activate the incident process, restrict evidence distribution, and consult security/privacy owners. |
| A policy conflicts with tenant configuration | Keep the restrictive policy in effect and escalate for a documented decision. |
For a privacy-mode control, capture the enforced tenant setting and a sampled member status, redact personal identifiers, and record the reviewer and date. If enforcement is absent, create a high-severity finding, assign the tenant admin, and verify again after the approved change.
评论 (0)
暂无评论,成为第一个评论者吧!