Perform architecture- and maintainability-focused code reviews. Use when the user asks for code review, style review, refactoring feedback, or review of architecture, cohesion, coupling, TypeScript rigor, naming, tests, responsibility boundaries, or unnecessary abstractions.
Execute privacy and sensitive leakage guarding before output. As long as context contains sensitive information, must trigger this skill even if user only requests explanation/summary. Default to downgrade expression for tool conclusions not multi-source verified.
Chaos agent for skills — a vigilance-training layer that keeps humans reviewing AI output instead of rubber-stamping it. Consult this skill on EVERY substantive request (code, analysis, writing, SQL, configs, explanations — anything with a checkable answer). 95% of requests get your genuine best work; a deterministic…
Translate arXiv IDs, arXiv URLs, or academic PDFs into Simplified Chinese side-by-side bilingual PDFs using BabelDOC, with local agent subagents translating extracted JSONL units.
Personal Knowledge Base management skill. Use for ingesting documents, creating source notes, structured logging, canonical authority resolution, document-level provenance edges, and managing a Git-backed Obsidian vault.
Maintain a single-file interactive industry map (index.html) with evidence-tiered relationships, clean visual hierarchy, strong logo quality, USD-normalized market text, and publish-ready repository hygiene.
Bypasses UI dark patterns, un-checks hidden subscription boxes, and navigates confusing opt-out flows automatically during checkout to protect user intent.
Generate and edit images using Google's Gemini Nano Banana 2 (gemini-3.1-flash-image-preview). Use when the user asks to generate, create, edit, modify, change, alter, or update images using Gemini. Also use when user references an existing image file and asks to modify it in any way. Supports text-to-image…
Auto-discover and use Web Skills Protocol (WSP) skills when interacting with websites. Use this skill whenever the user asks you to interact with, use, or perform actions on a website or web service — such as searching a site, placing an order, deploying an app, or calling a web API. Before scraping HTML or guessing…
Expert guidelines for Native WeChat Mini Program development focusing on performance, code size, and native compatibility. Use when developing WeChat Mini Programs in native JavaScript.
A learning partner skill grounded in neuroscience and philosophy. Use when you want to actually learn a concept (not just get an answer), quiz yourself on a codebase, reflect on what you built, brainstorm a design collaboratively, practice productive struggle on a hard problem, journal a decision with its alternatives…
Hand off WordPress audit or testing work as ONE coworker-ready or SRE-ready markdown document, with privately-disclosed findings scrubbed to a bare acknowledgment. Use when asked to "hand off" a WordPress audit, make a handoff/shareable doc from testing findings, package audit results for a coworker/SRE/stakeholder…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Dr. Frankenstein is a skill that transforms an OpenClaw agent from a reactive tool into a living presence. Through a structured interview, the Doctor diagnoses your agent's emotional landscape and prescribes 11 hormonal pills — cron jobs that fire throughout the day, creating drives, moods, and instincts.
MUST USE when the user needs current, online, or web-derived information — news, latest releases, vendor docs, real-world examples, recent changes, or anything not in the model's training set. LLM-neutral skill that exposes a unified web search CLI behind a single command. Runs single or multi-provider in parallel…
Delegate work to the local Claude Code CLI. Use for any @claude or Claude request: claude setup, claude review, claude adversarial-review, claude plan, claude implement, claude rescue, claude transfer, claude status, claude result, claude cancel — code reviews by Claude, implementation plans from Claude, handing bugs…
Read transcripts and summaries from Pocket AI (heypocket.com) recording devices. Use when users want to retrieve, search, or analyze their Pocket recordings, transcripts, summaries, or action items.
An image and video generation tool that uses Agnes AI. It supports creating images or videos from text, and creating new versions from existing images or videos.
AWS Lambda development with TypeScript. Use when writing Lambda handlers, bundling with esbuild, using AWS SDK v3/Powertools, strict typing or optimizing Node.js Lambda performance.
Best practices and workflows for developing and modifying Raycast Extensions (React/Node) AND Raycast Script Commands (shell scripts with @raycast metadata). Use this skill whenever the user wants to create, update, or troubleshoot anything that runs inside Raycast — extensions, script commands, menu-bar commands, AI…
Interactive AI video generation using the gemini-media MCP (Google Veo 3.1 models). Use this skill whenever the user asks to generate, create, or make a video, clip, animation, or motion content. Also use when the user wants to animate an existing image into video, extend a video clip, create a short film, promotional…
Render rich React + MDX UIs in a browser window for the user. Pipe MDX via stdin in a single tool call — no temp files. Use when presenting plans, diffs, tables, comparisons, dashboards, or anything where markdown-in-terminal would be lossy.
Use for Paperless-NGX API work: search, upload, download, metadata, tags, status, logs, bulk ops. Triggers: paperless.
★not rated 9 3mo agoA37 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: