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: Media
5,297 results · page 62 of 177
- View details
blockrun-debugSkillMedia
Use when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list, HTTP 402 / Insufficient balance, fetch failed, video or music timeouts, a 501 'not served' error or 'API error after payment' while the balanc
Ready to connect★ 395
- View details
image-promptingSkillMedia
Use when generating or editing images via `blockrun_image` — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured, text-accurate prompts
Ready to connect★ 395
- View details
xiaobei-skill-rebuild-image-in-powerpointSkillMedia
Use when a user wants Codex to directly operate PowerPoint and reconstruct an entire reference image as editable PowerPoint objects while preserving its full layout, labels, connectors, and visual relationships. Do not use for paper-to-deck generation or VBA-only output.
Ready to connect★ 380
- View details
happyhorse-prompterSkillMedia
Generates compact prompts (30-55 words) following HappyHorse 1.0 strict rules: subject-first + explicit camera techniques + audio activation path (with X audible / speaking English at natural pace). Optionally includes the "8s timing beats" structure. Use for trigger scenarios like "generate a video
Ready to connect★ 394
- View details
kling-prompterSkillMedia
Generates video prompts that follow Kling 3.0 (Kuaishou) rules. Three adaptive styles: a 4-part basic formula (short videos), a 5-layer advanced formula (storyline + audio), and a dedicated image-to-video style (motion-only descriptions). Kling is a cinematic-grade model with the strongest Chinese-l
Ready to connect★ 394
- View details
prompt-translatorSkillMedia
Converts an AI video prompt from a source model's style (e.g., Sora 2) into the best-practice style for a target model (e.g., Kling 3.0 / Wan 2.7 / Veo 3.1, etc.). Based on a benchmark of 110 entries covering 10 scenarios × 11 models (prompts/data/cross-model-matrix.), it works via table-lookup in-c
Ready to connect★ 394
- View details
seedance-debuggerSkillMedia
Diagnoses common issues when generating videos with Seedance 2.0 (12 categories including character ID drift/twins/subtitles/Logo/style drift/extension jumps/quality degradation/wrong effects/Chinese pronunciation/inaccurate voice tone/ending noise), identifies root causes, and provides fixed prompt
Ready to connect★ 394
- View details
seedance-prompterSkillMedia
Converts the user's natural-language video requirements into prompts following the Doubao Seedance 2.0 advanced formula (8 elements: precise subject + action details + scene environment + lighting and color tone + camera movement + visual style + image quality + constraints). Used for trigger scenar
Ready to connect★ 394
- View details
seedance-storyboardSkillMedia
Breaks down complex plots or story outlines into Seedance 2.0's multi-shot structure of "Shot 1 / Shot 2 / Shot 3". Each shot is organized along 4 dimensions (camera movement + subject actions and expressions + position/spatial changes + audio). Use for triggers like "help me turn this story into Se
Ready to connect★ 394
- View details
interview-transcriptionSkillMedia
Transcription, recording management, and quote extraction. Use when processing audio/video or generating timestamped transcripts.
Ready to connect★ 393
- View details
photo-metadataSkillMedia
Embeds photo IPTC/EXIF/XMP metadata, caption, credit, alt text, license, AI-source label, GPS stripping, and C2PA credentials.
Ready to connect★ 393
- View details
video-dashboardSkillMedia
Aggregates transcript and frame data into an interactive web dashboard. Use for content, topic, or sentiment analysis.
Ready to connect★ 393
- View details
video-transcribeSkillMedia
Batch Whisper transcription of video or audio (WAV, podcasts) with a re-runnable provenance record. Use to transcribe recordings.
Ready to connect★ 393
- View details
alanine_scanning_pipelineSkillMedia
Alanine Scanning Mutagenesis Pipeline - Alanine scanning: design scan, compute properties for each mutant, predict interactions, and compare. Use this skill for protein biochemistry tasks involving AlanineScanningDesigner ComputeProtPara PredictDrugTargetInteraction calculate protein sequence proper
Ready to connect★ 392
- View details
cancer_therapy_designSkillMedia
Cancer Therapy Design - Design cancer therapy: identify targets, find drugs, check safety, and analyze differential expression. Use this skill for oncology tasks involving get associated targets by disease efoId get associated drugs by target name get adverse reactions by drug name tcga differential
Ready to connect★ 392
- View details
combinatorial_chemistrySkillMedia
Combinatorial Chemistry Library Design - Design combinatorial library: validate core SMILES, generate variants, compute properties, and predict ADMET for library. Use this skill for combinatorial chemistry tasks involving is valid smiles calculate mol basic info calculate mol drug chemistry pred mol
Ready to connect★ 392
- View details
enzyme_inhibitor_designSkillMedia
Enzyme Inhibitor Design - Design enzyme inhibitor: target structure, pocket prediction, compound screening, and ADMET assessment. Use this skill for enzyme pharmacology tasks involving retrieve protein data by pdbcode pred pocket prank quick molecule docking pred molecule admet calculate mol drug ch
Ready to connect★ 392
- View details
polymer_property_analysisSkillMedia
Polymer & Material Property Analysis - Analyze polymer properties: composition, symmetry, density, and lattice parameters for material design. Use this skill for polymer science tasks involving MaterialCompositionAnalyzer CalculateSymmetry CalculateDensity MofLattice. Combines 4 tools from 2 SCP ser
Ready to connect★ 392
- View details
openspecSkillMedia
Spec-driven development (SDD). Use when implementing any feature or change—agree on the spec before writing code: write a proposal, spec deltas, and tasks in openspec/changes/<id>/ (plus design for complex cases); once aligned, implement strictly per the spec, then archive the deltas into the baseli
Ready to connect★ 389
- View details
game-concept-architectSkillMedia
Expands a one-sentence game idea into a verifiable game design blueprint: from concept seed, player verbs, design nucleus options, action-goal alignment, assumption ledger, player promises, core loop, scope gate, to validation plan. Works for real projects, private projects, client projects, public
Ready to connect★ 387
- View details
game-experience-analyzerSkillMedia
Analyzes game screenshots, local recordings, PVs, user-acquisition creatives, store pages, or video links into an evidence-chain diagnostic report in Chinese, including sample scope gate, evidence index, breakdown diagnostic package, mode routing, category-sensitive recommendations, validation plan,
Ready to connect★ 387
- View details
ai-news-researchSkillMedia
All my YouTube tutorials. Everything here is free - but please follow me on YouTube if you find these helpful.
Ready to connect★ 385
- View details
linkedin-postSkillMedia
All my YouTube tutorials. Everything here is free - but please follow me on YouTube if you find these helpful.
Ready to connect★ 385
- View details
youtube-descriptionSkillMedia
All my YouTube tutorials. Everything here is free - but please follow me on YouTube if you find these helpful.
Ready to connect★ 385
- View details
automation-workflowsSkillMedia
Design and implement automation workflows to save time and scale operations as a solopreneur. Use when identifying repetitive tasks to automate, building workflows across tools, setting up triggers and actions, or optimizing existing automations. Covers automation opportunity identification, workflo
Ready to connect★ 383
- View details
fal-upscaleSkillMedia
Lets your agent upscale and enhance the resolution of images and videos with AI models.
Ready to connect★ 383
- View details
living-ui-modifySkillMedia
Modify an existing Living UI application (PocketBase + React kit) — add features, change design, fix bugs — then re-validate and relaunch it.
Ready to connect★ 383
- View details
prompt-engineering-expertSkillMedia
Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents
Ready to connect★ 383
- View details
remotion-video-toolkitSkillMedia
Complete toolkit for programmatic video creation with Remotion + React. Covers animations, timing, rendering (CLI/Node.js/Lambda/Cloud Run), captions, 3D, charts, text effects, transitions, and media handling. Use when writing Remotion code, building video generation pipelines, or creating data-driv
Ready to connect★ 383
- View details
refactorSkillMedia
Refactors code following Ousterhout's design principles. Analyzes complexity, creates prioritized refactoring plan, and executes with safety-first approach. Optimized for Vite/React, Tauri/Rust, Zustand stack.
Ready to connect★ 381
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.