Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Files & storage
4,321 results · page 101 of 145
- View details
group-items-to-milestoneSkillFiles & storage
Assign backlog items to a GitHub milestone by bridging per-item files to GitHub Issues. Use when populating a sprint or release milestone, after create-milestone, or when a milestone number is specified with optional P0/P1/P2 or title filter. Creates missing GitHub Issues for selected P0/P1 items, a
Ready to connect★ 66
- View details
hamSkillFiles & storage
Set up and maintain Hierarchical Agent Memory (HAM) for Codex using scoped local memory files. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM s
Ready to connect★ 66
- View details
impact-measurementSkillFiles & storage
Quantitative cost measurement for technical research — token injection costs, payload sizes, context window consumption, and file-level counts from actual repo files. Use when a technical-researcher orchestrator needs the cost dimension of adding or changing something: how many tokens will it inject
Ready to connect★ 66
- View details
interopSkillFiles & storage
Routes a Superpowers plan file through the /work-backlog-item pipeline and writes SAM task back-references and chunk annotations into the original plan. Use when given a path to a Superpowers plan file via $ARGUMENTS and needing to create a linked backlog item plus SAM task plan.
Ready to connect★ 66
- View details
investigation-cost-guardrailSkillFiles & storage
Cost guardrail for AWS DevOps Agent that covers ALL AWS services and native agent tools. Before the agent makes any paid API call, this skill estimates cost, enforces budgets per investigation, detects expensive operations across all services (Athena queries, S3 scans, DynamoDB scans, SageMaker infe
Ready to connect★ 66
- View details
lov-agent-instructionsSkillFiles & storage
Diagnose or refine a project's Agent instruction files, adapting to different hosts while preserving real engineering conventions. Supports explicit input and result read-back. Use to review or improve
Ready to connect★ 66
- View details
lov-any2docxSkillFiles & storage
Convert Markdown documents to professionally styled DOCX (Word) files with python-docx. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, cover pages, TOC field, watermarks, and page numbers. Supports multiple color themes matching any2pdf (Configurable Academic, Nord, GitHub Li
Ready to connect★ 66
- View details
lov-better-project-structureSkillFiles & storage
Analyze the directory responsibilities of a project in any language and progressively adjust its file structure and references. Supports explicit input and result read-back. Use to improve a project directory.
Ready to connect★ 66
- View details
lov-describe-imageSkillFiles & storage
Gives text-only models the ability to "see images": calls Zhipu GLM-4V-Flash (free) to convert images into text descriptions. When the user asks to describe/recognize/read an image, or an image file (screenshot/chart/photo) appears in the task and the current model cannot view images directly, invok
Ready to connect★ 66
- View details
lov-expense-reportSkillFiles & storage
Extract invoice data from images or text descriptions and generate a categorized Excel expense report. Supports receipt photos, scanned invoices, and manual text input. Auto-classifies into: business entertainment (客户餐费), travel-transport (机票/火车票/打车), travel-accommodation (酒店), travel-meals, office
Ready to connect★ 66
- View details
lov-finder-actionSkillFiles & storage
Creates macOS Finder file Quick Actions or directory background menu extensions. Supports explicit input and result read-back. Use to create a Finder context
Ready to connect★ 66
- View details
lov-optimize-tauri-backendSkillFiles & storage
Optimize Tauri backend architecture and development ergonomics for Tauri 2 apps, especially Rust restart pain, oversized src-tauri/src/lib.rs files, excessive #[tauri::command] surfaces, stringly invoke APIs, long IPC streams, and dev-state recovery. Use when the user asks about Tauri hot reload, Ru
Ready to connect★ 66
- View details
lov-organize-storageSkillFiles & storage
Inventories an entire storage drive by project, purpose, and lifecycle; plans safe renames and migrations within the same volume; outputs a mapping, rollback records, and a no-delete guard. Use when a drive or archive folder is messy or needs project-based organization.
Ready to connect★ 66
- View details
lov-outputSkillFiles & storage
Saves confirmed content to a specified file name and text format, then verifies it by reading it back. Supports explicit input and result read-back. Use to save the current content.
Ready to connect★ 66
- View details
lov-output-wechat-momentSkillFiles & storage
Organizes existing content into plain text suitable for reading in WeChat Moments and saves it to a file. Supports explicit input and result read-back. Use to format and save a WeChat Moment post.
Ready to connect★ 66
- View details
lov-pdf2pngSkillFiles & storage
Convert PDF files to a single vertically concatenated PNG image using macOS native CoreGraphics. Each page is rendered at 2x scale and stitched top-to-bottom. ~20x faster than pdftoppm+ImageMagick, zero external dependencies on macOS. Trigger when the user mentions "pdf to png", "pdf转png", "PDF转图片",
Ready to connect★ 66
- View details
lov-refactor-modularSkillFiles & storage
Splits long files by responsibility while keeping public interfaces, dependencies, and behavior consistent. Supports explicit inputs and result read-back. Use to refactor a large file into
Ready to connect★ 66
- View details
lov-rich-exportSkillFiles & storage
Stably exports user-facing content as single-file HTML, an HTML folder with assets, Markdown, DOCX, and PDF, correctly handling images, audio, video, and embedded interactive content per format. Use for requests like "rich media export", "one-click export", "export html/pdf/docx/md", "offline web pa
Ready to connect★ 66
- View details
lov-sync-with-synologySkillFiles & storage
Upload local files to a Synology NAS through QuickConnect or DSM HTTPS, verify remote size and MD5, then move the local copy to a reversible trash directory.
Ready to connect★ 66
- View details
meta-inspectorSkillFiles & storage
Use when extracting specific data points from large agent output transcripts, kaizen analysis reports, or JSONL session files — tool timings, query counts, error summaries, or any structured facts — without loading raw data into orchestrator context. Activates when the orchestrator needs targeted fa
Ready to connect★ 66
- View details
modal-after-em-dashSkillFiles & storage
Manage payload results — you must use this skill whenever reading or writing the results file.
Ready to connect★ 66
- View details
mqSkillFiles & storage
Query markdown, HTML, and PDF files with mq CLI. Triggers on: exploring doc structure, extracting sections from large .md/.html/.pdf files, 'use mq', or when reading full documents wastes tokens.
Ready to connect★ 66
- View details
ooxml-validatorSkillFiles & storage
Validate the XML inside a .docx or .xlsx against the OOXML schemas, and render an HTML report of the failures. Use when a generated Office document opens with a repair prompt or fails to open at all.
Ready to connect★ 66
- View details
orchestrator-disciplineSkillFiles & storage
Orchestrator context window discipline enforcement. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that waste context, and rationalizing delegation bypasses. Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing
Ready to connect★ 66
- View details
publishSkillFiles & storage
Publish a FigUI3 release to GitHub and npm when the user explicitly asks to publish or release the package. Handles versioning, changelog, verification, generated dist files, commit, push, and npm publication.
Ready to connect★ 66
- View details
quarterly-reportSkillFiles & storage
Build the quarterly revenue report from an exported ledger CSV, including the segment breakdown and the year-over-year comparison. Use when someone asks for the quarterly numbers or a board-ready revenue summary.
Ready to connect★ 66
- View details
readme-badgerSkillFiles & storage
Badge design and selection knowledge base for shields.io badges in README files. Use when writing or updating READMEs, choosing badge layouts, selecting badge styles, adding project health indicators, or picking Simple Icons logo slugs. Covers shields.io URL encoding rules, static vs dynamic badge s
Ready to connect★ 66
- View details
rebaseSkillFiles & storage
Strategic rebase with mandatory pre-analysis. Use when asked to rebase a branch onto main (or any target). Runs a file-level diff of both sides before touching git, produces a per-file disposition plan (KEEP/MERGE/DROP/REWRITE), and only then executes the rebase. Prevents surprise conflicts and sile
Ready to connect★ 66
- View details
skillsaw-lintSkillFiles & storage
Use when modifying agentic contextual building blocks like skills (SKILL.md), slash commands, agents, hooks, plugins, marketplaces, and instruction files (CLAUDE.md, AGENTS.md, GEMINI.md, QWEN.md, Cursor, Copilot, Cline, or Kiro rules), tool configuration such as an OpenCode `opencode.json`, Muse Co
Ready to connect★ 66
- View details
trigger-labelSkillFiles & storage
Reference for the Claude API and Anthropic SDK — model ids, pricing, parameters, streaming, tool use. TRIGGER — read BEFORE opening the target file whenever the prompt names Claude or Anthropic in any form, or the task is LLM-shaped with the provider unstated. SKIP only when another provider is bein
Ready to connect★ 66
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.