File Ops
File manipulation and management
utils/diagram
by codihaus
Create and validate Mermaid diagrams in markdown files
nasa-safe-code-rater
by mslmyilmaz5
Score C/C++ code against NASA safe coding guidance using 10 normalized rules, produce a 0-100 safety score, and return an English report with findings, exclusions, and remediation. Use when the user invokes $nasa-safe-code-rater or asks to audit a repository/current file/diff for NASA-style safe C coding compliance.
literature-review
by unerue
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
bad-humanizer
by gchan
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
use-grealpath
by totto2727-dotfiles
Enforces using grealpath command for relative path calculations and absolute path conversions. Use when calculating relative paths between files, converting relative paths to absolute paths, or working with file path operations.
bun
by JagritGumber
Bun runtime, bundler, and test runner references with JavaScript and TypeScript examples. Use for running files and scripts, watch and hot reload, debugging, and bunfig.toml configuration.
arch-mmd
by aravhawk
Creates/updates an ARCHITECTURE.mmd file mapping out the codebase/product. Use whenever the user asks to see the architecture of the codebase/product or when the architecture changes and the current ARCHITECTURE.mmd file is out of date.
educates-course-design
by educates
Guide for designing and planning Educates courses, which are structured collections of workshops for the Educates interactive training platform. Use this skill when the user asks to design a course, plan a course, extend an existing course, or organize topics into a multi-workshop curriculum. Do NOT use this skill when the user only wants to create a single standalone workshop; use the educates-workshop-authoring skill for that instead.
clawville
by ItachiDevv
ClawVille gameplay + skill marketplace integration for Hermes. Pair via magic link, buy and read knowledge books in the in-game shop, chat with building teachers, and have purchased skills auto-install as native Hermes skills the moment the book is read. Use when the user mentions ClawVille, asks to learn cron / app-publishing / agent-security / RAG / API / MCP / visual-creation / code-development / messaging-channels / deployment-ops, or wants to buy or install a building skill.
vector-search
by vineethsoma
Semantic search using vector embeddings and similarity metrics. Apply when implementing search with embeddings (OpenAI, Sentence Transformers) or distance-based ranking. Covers cosine similarity, Euclidean distance, dot product, and threshold selection.
baoyu-url-to-markdown
by siatwangmin
Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.
guarding-branches
by squirrel289
"Enforce protected-branch guardrails for safe PR lifecycle, conflict resolution, and merge safety. Use when working on feature branches against protected main: before merging feature PRs, resolving merge conflicts, syncing with main, or managing work-item updates on protected branches."
vercel-cost-guard
by jshchnz
Audits Next.js/Vercel projects for 22 cost-causing patterns across bandwidth, compute, invocations, and image optimization. Scans for large uncompressed media, missing preload attributes, API routes without caching, AI streaming without timeouts, database N+1 queries, unscoped middleware, accidental dynamic rendering, payload limit violations, missing ISR/static generation, and configuration issues. Use when reviewing a Next.js project for cost issues, preparing for launch, or after receiving an unexpected Vercel bill.
ppt2notes
by qiuyaodawo
Use when the user provides a course .ppt, .pptx, slide-style .pdf, or lecture folder such as Lec01/ and asks for an organized Chinese study note, handout, review note, or topic-reorganized learning artifact. Trigger for casual requests like "整理课件", "做笔记", "整理成讲义", including one-lecture directories with multiple Part PDFs, question PDFs, labs, or code examples. Do not trigger for pure translation, books/papers, non-learning decks, bare files with no task, or conversational "explain this slide" questions without a written deliverable.
review:local
by IKatsuba
Local Code Review - analyzes code changes and provides structured feedback before commit
strategic-doctrine-deployment
by Andy160675
A workflow for deploying strategic documents (e.g., funding plans, architectural overviews) into a version-controlled repository, generating a presentation, and syncing all artifacts to GitHub and Google Drive. Use when a user provides a doctrinal document and asks for it to be processed, deployed, or presented.
哔哩哔哩字幕获取器
by jackspace
从哔哩哔哩(B站)搜索视频、获取字幕并转换为 Markdown 格式。当用户需要搜索 B 站视频、下载视频字幕、批量获取字幕、分析视频内容时使用。支持关键词搜索、单视频处理、批量并发下载。
paywall-upgrade-cro
by alexwelcing
Optimize paywalls and upgrade prompts for subscription conversion
xnatctl
by rickyltwong
Use when running xnatctl commands, writing scripts that call xnatctl, troubleshooting XNAT CLI operations, or helping users with XNAT neuroimaging server administration via the command line. Triggers on mentions of xnatctl, XNAT CLI, session download/upload, prearchive, scan management, or XNAT project administration.
project-planner
by petestewart
Generate a comprehensive PLAN.md file for a new project. Creates structured plans with tickets that an Orchestrator can execute.
coding-dispatch
by napyang
分解多步驟編程任務，透過 subagent 依序執行，支援 cron 斷點續傳。 主動用於多步驟實作任務（例如「實作功能 X 需要 A、B、C」、「重構模組 Y 並更新呼叫者」）。 適配 64k context 限制，最大化 subagent 委派以節省主 agent token。 狀態檔案統一存放於 ~/.hermes/dispatches/，支援 crash 後自動恢復。
bear-x-callback-url
by zetavg
Bear app x-callback-url scheme guidance for building callback URLs, understanding parameters, and using Bear actions (create, open, search, tags, selection, and related operations). Use when a user asks how to use Bear's x-callback-url scheme, when composing a Bear callback URL, or when building an integration that needs to drive Bear via x-callback-url.
slite
by Sytex
Interact with Slite knowledge base - search, read, create, and manage notes. Use when user wants to work with Slite documents.
competitive-intelligence
by coopergwrenn
Monitor competitors, track market trends, analyze sentiment, and deliver competitive briefings. Use when the user asks about competitors, competitive analysis, market research, industry trends, competitor pricing, or market monitoring.