92 boosters for "triggers" — open source, verified from GitHub, ready to install
从先知社区5600+篇安全文档中提炼的漏洞挖掘核心思维框架。 所有安全研究都遵循：假设 → 测试 → 迭代优化 Corner case 是所有漏洞类型的共同温床
Guide the practitioner through creating a complete, linked artifact chain for a new feature: PRD slice → Technical Specification → ADR identification → Task breakdown. Ask the practitioner: 1. What is the feature name? (5 words max for the title)
Automates GitHub issue creation and management by inferring type, labels, and milestones from conversation context, saving developers time on routine issue tracking tasks.
Analyze, review, and provide recommendations for distributed system designs. Use when: (1) Reviewing existing system architectures for gaps or improvements, (2) Analyzing system designs for scalability, reliability, or performance issues, (3) Providing recommendations on load balancing, caching, databases, sharding, replication, messaging, rate limiting, authentication, resilience, or monitoring, (4) Assessing trade-offs in system design decisions, (5) Creating system design review documents with gaps and recommendations. Triggers: "review my system design", "analyze this architecture", "what are the gaps", "system design recommendations", "scalability review", "reliability analysis".
A skill that enables Claude to take screenshots to verify visual state and debug GUI applications, particularly useful for developers working with visual tools and uncertain operations.
A Telegram automation assistant that helps users digest unread messages, analyze writing style, and draft/publish posts to channels. Ideal for power Telegram users and content creators seeking workflow automation.
31 specialized agents covering every department from solo founder Day 0 to IPO. 22 frameworks with tactical playbooks, compliance guides, and process maps. Before loading any agent files, consult . It contains:
A GDExtension (C++) plugin for Godot 4 that brings full Solana blockchain support to game development. Write GDScript to send transactions, manage wallets, mint NFTs, and interact with Anchor programs — on Windows, Linux, macOS, Web, Android, and iOS.
Recall automatically searches across memory sources when users make vague references to past conversations, helping an AI assistant reconstruct context without guessing. Ideal for users who frequently reference earlier discussions and need reliable context retrieval.
Videos with 80%+ completion get 2-3x algorithmic reach. Your hook determines everything. Layer these elements for maximum impact: 1. Base Layer — Ambient bed (room tone, wind, hum) or silence
Transformation content is the highest-engagement format on social media. This skill generates precise Seedance 2.0 prompts that capture the full emotional arc of change: tension, reveal, payoff. Before generating prompts, establish: Show both states in rapid alternation — before/after/before — withi
A complete system for crafting Seedance 2.0 prompts on Higgsfield that feature AI avatars, digital personas, virtual presenters, and synthetic characters as the primary subject. This skill covers everything from photorealistic digital humans to stylized 3D characters, including hook patterns, enviro
Transform podcast audio into cinematic visual content using Seedance 2.0 on Higgsfield. This skill produces video prompts that replace static audiograms with storytelling-driven visual experiences built entirely from constructed imagery. The hook is the opening frame that stops the scroll. It must c
The first two seconds determine whether a viewer stops scrolling. These patterns open with immediate visual authority. Luxury camera work operates within a narrow, controlled vocabulary. No exceptions. The most used luxury camera move. Camera travels toward subject at 0.1x–0.3x of normal speed. Tota
Seedance 2.0 accepts multi-modal inputs and produces short-form cinematic video output. Before writing any prompt, confirm the assets available: Before generating a prompt, answer these questions: Every course promo follows one arc:
Traditional testimonials fail because they're static talking heads in flat lighting. Cinematic social proof makes viewers feel the transformation. Show the result first, the emotion second, the person third. The first two seconds determine whether the viewer stays. Every testimonial video needs an i
The most powerful personal brand camera move. Communicates: "this person is worth getting closer to." Creates authenticity by mimicking doc-style camera work. Shows the subject from multiple angles, communicating confidence.
When generating a prompt, collect or infer: Seedance 2.0 prompt structure: Each prompt block should be 15–25 lines covering: scene, camera, lighting, timing breakdown, motion notes, and sound direction.
1. Never show a flat screenshot. Always add depth — perspective, reflection, environment, motion. 2. The UI is the hero, not the narrator. Show the interface doing things, not someone explaining it. 3. Sound sells more than visuals. A satisfying click, a smooth transition sound, a bass hit on featur
Analyze skills using historical session data + static quality checks, output a diagnostic report with P0/P1/P2 prioritized fixes. Scores each skill on a 5-point composite scale across 8 dimensions. CSO (Claude/Agent Search Optimization) = writing skill descriptions so agents select the right skill a
The user provides a sentence or paragraph that needs verification. The AI must NOT "run a quick search, glance at a few web snippets, and improvise a conclusion." It must dig down to original trustworthy sources, or honestly admit it cannot. Five scenarios are covered: 1. Basic truthfulness check: w
Skill metadata (version, author, license, optional_mcps, fallback) lives in manifest.json and plugin.json. Claude Code only reads and from this frontmatter; extra keys are silently ignored, so they belong with
Turn a folder of raw files into a Markdown vault that an LLM can grep, and then answer questions over that vault responsibly. source file, carrying retrieval frontmatter (abstract / tags / synonyms) + a
<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
