发现 Skills

Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability.

Design short-term, long-term, and graph-based memory architectures

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Create MDX documentation files with proper frontmatter, imports, and component integration. Apply when creating or updating Fumadocs documentation pages in content/docs/.

A Dianping (大众点评) number-taking skill for Chinese users. It parses the number-taking page, reads the count of queued tables in one pass, takes a queue number following a real browser flow, and — when the agent is periodically awakened — takes a number or sends a departure reminder based on user thresholds.

Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "UX review", "users are confused", "heuristic evaluation", "form usability", or "navigation problems". Covers Nielsen's 10 heuristics, severity ratings, and information architecture. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

Specialized knowledge of Bash and Zsh scripting, shell automation, command-line tools, and scripting best practices. Use when the user needs to write, debug, or optimize shell scripts, work with command-line tools, automate tasks with bash/zsh, or asks for shell script help.

Academic literature orientation skill that searches papers via Consensus, builds a strategic search plan using PICO (default) or SPIDER / Decomposition / hybrid as fallbacks, and synthesizes findings into a professionally formatted Word document (.docx) research guide. "Grill-me" intake (research question specificity + framework hint + tentative depth) before the recon search; a second forcing checkpoint after Phase 2 confirms framework + sub-areas + depth before searches consume budget. Configurable depth (5/10/20 queries) controls coverage vs. speed. Output is a "launching pad" — not a finished review, but an orientation guide that lets a researcher dive in confidently. Triggers: "litreview on [topic]", "literature review on [topic]", "I'm starting a literature review on X", "I'm writing a paper on X", "help me research X", "I'm doing research on X", "can you help me research X". Do NOT trigger for single one-off paper searches where the user just wants a quick list — that's a plain Consensus search.

Guide for AI agents to source electronic components using parts-mcp — tool sequencing, decision patterns, and multi-step workflows

Use this skill when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol (MCP) servers into Claude Code plugins to enable external tools and services to be exposed as structured tools.

Synthesize qualitative and quantitative user research into structured insights and opportunity areas. Use when analyzing interview notes, survey responses, support tickets, or behavioral data to identify themes, build personas, or prioritize opportunities.

Guide for migrating Apache Airflow 2.x projects to Airflow 3.x. Use when the user mentions Airflow 3 migration, upgrade, compatibility issues, breaking changes, or wants to modernize their Airflow codebase. If you detect Airflow 2.x code that needs migration, prompt the user and ask if they want you to help upgrade. Always load this skill as the first step for any migration-related request.

Unity Editor control. Use when users want to enter Play mode, select objects, perform undo/redo, or execute menu commands. Triggers: play, stop, pause, select, undo, redo, menu, editor, Unity editor, Unity play, Unity undo, Unity select.

Find and analyze screenshots from ~/Downloads/Screenshots/ for UI/UX review. Use when asked to look at screenshots, review UI designs, inspect interface errors, analyze layout issues, or examine visual problems. Triggers on "check my latest screenshot", "review my UI", "analyze this screen capture".

Android APK unpacking and resource extraction tool for reverse engineering. Use when you need to decode APK files, extract resources, examine AndroidManifest.xml, analyze smali code, or repackage modified APKs.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Detects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).

Use when Phase 1 (research-direction-exploration) is complete and G1 gate has passed — subjects the research problem to adversarial defense-style questioning, classifies project intent, re-evaluates venue target, and produces a final feasibility ruling before any method design begins

USE WHEN the user wants to manage google groups settings via the `gws` CLI.

Write/reconstruct the NSFC main text "(3) Research Foundation" and simultaneously organize "Working Conditions" and "Research Risk Response", using an evidence chain to demonstrate project feasibility, alignment of resource conditions with research content, and executable risk plans. Suitable for users needing to write/update "Research Foundation, Preliminary Work, Feasibility Analysis, Working Conditions, Platform Team, Risk Response" and other scenarios.

Create and manage Google Slides presentations. Use when the user asks to create slides, add content to presentations, or export to PDF/PPTX.