发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
python-dev-guidelines
Python development best practices for DevSecOps. Covers type hints, error handling, testing with pytest, logging patterns, dependency management, security practices, and code organization. Use when writing Python code, creating modules, setting up projects, or debugging Python applications.
lexic-workflow-hygiene
Proactively manage workflow lifecycle: suggest templates after successful runs, check for stale or paused runs when resuming sessions, search templates before starting new workflows from scratch, and guide users toward the right capture tool (learn vs save). Activate when: (1) a run completes successfully, (2) a session starts or the user says "where were we", (3) the user describes a workflow that sounds like something done before, (4) the user wants to capture something and the right tool (learn vs save) isn't obvious.
vfx-visual-effects-basics
Master fundamental visual effects creation and implementation
rebase
Rebase the current branch onto the latest main. Use when asked to rebase, sync with main, update branch, or pull latest changes. Fetches and rebases onto latest main; does not push automatically.
Liangliang619-liangliangprivaterepo-excel-xlsx
Comprehensive, practical guidance for creating, editing, and analyzing Microsoft Excel .xlsx workbooks and related spreadsheet files. Explains when to treat CSV as a plain data‑exchange format versus when to keep a live workbook that preserves formulas, styles, merged cells, and worksheet structure. Key recommendations include using pandas for heavy data analysis and CSV/value extraction, and using openpyxl (or Excel libraries) when you must preserve formulas, cell styles, merged ranges, or workbook‑level metadata. The guidance highlights common pitfalls—Excel date-serial quirks (the 1900 leap-year bug, fractional day/time formats), format/locale conversions, and cross-platform differences (Excel/LibreOffice/Google Sheets)—and advises writing formulas into cells rather than hard‑coding computed results when a workbook must remain dynamic. Use cases: ETL to/from spreadsheets, reproducible models, reporting templates, and cross‑platform spreadsheet compatibility checks.
veo-video-generation
This skill teaches agents how to generate videos with Veo 3.1 using the Gemini API with an emphasis on REST and Python. It covers request/response shapes, long-running operations (polling), downloading results, and the major Veo controls (aspect ratio, resolution, duration, negative prompts, reference images, first/last frame interpolation, and video extension).
testing
For testing with Light Protocol programs and clients on localnet, devnet, and mainnet validation.
hyperframes
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill.
xiaohongshu-mastery-mentor
Top Xiaohongshu (XHS) operations mentor. Distills viral methodologies for the six leading Xiaohongshu niches (beauty / fashion / mother & baby / home / food / knowledge) + an in-depth analysis of the Xiaohongshu CES distribution algorithm (status as of April 2026) + a seeding-to-conversion-to-private-domain closed-loop operations manual. Extracts 7 core mental models (audience reverse-funnel / search pool / "fries" leverage, etc.), 12 decision-making heuristics, a complete 6-step SOP for topic → cover → body → tags → publish → maintenance, and 4 monetization paths (brand deals / live streaming / store / private domain). Use when users mention terms like “Xiaohongshu”, “Xiaohongshu note”, “Xiaohongshu operations”, “Xiaohongshu follower growth”, “Xiaohongshu topic selection”, “Xiaohongshu viral”, “seeding”, “fries”, “Xiaohongshu algorithm”, “Xiaohongshu throttling/limited reach”, “Xiaohongshu brand deals”, “Xiaohongshu store”, “Xiaohongshu cover”, “Xiaohongshu title”, “Xiaohongshu MCN”, “bugu”, “xhs”. It should also trigger when a user asks things like “How do I write this note?”, “Help me come up with Xiaohongshu content”, “How to do Xiaohongshu”, “Post on Xiaohongshu”, or “Start a Xiaohongshu account.”
enable-self-service
Provides self-service capabilities for developers to manage resources and deployments across cloud environments. Use when enabling developers, implementing self-service, or improving developer experience.
validate-ui
Validate UI in the browser for layout, responsiveness, and interaction issues.
wordpress-mcp-setup
Connect Hermes to a WordPress site via MCP (WordPress/mcp-adapter). Covers discovery, auth, config, pitfalls for local (ServBay) and remote WP installs, and full Elementor MCP tool reference.
ai-code-review-guardrails
Defines guardrails and rules for AI-assisted code review: what to check, severity levels, feedback format, and boundaries. Use when establishing code review standards, configuring review automation, or defining what AI reviewers should and should not do. Complements security-evaluator for security-focused review.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Writing Skills
TODO: Describe the purpose in 1-2 sentences.
refactoring
AI-powered code refactoring and modernization. Use this skill for code cleanup, technical debt reduction, framework migration, and improving code quality.
coding-agent-loops
Run long-lived AI coding agents in persistent tmux sessions with retry loops and completion hooks. Use when running multi-step coding tasks, GSD phases, or any programming agent that needs to survive restarts, retry on failure, and notify on completion.
Lua2147-claude-toolkit-catalog-stagehand
Done. Three files created at `.claude/skills/stagehand/`:
agentic-actions-auditor
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
quality-acceptance-report
当产品版本需要正式验收时使用。验收测试报告自动生成,整合测试结果、验收标准、遗留问题和签收确认,产出可签收的验收报告文档。关键词:验收报告、验收测试、测试报告、签收报告、UAT报告、验收确认。
ai-context-handoff
A skill for generating a lean, high-value continuation package for AI-to-AI handoffs, optimized for low token usage and fast continuation. This skill focuses on preserving only the critical information required for implementation continuity while aggressively removing fluff, repetition, and non-essential context. The output should enable another AI agent to continue the project safely with minimal ambiguity, even in situations with limited context windows or low model quotas.
just
just is a handy command runner for saving and running project-specific commands. Features include recipe parameters, .env file loading, shell completion, cross-platform support, and recipes in arbitrary languages. This skill is triggered when the user says things like "create a justfile", "write a just recipe", "run just commands", "set up project automation with just", "understand justfile syntax", or "add a task to the justfile".
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Especialista em Anime
Activated when the conversation involves anime, manga, or light novels