Turn a codebase into Mermaid diagrams such as architecture, ER, sequence, class, and flow diagrams. It analyzes relevant files, writes diagram source, renders SVG and PNG images, and checks the rendered result for readability and correctness.
Organize invoices and receipts by extracting dates, vendors, amounts, and descriptions from PDFs and images. Create consistent filenames, sort copies into folders, and produce a CSV summary for accounting, expense tracking, or tax preparation.
Create original posters and static artwork by first defining a visual direction for color, shape, space, and typography. Receive a Markdown design philosophy alongside a PNG or PDF artwork that communicates primarily through visuals.
Read, create, and review PDFs with checks of both content and appearance. Uses Python tools for document generation and text extraction, then inspects rendered page images for spacing, alignment, and readability.
Review and rewrite Twitter drafts using insights from its open-source recommendation algorithm. The skill examines audience fit, replies, sharing, and negative reactions, then explains suggested edits and ways to refine your content strategy.
Generate and edit images through the OpenAI Image API using a bundled command-line script. Create product shots, illustrations, and covers, replace backgrounds, remove objects, produce transparent images, or generate batches of variations.
Create animated GIFs for Slack messages and custom emoji from a description. Combine motion such as bouncing, spinning, and shaking, then check dimensions and file size and adjust frames or colors to fit the intended use.
Turn text into audio files for narration, product demos, phone prompts, or accessibility reads using the OpenAI Audio API. Choose built-in voices and delivery directions, then generate a single clip or a batch of files.
Create, edit, analyze, and format Excel, CSV, and TSV files using Python. Preserves existing spreadsheet styles and formulas, checks references, and supports summaries, charts, and readable layouts for new workbooks.
Read, create, and edit .docx documents with python-docx, then render pages for visual inspection. Organize headings, tables, and lists, and check spacing, alignment, pagination, and readability before delivering the finished document.
Search biomedical literature in PubMed using Boolean logic, MeSH subject terms, field filters, and publication criteria. The skill also guides programmatic retrieval through NCBI E-utilities, batch processing, citation matching, and exporting records for review or reference management.
Search the skills.sh ecosystem for agent skills that match a task, then help add a selected skill to Skill Compose. Results include the skill name, source, install count, and link, while the workflow separates discovery from installation.
Review or edit Chinese text to reduce patterns often associated with AI-generated writing. It identifies inflated claims, promotional wording, vague attribution, repetitive structures, and filler, then rewrites passages while preserving meaning and the intended tone.
Investigate an agent run by reviewing its execution trace, a record of steps and tool calls. Start with a run overview, then inspect relevant inputs, outputs, errors, and token use to explain what happened or diagnose a failure.
Get topic-specific guidance for creating videos with Remotion and React. The skill points to rules and code examples for compositions, animation, media assets, audio, captions, charts, transitions, and other common video tasks.
Turn a project description into a coordinated visual identity package. Define logo variants, color palettes, and typography, then create layouts for business cards and social media covers along with a brand specification document for consistent use.
Turn a user’s requirements and an available skills list into a workflow plan. It recommends existing skills, identifies missing capabilities that may need new skills, and drafts a system prompt for an agent that combines them.
Review text for patterns associated with AI-generated writing, including vocabulary, structure, formatting, citations, and model-specific artifacts. The skill combines multiple signals, weighs context and mitigating evidence, and presents a cautious assessment with confidence and caveats.
Revise an existing agent skill in response to feedback. The skill guides the agent to inspect the skill files, plan focused changes, update instructions or supporting scripts, and validate the result before packaging it.
Generate images from text prompts or edit them with Google Gemini. The skill also covers combining reference images and keeping a person’s appearance consistent across a set, with guidance for model choice, image ratios, and prompt details.
Use yt-dlp to save videos or audio from supported sites, including YouTube and social platforms. Choose a resolution, download subtitles or playlists, and set output filenames. Some private or restricted content may require browser cookies, and merging formats may require ffmpeg.
Use RDKit's Python tools to read and write molecular structures, calculate properties such as molecular weight and LogP, search substructures, compare fingerprints, model reactions, and generate 2D or 3D coordinates. It supports detailed, customizable cheminformatics workflows.
Organize complex, multi-step work with three Markdown files: a task plan, research findings, and a progress log. The workflow helps an agent retain decisions, record errors, track phases, and recover context when resuming a task after a session reset.
Extract audio from videos or download audio from supported websites with yt-dlp, then save it as MP3, M4A, FLAC, WAV, or OPUS. The workflow can embed track metadata and cover art, and process playlists or podcast episodes in batches.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)