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 69 of 149

  • okfSkillFiles & storage

    Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source. Use when capturing knowledge into a bundle (a service, schema, metric, decision, runbook: "document this in OKF", "capture thi

    Ready to connect★ 156

    github.com/serradura/okf156 stars

    View details
  • okf-principlesSkillFiles & storage

    Restructure agent instruction artifacts (Claude Agent Skills, rules files, CLAUDE.md, playbooks) by applying five structural principles derived from the Open Knowledge Format - bounding the worst-case context a question loads (the mean may rise; the win is the tail and answer accuracy) and making cr

    Ready to connect★ 156

    github.com/serradura/okf156 stars

    View details
  • parallel-dispatchSkillFiles & storage

    MECE task decomposition, file ownership enforcement, DAG-based execution, and safe merge protocol for intra-domain parallel dispatch. The safety invariants that prevent merge chaos when multiple agents write in parallel. Applies recursively at every nesting depth.

    Ready to connect★ 156

    github.com/irahardianto/awesome-agv156 stars

    View details
  • qwen-asrSkillFiles & storage

    Transcribe audio files using Qwen ASR. Use when the user sends voice messages and wants them converted to text.

    Ready to connect★ 156

    github.com/aahl/skills156 stars

    View details
  • testability-patternsSkillFiles & storage

    Implementation examples for the three testability rules (I/O isolation, pure logic, dependency direction) across Go, TypeScript, Python, Rust, and Dart. Loaded by reference from architectural-pattern.md — not triggered by file patterns.

    Ready to connect★ 156

    github.com/irahardianto/awesome-agv156 stars

    View details
  • map-tokenreportSkillFiles & storage

    Show per-subtask/agent token accounting (input, output, cache read/creation, cost, cache-hit ratio) for the current branch. Supports --dashboard (box-drawing visual), --history (trends), --estimate (cost projection), --json / --csv export, and --finalize (record session snapshot). Use when asked for

    Ready to connect★ 155

    github.com/azalio/map-framework155 stars

    View details
  • recallloomSkillFiles & storage

    Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful progress across sessions. Works best for long-horizon, file-based projects and supports research writing, product document collab

    Ready to connect★ 155

    github.com/frappucc1no/recall-loom155 stars

    View details
  • workflowSkillFiles & storage

    Author and run a deterministic multi-agent workflow — a JavaScript script that fans out, pipelines, loops, and judges across many child agents. Use when the work decomposes into many similar units (review every changed file, research N topics, migrate M call sites), when it needs adversarial verific

    Ready to connect★ 155

    github.com/mweinbach/agent-coworker155 stars

    View details
  • experiment-forensicsSkillFiles & storage

    Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, ver

    Ready to connect★ 154

    github.com/wanshuiyin/anti-autoresearch154 stars

    View details
  • laravel:config-env-storageSkillFiles & storage

    Portable storage configuration across S3/R2/MinIO with optional CDN—env toggles, path-style endpoints, and URL generation

    Ready to connect★ 154

    github.com/jpcaparas/superpowers-laravel147 stars

    View details
  • laravel:constants-and-configurationSkillFiles & storage

    Replace hardcoded values with constants, enums, and configuration for maintainability; use PHP 8.1+ enums and config files

    Ready to connect★ 154

    github.com/jpcaparas/superpowers-laravel147 stars

    View details
  • laravel:effective-contextSkillFiles & storage

    Provide comprehensive context in prompts—files, errors, Laravel version, dependencies, and monorepo details—for accurate AI responses

    Ready to connect★ 154

    github.com/jpcaparas/superpowers-laravel147 stars

    View details
  • laravel:filesystem-uploadsSkillFiles & storage

    Store and serve files via Storage; set visibility, generate URLs, and handle streaming safely

    Ready to connect★ 154

    github.com/jpcaparas/superpowers-laravel147 stars

    View details
  • laravel:internationalization-and-translationSkillFiles & storage

    Build with i18n in mind from day one using Laravel translation helpers, JSON files, Blade integration, and locale management

    Ready to connect★ 154

    github.com/jpcaparas/superpowers-laravel147 stars

    View details
  • campaign-plannerSkillFiles & storage

    Generates a complete marketing campaign plan covering goal setting, audience analysis, core messaging, channel strategy, content calendar, and performance metrics. Suitable for scenarios such as product launches, customer acquisition, or brand awareness, and excels at weekly execution roadmaps. Trig

    Ready to connect★ 152

    github.com/rongxinzy/rongxinai118 stars

    View details
  • git-repo-auditSkillFiles & storage

    Performs deep analysis of Git repository history, identifies frequently changed hot-spot files, analyzes actual code contribution attribution, and scans historical commits for security issues such as leaked secrets. Triggers when the user mentions analyzing a repository, viewing code attribution, fi

    Ready to connect★ 152

    github.com/rongxinzy/rongxinai118 stars

    View details
  • hitl-approvalSkillFiles & storage

    Human-in-the-loop approval workflow for high-risk agent operations (file deletions, deployments, config changes).

    Ready to connect★ 152

    github.com/nwiizo/ccswarm149 stars

    View details
  • lark-docSkillFiles & storage

    Feishu cloud docs (Docx / Wiki documents): read and edit Feishu document content. Use when the user provides a document URL or token, or needs to view, create, or edit documents, or insert or download document images/attachments. For spreadsheets, Base (multidimensional tables), or boards embedded i

    Ready to connect★ 152

    github.com/rongxinzy/rongxinai118 stars

    View details
  • lark-markdownSkillFiles & storage

    Lark Markdown: view, create, upload, edit, and compare Markdown files. Use when the user needs to create or edit Markdown files, read, modify, apply a local patch, or compare diffs. Not responsible for importing Markdown into Lark online documents, nor for cloud-space management operations such as f

    Ready to connect★ 152

    github.com/rongxinzy/rongxinai118 stars

    View details
  • log-diagnosticSkillFiles & storage

    Analyzes error patterns in log files, supporting common formats such as JSON, syslog, and Nginx. Automatically detects and outputs error clustering, frequency statistics, and time distribution reports for troubleshooting and identifying peak periods. Triggered when a user uploads a .log file and ask

    Ready to connect★ 152

    github.com/rongxinzy/rongxinai118 stars

    View details
  • minimax-xlsxSkillFiles & storage

    Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new xlsx from scratch, re

    Ready to connect★ 152

    github.com/rongxinzy/rongxinai118 stars

    View details
  • regression-insightSkillFiles & storage

    Performs linear regression (OLS) or logistic regression on CSV/Excel data, outputting complete statistical results (including regression coefficients, R², p-values, VIF, etc.) and plain-language interpretation in Chinese. Triggers when the user mentions regression analysis, model fitting, coefficien

    Ready to connect★ 152

    github.com/rongxinzy/rongxinai118 stars

    View details
  • forgejoSkillFiles & storage

    Forgejo REST API toolkit — manage issues, pull requests, wikis, and repos on a Forgejo server. Use when the agent needs to file an issue, open / review / merge a PR, read or write a wiki page, or look up repo / branch info. One standalone script per resource type. Reads credentials from environment,

    Ready to connect★ 149

    github.com/tencent/skillhone151 stars

    View details
  • 3dsmax-scriptingSkillFiles & storage

    Automate 3ds Max with MAXScript and Python — scene manipulation, object creation, material assignment, camera setup, batch operations, UI tools, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, creating custom tools, or scripting scene setup for

    Ready to connect★ 150

    github.com/terminalskills/skills144 stars

    View details
  • after-effectsSkillFiles & storage

    Automate Adobe After Effects workflows. Use when a user asks to script After Effects with ExtendScript or CEP, batch render compositions, automate motion graphics templates (MOGRTs), build render pipelines with aerender, create expressions for animations, manage project files programmatically, autom

    Ready to connect★ 150

    github.com/terminalskills/skills144 stars

    View details
  • agent-sandboxSkillFiles & storage

    Run AI agent code safely in isolated sandboxes with resource limits, audit trails, and kill switches. Use when someone asks to "sandbox my agent", "run agent code safely", "add guardrails to AI agent", "isolate agent execution", "audit agent actions", "prevent agent from deleting files", "restrict a

    Ready to connect★ 150

    github.com/terminalskills/skills144 stars

    View details
  • aiderSkillFiles & storage

    You are an expert in Aider, the terminal-based AI coding assistant that reads your codebase, makes changes across multiple files, and creates proper git commits. You help developers use Aider for autonomous code generation, refactoring, bug fixing, and test writing — working with any LLM (Claude, GP

    Ready to connect★ 150

    github.com/terminalskills/skills144 stars

    View details
  • api-load-testerSkillFiles & storage

    Generates and executes load test scripts for APIs using k6, wrk, or autocannon. Creates realistic test scenarios from OpenAPI specs, route files, or endpoint descriptions. Use when someone needs to load test, stress test, benchmark, or find the breaking point of their API. Trigger words: load test,

    Ready to connect★ 150

    github.com/terminalskills/skills144 stars

    View details
  • archiverSkillFiles & storage

    Create ZIP and TAR archives programmatically with Archiver — bundle files, directories, and streams into compressed archives with progress tracking. Use when tasks involve generating downloadable bundles, backing up directories, creating deployment packages, or building export features that zip mult

    Ready to connect★ 150

    github.com/terminalskills/skills144 stars

    View details
  • audiowaveformSkillFiles & storage

    Generate waveform visualizations from audio files. Use when a user asks to create waveform images, build audio player visualizations, generate waveform data for web players, create podcast episode previews, build audio thumbnails, render waveform PNGs for social media, extract peak data as JSON, or

    Ready to connect★ 150

    github.com/terminalskills/skills144 stars

    View details

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.

See how to connect your AI