Finishing a Development Branch
Finishes a development branch after tests pass—merge, PR, or cleanup with a clear integrate decision.
ai agent skills.
371 skills · 141–160
Finishes a development branch after tests pass—merge, PR, or cleanup with a clear integrate decision.
Pushes agents toward distinctive, intentional UI aesthetics instead of generic AI-looking layouts.
Enforces complete LLM code output by banning placeholders and truncated file generation.
Validates gcloud CLI operations and constructs commands with Google Cloud safety checks.
This skill creates image sets for a marketplace listing through the Higgsfield CLI. Bundles range from a single main image to a full set with five secondary shots and seven A+ style modules, and custom picks include infographics, detail shots, and what's in the box. Marketplace rules and prompt wording are handled on Higgsfield's side. You get back image URLs with short labels.
This skill makes product and brand images through the Higgsfield CLI, starting from a product photo you upload or a text description. Modes include clean studio shots, lifestyle scenes, a model wearing the item, and restyled or seasonal versions. It asks a few questions before generating and can return several variants and aspect ratios.
Addresses GitHub PR review comments systematically with gh—triage, reply, and fix loops.
Debugs failing GitHub Actions PR checks with `gh`, summarizes failures, and proposes fixes.
Adds Claude Code hooks that block dangerous Git commands before execution.
Scaffolds, enhances, and upgrades Google ADK agent projects through agents-cli.
Runs Google Analytics Data API reports with metrics, dimensions, and property queries.
Runs a relentless interview to sharpen a plan or design before you build.
Grills a plan or design while grounding questions in your existing docs and specs.
Relentlessly stress-tests a plan, decision, or idea with hard clarifying questions before you commit.
Lists, messages, creates, and manages xAI Grok Bot teammates from the CLI/agent without clicking the desktop UI.
OpenClaw-oriented investigate workflow from gstack—public SKILL.md for ClawHub/OpenClaw agent use.
OpenClaw port of gstack office-hours—structured decision unblocking with a public SKILL.md.
This skill handles HubSpot support tickets through the hubspot CLI. It creates a ticket linked to a contact or company, lists open or unassigned tickets by priority, moves batches of tickets between stages, logs a resolution note, and closes the ticket. It checks the portal's own pipeline and field values at the start of each session.
Compacts a conversation into a handoff document for another agent or coding session.
Raises UI to high-end agency craft—type, spacing, shadows, cards—and blocks generic AI defaults.
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.