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
4,446 results · page 98 of 149
- View details
cursorSkillFiles & storage
Control Cursor AI code editor via CLI. Use when opening files, comparing diffs, managing extensions, or configuring Cursor as git editor.
Ready to connect★ 73
- View details
data-cleaning-standardsSkillFiles & storage
Clean and standardize vehicle insurance CSV/Excel data. Use when handling missing values, fixing data formats, removing duplicates, or standardizing fields. Mentions "clean data", "handle nulls", "standardize", "duplicates", or "normalize".
Ready to connect★ 73
- View details
data-privacy-agreementSkillFiles & storage
Draft and fill data privacy agreement templates — DPA, data processing agreement, GDPR, HIPAA BAA, business associate agreement, AI addendum. Produces signable DOCX files from Common Paper standard forms. Use when user says "DPA," "data processing agreement," "HIPAA BAA," "business associate agreeme
Ready to connect★ 73
- View details
giilSkillFiles & storage
Download full-resolution images from iCloud, Dropbox, Google Photos share links. Use when extracting images from cloud share URLs, remote debugging with screenshots, or downloading shared photo albums.
Ready to connect★ 73
- View details
investigation-add-zhou210712SkillFiles & storage
Add data to an ongoing investigation—files, interview transcripts, or observations. Process in batches against documented filtering criteria, surface what matters, and log everything reviewed for coverage verification. Use when new evidence, interview transcripts, or documentary material enters an o
Ready to connect★ 73
- View details
legal-hold-zhou210712SkillFiles & storage
Issue, update, release, or report legal hold notices — draft hold notices as .docx files, update hold fields in the case log, and schedule the next update. Use when the user says "发出证据保全通知", "更新保全通知", "解除保全", or requests a portfolio-wide legal hold status report.
Ready to connect★ 73
- View details
lex-diegosouzapwSkillFiles & storage
LEX: Legal-Entity-X-ref workflow skill. Use this skill when the user needs Centralized ''Truth Engine'' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing
Ready to connect★ 73
- View details
lex-v2SkillFiles & storage
LEX: Legal-Entity-X-ref workflow skill. Use this skill when the user needs Centralized ''Truth Engine'' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing
Ready to connect★ 73
- View details
magic-phoneSkillFiles & storage
Generate a 'wizarding-world-style phone interface' for any Harry Potter character — including chat history, social feed posts, and parchment notes. Data and UI are separated, so you can create new characters simply by writing a JSON data file.
Ready to connect★ 73
- View details
orchestrateSkillFiles & storage
Orchestrate multi-task execution plans using Claude's native Agent tool (DAG-based, no external engine). Use when: executing a plan.json file with parallel/sequential task dependencies. Not for: producing the plan in the first place — use /plan; single tasks with no dependencies between them. Keywor
Ready to connect★ 73
- View details
project-structure-guideSkillFiles & storage
Guide for organizing project directories following language-specific best practices. Use when: creating projects, reorganizing structure, adding modules, setting up builds, deciding file placement. Not for: structuring specifically for AI navigation — use /ai-friendly-architecture; restructuring exi
Ready to connect★ 73
- View details
spherse-use-ui-sdkSkillFiles & storage
Use the injected window.spherse SDK to call App capabilities within Spherse's HTML content (create a session and get the session ID, silently send messages in the background, open an existing session, open files, send messages to a session, read/write data, enumerate data, list directories, get file
Ready to connect★ 73
- View details
update-abilities-overrideSkillFiles & storage
When Dota patches release, maintain game/scripts/npc/npc_abilities_override.txt using the official ability KV files in docs/reference as the skeleton: write only diffs; the engine merges missing keys. Process each ability by priority: P1 remove same-value entries → P2 diffs and MaxLevel extension →
Ready to connect★ 73
- View details
create-demo-modelSkillFiles & storage
Create a Diff Studio demo model TS file and register it in the package, using equations from an IVP file. Use this skill when the user wants to create a demo model from an IVP file, mentions "demo model", "IVP file", "Diff Studio demo", or asks to convert an .ivp file into a demo.
Ready to connect★ 72
- View details
create-demo-model-from-ivp-fileSkillFiles & storage
Create a Diff Studio demo model TS file and register it in the package, using equations from an IVP file
Ready to connect★ 72
- View details
datagrok-entitiesSkillFiles & storage
Call datagrok_show_entities after any MCP tool result that returns entity data (files, scripts, queries, connections, projects, spaces, groups, users). Always use the tool — never list entities as plain text, markdown links, or bullet lists.
Ready to connect★ 72
- View details
dotnet-backend-patternsSkillFiles & storage
Provides .NET and ASP.NET Core patterns for REST APIs, Entity Framework, dependency injection, and middleware. Use when working with C# files (*.cs, *.csproj) or when the user mentions .NET, ASP.NET Core, C#, or Entity Framework.
Ready to connect★ 72
- View details
gemini-integrationSkillFiles & storage
Use Gemini CLI for long-context codebase exploration, architecture review, refactor impact analysis, documentation synthesis, or structured data analysis when the host should hand off a large cross-file problem instead of solving it file-by-file.
Ready to connect★ 72
- View details
lint-pipelineSkillFiles & storage
Use when changing how ryl takes input or writes files back — the `check` subcommand and its flags, directory walking, input de-duplication, source kinds, stdin, inline directives, Markdown embedding, or `--fix`/`--diff`. Records the invariants each stage holds and why, so a change does not quietly b
Ready to connect★ 72
- View details
markdown-injection-scannerSkillFiles & storage
Scans Markdown (.md) files for malicious code injection including XSS, prompt injection, script injection, obfuscated payloads, and supply chain attack vectors. Use when auditing .md files for security threats or when the user mentions scanning markdown for malicious content.
Ready to connect★ 72
- View details
output-formatsSkillFiles & storage
Use when changing `--format`/`--output-file`, the `[output]` TOML table, or the JUnit/GitLab report writers. Covers the repeatable-target model, the CLI > config > default precedence, every exit-2 guard on conflicting destinations, and the GitLab fingerprint contract.
Ready to connect★ 72
- View details
sandbox-guardSkillFiles & storage
Generate Docker sandbox configurations for safely running untrusted OpenClaw skills. Isolates filesystem, network,
Ready to connect★ 72
- View details
skill-guardSkillFiles & storage
Runtime security monitor for active OpenClaw skills. Watches file access, network calls, and shell commands.
Ready to connect★ 72
- View details
back-of-the-envelopeSkillFiles & storage
This skill should be used when the user needs to "estimate QPS", "back-of-the-envelope" (BOTEC) numbers, "how much storage / bandwidth", "how many servers", "peak load", "capacity planning", or wants the standard latency / throughput / availability numbers to ground a design (latency table, QPS rate
Ready to connect★ 71
- View details
blob-storeSkillFiles & storage
This skill should be used when the user wants a "blob store" or "object storage", names "S3" or an S3-compatible store, needs to "store images / video / files", asks about "multipart upload" or "resumable upload", "signed / presigned URLs", "media storage", "unstructured data at scale", object "vers
Ready to connect★ 71
- View details
cloud-securitySkillFiles & storage
Cloud security covers security assessment for major cloud platforms including AWS, Azure, and GCP, with core focus on IAM misconfiguration detection, storage bucket exposure scanning, metadata service attacks, container escape, and Kubernetes RBAC auditing.
Ready to connect★ 71
- View details
data-loss-prevention-bypassSkillFiles & storage
DLP bypass techniques covering steganography (LSB, audio, video), DNS tunneling, ICMP tunneling, cloud sync abuse (Dropbox, OneDrive), WebSocket/HTTP3 exfil, AI-augmented exfil (semantic chunking), and modern DLP evasion patterns.
Ready to connect★ 71
- View details
digital-forensicsSkillFiles & storage
Lets your agent investigate cyber incidents by analyzing memory dumps, disk timelines, network captures, and preserving evidence.
Ready to connect★ 71
- View details
draft-wireframeSkillFiles & storage
Wireframe a screen — text/ASCII by default, or hand-drawn HTML when the user says "sketch", "hand-drawn", "lo-fi HTML", "whiteboard", "graph paper", or "visual wireframe". Text mode produces a buildable ASCII spec Form and Prism can act on. HTML mode produces a single self-contained file with graph-
Ready to connect★ 71
- View details
file-inclusionSkillFiles & storage
Local File Inclusion (LFI) and Remote File Inclusion (RFI) attack techniques covering path traversal, PHP wrapper abuse, log poisoning, session file inclusion, and remote payload hosting for code execution.
Ready to connect★ 71
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.
54,764 of the 55,196 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.