Prototype
Builds a throwaway prototype to answer a design or state-model question before implementation.
ai agent skills.
371 skills · 241–260
Builds a throwaway prototype to answer a design or state-model question before implementation.
This skill builds sales reports from HubSpot with the hubspot CLI. Reports include a daily briefing of deals closing this week, open pipeline broken out per stage and per owner, and closed-won against closed-lost for a period. Saved reports and known limits of the data are covered too.
Deploys Flask, Django, and FastAPI applications to Azure App Service on Linux.
This skill tests you on an article or book you finished lately in Readwise Reader, or on a document you name. Questions come singly, each answer is graded before the next, and you get a final score. Questions use your highlights and can be tailored with a persona file.
Applies Vercel Engineering’s React/Next.js performance rules (waterfalls, bundles, server/client fetching, rerenders).
Implements React View Transitions for smooth navigations and UI state changes.
This skill reads and edits Google Docs with gws, the Google Workspace CLI. A helper adds text to the end of a doc, and the raw API covers other document edits.
This skill reads from and writes to Google Sheets through the Google Workspace CLI (gws). Helpers read cell values and append rows, and the raw API covers other spreadsheet changes.
Processes code-review feedback thoughtfully before implementing changes—especially pushy or unclear notes.
This skill compares general ledger balances with subledgers, bank statements, or outside data. It handles bank, subledger, and intercompany reconciliations and sorts each difference as timing, an adjustment, or something to investigate. Aging and escalation guidance are included for items that stay open.
Audits and upgrades existing sites/apps to premium quality without breaking functionality.
Transforms monolithic Terraform into reusable modules using HashiCorp module design principles.
Routes Remotion video-in-React work to the right Remotion skill patterns and best practices.
Transcribes, displays, and animates captions inside Remotion compositions.
Scaffolds and authors new Remotion compositions and video projects in React.
Finds and applies Remotion documentation when building programmatic videos in React.
Adds interactive Remotion player behaviors—scrubbing, inputs, and dynamic props.
Renders Remotion videos with the right CLI, Lambda, or CI pipeline settings.
Previews Remotion videos in Studio using the recommended local workflow.
This skill cleans up recordings using the ElevenLabs Voice Isolator API, stripping noise, music, and ambience so the voice stays. It shows Python, JavaScript, and CLI usage, takes files or URLs, and lists supported formats. It is handy before transcription.
An agent skill is a portable pack of instructions that gives an agent specialized know-how for a task. In the open Agent Skills format (from Anthropic, now widely adopted), that pack is a folder with a SKILL.md file and optional scripts or references the agent can load when needed.
SKILL.md is the required main file in a skill folder. It starts with simple metadata (name and description) plus the instructions. Agents use the metadata to decide when a skill applies, then read the full file — and any linked files — only when the task needs them.
Open the listing and follow the source link — usually a GitHub SKILL.md. Install with your agent’s skill flow, or add the repo the way that product documents. When this site shows the skill text, Copy is on the page.
A prompt is paste-in text for one chat turn (or a short thread). A skill is a reusable file pack an agent can discover and load across a task, sometimes with code attached. Prompts live in the prompt directory; skills usually live on GitHub and we link out.
Each skill uses one sitewide category — the same set as the rest of the directory (Coding agent, Marketing, Document intelligence, and so on). Hops filter to categories that already have skills.
Yes. Submit with a public GitHub SKILL.md URL, or attach a skill as part of a method on a use case. An editor reviews it before it appears here.