Craft better prompts using proven optimization techniques — use when your prompt needs refinement

Swift concurrency review/fix: compiler errors, Sendable, isolation, remediation.

Frontend UI: pages, apps, components, polished non-generic design.

TDD: enforce RED-GREEN-REFACTOR, tests before code.

Write a markdown plan to .hermes/plans/; no execution.

Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.

W&B: log ML experiments, sweeps, model registry, dashboards.

Himalaya CLI: IMAP/SMTP email from terminal.

Delegate coding to OpenAI Codex CLI (features, PRs).

Track Apple devices/AirTags via FindMy.app on macOS.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

对前端代码进行安全审计，检测 XSS、CSRF 等漏洞。当用户请求代码审查或询问代码安全性时使用。

Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks.

进行系统化的代码审查，检查代码质量、安全性和性能。当用户要求审查代码、review 或检查代码时使用

Provides expert guidance on Git operations including branch management, commit best practices, merge conflicts, and version control workflows. Use when the user needs help with Git commands, workflows, or resolving repository issues.

Run tests, linting, and quality checks for WooCommerce development. Use when running tests, fixing code style, or following the development workflow in WooCommerce projects.

Bun shell scripting with Bun.$, Bun.spawn, subprocess management. Use for shell commands, template literals, or command execution.

Detect and analyze adverse drug event signals using FDA FAERS reports, drug labels, and disproportionality statistics (PRR, ROR, IC). Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, regulatory submissions, and detecting rare AE signals not visible in clinical trials.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use acli (Atlassian CLI) to interact with Jira Cloud — create, search, view, link, and edit work items via shell commands instead of MCP tools. Prefer acli over Atlassian MCP to minimize token usage.