发现 Skills

Selecting and implementing AWS services and architectural patterns. Use when designing AWS cloud architectures, choosing compute/storage/database services, implementing serverless or container patterns, or applying AWS Well-Architected Framework principles.

Support discovery and research workflows using PM Brain’s discovery frameworks (research interviews, continuous discovery, JTBD, segmentation, opportunity assessment, idea validation, problem-solution space, product-market-fit).

Generate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document — especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M&A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M&A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.

LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.

Comprehensive toolkit for Claude Code with 135+ agents, 176+ plugins, 42 commands, 20 hooks, 15 rules, and 400K+ skills via SkillKit

Personal AI assistant framework supporting multiple chat channels (DingTalk, Feishu, QQ, Discord, etc.) with extensible skills, local/cloud deployment, and cron scheduling.

```markdown

```markdown

```markdown

Build and configure personal AI agents with memory, personality, and autonomy using OpenHanako on Electron.

Extract structured PII spans from text using the OpenAI Privacy Filter 1.5B model reversed — returns what, where, and which type instead of masking.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Send an interactive Feishu tutorial card that showcases Dolores' core capabilities. Triggered when the user types 'tutorial' or 'help'.

Apply Kingdon's multiple streams framework to analyze how problems, policies, and politics converge to open policy windows. Use this skill when the user needs to explain why certain policies get adopted while others don't, identify policy windows and entrepreneurial opportunities, or analyze the agenda-setting process in public policy — even if they say 'why did this policy pass now', 'policy window', or 'how do issues get on the agenda'.

Convert disc-based ROM images from BIN/CUE to CHD and back with chdman from MAME or rom-tools. Use when the user needs to shrink, organize, verify, or round-trip CD-based game images on macOS or Windows, especially for RetroArch, DuckStation, PS1/PSX, Sega CD, TurboGrafx-CD, Neo Geo CD, or when they mention BIN/CUE, cue sheets, CHD, chdman, or rom-tools.

Format commit messages following conventional commits standard. Use when: writing commit messages, git commit, reviewing commit history. Keywords: commit, git, message, conventional, 提交, 訊息, feat, fix, refactor.

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when the user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know which Claude Code features they should use.

Provides templates, standards, and best practices for writing clear, comprehensive technical documentation

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

Compute common trading indicators from OHLCV price data for analysis and strategy development.

Collaborative planning using abstract roles (designer + inspiration + reviewer).

Investigate suspected bugs or run proactive code audits. Triggers: "bug", "broken", "doesn't work", "failing", "investigate bug", "debug", "find the bug", "troubleshoot", "audit code", "find bugs in", "code audit", "hunt bugs".

ESPHome + Home Assistant workflows for provisioning, adoption, entity naming, encryption keys (noise_psk / api encryption), OTA updates, and troubleshooting offline devices. Use when working with ESPHome Device Builder, the HA ESPHome integration, or when generating ESPHome YAML and validating entities in HA.

Read WeCom (Enterprise WeChat) Smart Sheet data directly via a backend HTTP interface without any browser JS memory operations. Cookies can be automatically extracted from a logged-in browser or provided manually. Use cases: (1) reading sheets outside the browser (2) bulk export (3) scheduled fetching (4) integration with other systems. Trigger keywords: WeCom API, smartsheet api, backend API, direct request, bulk export. Prerequisite: requires the WeCom document cookie (extracted from a logged-in browser or provided manually).