搜索结果
全部能力
找到 1056 个相关结果 / 安全审计
软件工程 / 诊断修复
framework-accessibility
framework-accessibility
Framework-specific accessibility patterns and fix templates for React, Vue, Angular, Svelte, Next.js, and Tailwind CSS.
软件工程 / 部署发布
cypress-playwright-setup
cypress-playwright-setup
Sets up end-to-end testing with Cypress or Playwright including page objects, fixtures, and CI integration. Use when users request "E2E testing", "Cypress…
软件工程 / 诊断修复
openapi-generator
openapi-generator
Generates OpenAPI 3.0/3.1 specifications from Express, Next.js, Fastify, Hono, or NestJS routes. Creates complete specs with schemas, examples, and…
软件工程 / 诊断修复
deal-review-framework
deal-review-framework
Structured deal assessment using MEDDIC, BANT. Risk scoring, required evidence by stage, red flag detection, coaching points.
软件工程 / 诊断修复
fortify
fortify
Use when the workflow lacks error handling, has been failing in production, or needs retry logic, fallback strategies, and circuit breakers.
软件工程 / 部署发布
kubernetes-expert
kubernetes-expert
Expert-level Kubernetes cluster management, deployment strategies, networking, and production operations
软件工程 / 诊断修复
electron-dev
electron-dev
Electron desktop application development with React, TypeScript, and Vite. Use when building desktop apps, implementing IPC communication, managing…
软件工程 / 诊断修复
privacy-data-security
privacy-data-security
Design and operate privacy and data security programs for SEC-registered firms under Reg S-P, Reg S-ID, and SEC cybersecurity expectations. Use when the user…
软件工程 / 诊断修复
curl-command-generator
curl-command-generator
Generates ready-to-run cURL commands from Express, Next.js, Fastify, or other API routes. Creates copy-paste commands with proper headers, authentication, and…
软件工程 / 诊断修复
data-quality
data-quality
Design and operate data quality programs for financial data — golden source architecture, validation rules, data lineage, exception management, profiling, and…
软件工程 / 部署发布
scalability-playbook
scalability-playbook
Identifies performance bottlenecks and provides ordered scaling strategies with triggers, phased plans, and cost implications. Use for "scalability planning",…
软件工程 / 诊断修复
accessibility-tester
accessibility-tester
WCAG 2.2 AA compliance expert specializing in audits, automated testing, screen reader validation, and remediation.
软件工程 / 诊断修复
ln-636-manual-test-auditor
ln-636-manual-test-auditor
Audits manual test evidence quality: reproducibility, fail-fast behavior, expected evidence/golden files, idempotency, and documentation. Use when auditing…
软件工程 / 部署发布
emergency-release-workflow
emergency-release-workflow
Emergency release workflow for critical bug fixes and security patches. Use when production issues require fast-track deployment.
软件工程 / 诊断修复
python
python
Backend services development with Python emphasizing security, performance, and maintainability for JARVIS AI Assistant
软件工程 / 诊断修复
performance-metrics
performance-metrics
Evaluate investment performance on a risk-adjusted basis using industry-standard ratios and capture analysis. Use when the user asks about Sharpe ratio,…
软件工程 / 诊断修复
syncfusion-react-data-manager
syncfusion-react-data-manager
Implements Syncfusion DataManager for local/remote binding, CRUD, querying, caching, and middleware. Supports JsonAdaptor, ODataAdaptor, ODataV4Adaptor,…
软件工程 / 部署发布
context-mode
context-mode
Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.
软件工程 / 诊断修复
load-test-builder
load-test-builder
Creates load and performance tests with k6, Artillery, or autocannon to validate system behavior under stress. Use when users request "load testing",…
软件工程 / 诊断修复
skill-creator
skill-creator
Creates new Claude Code skills following repository conventions with proper structure, frontmatter, workflows, code examples, and reference files. Use when…