Loading...
Loading...
Found 977 Skills
Analyze a task specification, review the codebase, and output a detailed assessment and success criteria. Use when user provides a new ticket or description to understand scope, risks, and definition of done before implementation.
Generate images from text prompts using Google Nano Banana (Gemini image generation) via eng0 data API. Use when user asks to generate, create, or make images, pictures, illustrations, or artwork from descriptions. Triggers include "generate image", "create image", "make a picture", "draw", "illustrate", "image of", "picture of", "nano banana". Do NOT use for image editing or manipulation of existing images.
Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding SEO metadata, fixing social share previews, reviewing Open Graph tags, setting up canonical URLs, or shipping new pages that need correct meta tags.
Create, refactor, shorten, or debug skills, descriptions, and reference loading. Use writing-agents-md for AGENTS.md/CLAUDE.md; excludes general documentation and READMEs.
Create or update a GitHub pull request with a standardized template. Use when the user wants to open a PR, create a pull request, update a PR description, submit changes, or push a PR.
Use when drafting, saving, formatting, validating, or repairing LinkedIn profile and content assets in this repository, including headlines, About sections, Experience descriptions, project copy, posts, articles, and LinkedIn image specs.
AI image generation and editing (Doubaoya) — one sentence for an image: text-to-image, image-to-image, editing, key visual, or a standalone illustration. Give a description and get an image; give a reference image (local files work too) and edit based on it. **Slow operation**: usually wait 1–2 minutes, up to 4 minutes. Don't interrupt or retry while waiting (retrying means paying twice for the same image). After generation, save locally and give you the path. Trigger phrases: draw a picture, help me draw, generate an image, generate a picture, AI generate image, output image, text-to-image, image-to-image, edit image, edit this image, Photoshop it, illustration, match an image, add an illustration, make a key visual, make a visual, draw according to this description, cover, cover image, WeChat cover, make a cover, match a cover image, first image inspiration. Not for: only cover **templates and reference data** (without an output image) go to dby-api; laying images into an article draft goes to dby-publish.
Communication and collaboration preferences covering how to write for the user, explain technical detail precisely, surface assumptions, handle unknowns, and make verification claims. Use when drafting or editing any user-facing prose — replies, progress updates, explanations, PR and ticket descriptions, commit messages, documents — and when deciding how much depth an answer needs, whether to ask or assume, or what a passing check actually proves.
[Pre-Publication Risk Check] Pre-publication risk screening. It goes through each sentence of a piece of copy, spoken script, title, subtitle, comment, account profile, or visual description you're about to publish, and separately answers two things: what the platform's automated review might flag, and whether the content itself has substantive problems; each finding includes the exact location and the minimal modification action — no full-text rewriting, no teaching how to evade review. Use when the user says "can I post this", "help me check for risks", "will I get throttled", "are there prohibited words", "check before publishing", "is this sentence problematic". WeChat Moments/WeChat ecosystem throttling and ban issues are not its domain — those go to xy-private-ops. | Made by 小爷
Manage Google Security Operations (SecOps) SOAR cases throughout their lifecycle. Use when listing, creating, inspecting, updating, or closing SOAR cases; adding investigative comments and notes; updating case priority or description; or linking and grouping security alerts within cases. Supports both remote Google SecOps MCP tools and local fallback tools. Don't use for SIEM UDM searches or detection rule authoring.
Write clear technical prose for anything that lives in a repository or on a forge: commit messages, PR titles and descriptions, PR and code review comments, issue text, READMEs, documentation, CONTRIBUTING.md, SECURITY.md, CODE_OF_CONDUCT.md, changelogs, ADRs. Use it when someone says commit this, open a PR, reply to a review comment, or file an issue. Use this whenever you are about to write or edit any of them, including short ones. A one-line commit message or a two-sentence review comment looks too small to need a skill, and that is exactly where the tells show up. Not for prose that needs a personal voice, such as blog posts, essays, or launch announcements.
Turns a plain-English description of a recurring report into a real, repeatable report — defines the metrics, pulls them from whatever data sources are connected, delivers a chat summary plus an XLSX workbook, and saves the definition so the same report reruns on demand or on a schedule. Handles anything from "sales by location versus last year" to AR aging to labor as a percentage of revenue. Works fully from an uploaded CSV or XLSX when no connector is available. Use this whenever the owner asks for a report, dashboard, KPI pack, metrics summary, or recurring numbers — including phrasings like "can you track this every week," "I need to see these numbers monthly," "build me a report on," "same report as last time," or "put together a KPI dashboard." Reach for it even when the owner names the metrics without using the word report.