发现 Skills

Comprehensive evaluation toolkit for analyzing Claude skills across security, quality, utility, and compliance dimensions. This skill should be used when users need to evaluate a skill before installation, review before publishing, or assess overall quality and safety. Performs 5-layer security analysis, validates structure and documentation, checks compliance with skill-creator guidelines, and generates markdown reports with scoring and recommendations.

Formulate a git commit message. Use this skill whenever asked to create a commit message.

Generate comprehensive, fact-checked SAP technical articles and configuration guides with embedded images, flowcharts, and references. Use when users request SAP documentation, how-to guides, configuration tutorials, process explanations, or technical articles on SAP topics (ECC, S/4HANA, modules like SD, MM, FI, PP, ABAP, OData APIs, archiving, etc.). Creates professional Word documents with proper formatting and web-sourced visual aids with built-in image downloading.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Design guide RNAs for CRISPR-Cas9/Cas12a experiments using CRISPRscan and local scoring algorithms. Score guides for on-target activity using Rule Set 2 and Azimuth models. Use when designing sgRNAs for gene knockout, activation, or repression experiments.

Remove sequencing adapters from FASTQ files using Cutadapt and Trimmomatic. Supports single-end and paired-end reads, Illumina TruSeq, Nextera, and custom adapter sequences. Use when FastQC shows adapter contamination or before alignment of short reads.

Notion API for creating and managing pages, databases, and blocks.

Autonomous QA agent that performs deep code quality inspection in three phases. Phase 1: Full codebase analysis — maps architecture, stack, modules, dependencies, and generates a structured test-case document with every functionality and verification checkpoint organized by module. Phase 2: Code tracing and verification — traces each functionality end-to-end through the source code, verifying integrations, data flow, naming conventions, formatting, logic correctness, and edge cases. Produces a detailed report with pass/fail results per checkpoint. Phase 3: Fix iteration — presents all findings to the user for confirmation, then iterates through approved issues applying fixes directly in the codebase. Use when the user says "agent qa", "QA", "quality assurance", "quality inspection", "code audit", "code scan", "deep code review", "trace code", "verify code", "scan project", "quality check", "code quality", "audit code", "inspect code", or "run QA".

Maps a repository's architecture, conventions, patterns, and entry points. Use as a sub-agent when you need deep codebase understanding before making changes, debugging unfamiliar code, or onboarding to a new project. Returns a structured report covering structure, key files, patterns, and dependencies.

Create and manage stacked (dependent) pull requests for complex features

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

Comprehensive guide to Phaser game test seam usage, including discovery, common commands, troubleshooting, and best practices. Use when testing Phaser games, interacting with canvas-rendered content, or when DOM-based testing fails. Test seams are the PRIMARY method for Phaser game testing - DOM text search does not work with canvas-rendered text.

Design DoS-resistant systems or respond to an active denial-of-service attack. Use this skill when designing a new service and want to evaluate its attack surface and build in layered defenses, assessing whether a production system's architecture is DoS-hardened, investigating a traffic spike to determine whether it is an attack or a self-inflicted surge, detecting a client retry storm and needing to apply backoff and jitter fixes, building or reviewing a DoS mitigation system (detection + response pipeline), or deciding how to respond strategically to an ongoing attack without leaking information about your defenses to the adversary.

Build a complete mnemonic device or memory palace for anything the user needs to memorize, recall, or remember. Use this skill whenever someone wants to memorize a list, sequence, set of terms, vocabulary, historical dates, medical facts, or any body of material they struggle to recall. Activates on requests like "help me remember", "I can't recall", "memorize this", "make a mnemonic", "build a memory palace", "use method of loci", "create a flashcard structure", "remember in order", "recall under pressure", or "stop forgetting." Covers simple devices (acronyms, peg method, chunking, rhyme schemes) and complex devices (memory palace, method of loci, location-based recall). Does NOT teach the underlying subject matter — the learner must understand the content first; this skill organizes it for retrieval.

Design a concrete practice schedule that will actually make learning stick — not just feel productive. Use this skill when the user is preparing for a test, building a new skill, training others, or planning a study program and needs to decide how to structure practice sessions over time. Triggers include: user is relying on marathon study sessions or cramming before a deadline; user practices one topic exhaustively before moving to the next; user feels they know material during practice but forgets it on tests or in real situations; user wants to know how often to review flashcards or revisit past material; user needs to design a training curriculum for a team or class; user is switching between topics during study and wants to know if that is helping or hurting; user is preparing for a performance context (exam, job, sport) and must choose between depth on one skill versus breadth across many. This skill does NOT address memorization technique or recall strategy — use retrieval-practice-study-system for those.

Use this skill when the user asks to 'ask Gemini', 'get Gemini\'s opinion', 'have Gemini review', 'improve writing style', 'make less AI-sounding', 'get feedback on article', 'review this draft', 'Nano Banana', 'Gemini API help', 'Gemini models', or needs a second opinion on content, writing, code, or design. Supports text questions and up to 10 images.

This skill should be used when the user asks to "create an avatar from a photo", "generate a portrait avatar", "make a profile image", "convert headshot to styled portrait", "team member avatar", "character-style avatar", or needs likeness-preserving avatars in any style (including pixel art).

This skill should be used when the user asks to "upscale an image", "increase image resolution", "make image bigger", "enlarge image", or "enhance image resolution". Requires Vertex AI credentials.

Interact with X (Twitter) API v2. Post tweets, search, engage, moderate, and analyze — all from your AI agent. Full 36-command skill for Twitter/X automation.

name: alternative-data description: Alternative data for trading — satellite, credit card, web traffic, app usage. origin: ECT

Quick code review for small PRs (<100 lines). Focuses on basic code quality, naming conventions, and obvious bugs.

Use this skill when creating, modifying, or reviewing API endpoints and routes. This includes SDK routes (/v1/*), Dashboard routes (/api/v1/*), request/response structures, input validation, OpenAPI documentation, or API-related middleware.

Systematically debug issues using graph-powered code navigation — trace call chains, find execution paths, correlate with recent changes.

Upgrade bstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new.