发现 测试与安全 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Use when asked to create a deep-research handoff bundle: do web research, codebase analysis, Gemini Oracle critique, and produce a prompt + context folder on Desktop for another AI agent (include a zipped archi...
Use this when running or adding tests (compile/lint/unit/E2E), updating test utilities, or working with Playwright/visual testing in markdowntown.
Repo workflow for markdowntown CLI development and scans.
Monorepo workflow for coordinating CLI + web changes, tests, and docs in markdowntown.
Use this when working on the Workbench UI, Workbench state/store, export/compile pipeline, or adapter/target behavior (agents-md, claude-code, github-copilot, etc.).
Nostrstack API development (Fastify + Prisma) including routing patterns, services, tenancy resolution, LightningProvider integration, and Nostr endpoints. Use when editing apps/api (routes, services, providers...
Release readiness and monitoring workflow for Sketch Magic. Use when preparing launch checklists, verifying telemetry, or validating health endpoints before a public release.
Enforce Sketch Magic dev-readiness gates. Use when asked “are you done?”, when dev server errors appear, when proof video is required, or when verifying compile/lint/test/dev-smoke status.
Prompt iteration workflow for kid-friendly, realistic outputs. Use when tuning prompts, selecting styles, or when outputs look too similar to the original sketch.
Use this when running or adding tests (compile/lint/unit/E2E), updating test utilities, or working with Playwright/visual testing in markdowntown.
Unified QA verification for both web UI and CLI work. Use when tasks require QA evidence, test execution, or verification checklists.
Debug OpenAI/Gemini image generation failures for Sketch Magic. Use when `/api/convert` returns 500, when models are unsupported, when outputs are empty, or when provider timeouts/quota errors appear.
Use this when instrumenting analytics, reviewing event taxonomy, or handling privacy/redaction rules for markdowntown.
Atlas Simulator scan flow and next-step guidance for markdowntown. Use when working on folder scanning, tool detection, cwd handling, results panels, or scan-to-workbench CTAs.
Playwright QA workflow for Sketch Magic. Use when running mobile flow tests, visual baselines, snapshot updates, or debugging flaky WebKit/Chromium runs and port conflicts.
Parallelized multi-agent critique system using Gemini, Copilot, Claude, and Codex. Decomposes complex engineering tasks into specialized domains and synthesizes a single authoritative report.
Run and manage a single-instance Chrome DevTools MCP server on this machine, including start/stop/status/dedupe workflows and safe cleanup to prevent multiple chrome-devtools-mcp processes from running concurre...
Azure CLI (az) operations for resource groups, deployments (ARM/Bicep), app services/container apps, ACR images, Key Vault secrets, role assignments, and operational checks. Use when a request involves `az` com...
Use this when writing or updating docs/ content, UX specs, or cross-linking guides in markdowntown.
Local development workflow for nostrstack, including running API/gallery with logs, regtest stack usage, MCP Chrome DevTools verification, QA fallback, and environment/setup troubleshooting. Use when starting d...
GitHub CLI (gh) operations for repos, PRs/issues, workflows/runs, secrets/variables, releases/tags, and deployment-related automation. Use when a request involves gh commands, GitHub Actions workflows/runs, sec...
Nostr-specific workflows in nostrstack: identifier parsing, event/profile landing pages, relay fetch/caching rules, NIP-05 identity resolution, and reference rendering. Use when working on Nostr event handling,...
Security and privacy guardrails for Sketch Magic. Use when handling API keys, logs, uploads, telemetry, or when debugging errors to avoid leaking secrets or user images.
Frontend UX and design system guidance for markdowntown. Use when changing UI, layout, styling, typography, motion, or Tailwind classes, especially for Workbench, Atlas, and Library surfaces.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。