用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill mindtickle-prod-checklist命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before / interrupt_after and Command(resume=...) — JSON-serializable state, clean resume semantics, and UI wiring for approval decisions. Use when adding an approval gate before an expensive tool call, wiring a Slack/web UI for agent approvals, or debugging a graph that crashes on interrupt. Trigger with "langgraph human in loop", "langgraph interrupt_before", "langgraph approval flow", "Command resume", "langgraph HITL".
正在显示 SKILL.md
| name | mindtickle-prod-checklist |
| description | Prod Checklist for MindTickle. Trigger: "mindtickle prod checklist". |
| allowed-tools | Read, Write, Edit |
| version | 1.7.0 |
| license | MIT |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
| tags | ["saas","mindtickle","sales"] |
| compatibility | Designed for Claude Code |
MindTickle powers sales readiness at scale, managing user provisioning via SCIM, course progress tracking across thousands of reps, and quiz completion data that feeds pipeline forecasting. A production integration must enforce multi-tenant isolation through company-specific headers, handle SCIM provisioning race conditions during bulk onboarding, and ensure quiz score integrity under concurrent submissions. Misconfigurations here can leak training data across tenants, corrupt completion records, or silently drop user provisioning events during org restructures.
X-Company-Id)X-Company-Id header injected server-side (never exposed to client)https://api.mindtickle.com/v2 (production, not sandbox)X-Company-Id header included on every request for tenant isolationX-RateLimit-* response headers)limit and offset)X-Company-Id at API gateway levelasync function validateMindTickleProduction(apiKey: string, companyId: string): Promise<void> {
const base = 'https://api.mindtickle.com/v2';
const headers = {
Authorization: `Bearer ${apiKey}`,
'X-Company-Id': companyId,
'Content-Type': 'application/json',
};
// 1. Connectivity check
const ping = await fetch(`${base}/health`, { headers, signal: AbortSignal.timeout(5000) });
console.assert(ping.ok, `API unreachable: ${ping.status}`);
// 2. Auth and tenant validation
const users = await fetch(`${base}/users?limit=1`, { headers });
console.assert(users.status !== 401, 'Invalid API key');
console.assert(users.status !== 403, 'Company ID rejected — check tenant config');
.(users., );
remaining = (users..() ?? );
.(remaining > , );
scimUrl = process..;
(scimUrl) {
scim = (, {
: { : },
: .(),
});
.(scim., );
}
courses = (, { headers });
.(courses., );
.();
}
| Check | Risk if Skipped | Priority |
|---|---|---|
| X-Company-Id tenant isolation | Cross-tenant data leak, compliance violation | Critical |
| SCIM conflict handling | Duplicate users or dropped provisioning during bulk onboard | Critical |
| Quiz submission retry queue | Lost quiz scores corrupt sales readiness metrics | Critical |
| Idempotent progress writes | Duplicate course completions inflate training KPIs | High |
| IdP-MindTickle user reconciliation | Ghost accounts retain access after offboarding | High |
See mindtickle-security-basics.