发现 Skills

Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.

Use megfile’s APIs, SmartPath, configuration, and CLI to perform filesystem tasks easy across local FS, S3/OSS-style object storage, SFTP, WebDAV, HTTP, HDFS, and stdio.

Unified project health dashboard that aggregates all quality metrics

Parse Gemini CLI headless output (JSON and stream-JSON formats). Covers response extraction, stats interpretation, error handling, and tool call analysis. Use when processing Gemini CLI programmatic output.

Central authority for Claude–Gemini shared workspace architecture. Defines directory structure, artifact exchange, and file-naming conventions. Use when setting up dual-CLI workflows, deciding where to store AI artifacts, or managing cross-CLI file exchange.

Provides guidance on secure coding practices including OWASP Top 10 2025, CWE Top 25, input validation, output encoding, and language-specific security patterns. Use when reviewing code for security vulnerabilities, implementing security controls, or learning secure development practices.

Clari integration. Manage data, records, and automate workflows. Use when the user wants to interact with Clari data.

Finto.io integration. Manage data, records, and automate workflows. Use when the user wants to interact with Finto.io data.

Google Merchant Center integration. Manage Accounts. Use when the user wants to interact with Google Merchant Center data.

Open Policy Agent integration. Manage data, records, and automate workflows. Use when the user wants to interact with Open Policy Agent data.

WorkOS integration. Manage data, records, and automate workflows. Use when the user wants to interact with WorkOS data.

ZITADEL integration. Manage data, records, and automate workflows. Use when the user wants to interact with ZITADEL data.

Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.

Comprehensive assistance for HarmonyOS

Audits Go code for error handling best practices - proper wrapping with %w, preserved context, meaningful messages, no error swallowing. Use before committing Go code or during error handling reviews.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Write failing tests from requirements. Invoke for each todo before /implement.

Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either ErnOS ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow).

This skill should be used when the user says "work <issue>", "pick up <issue>", "implement <issue>", "do <issue>", or any variation where they hand you a Plane issue (by ID, URL, or description) and expect end-to-end implementation through to merge. Covers the full lifecycle: read issue, branch, plan, implement, commit, push, open PR, run adversarial bug analysis, remediate, and merge.

Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.

Generates new Claude Code custom slash command prompts following the established template structure. Use when the user asks to create a new slash command, generate a command prompt, or build a custom command for .claude/commands/

Comprehensive visual audit of the web application in the browser to identify and report UI/UX bugs.

Create a new module file for fe-tools utilities. Use when a new focused file under `packages/<pkg>/src/` is needed (e.g., new validators module).

Autonomous iterative code-review loop with externalized state, convergence detection, P0/P1/P2 findings, fresh context per pass.