372 skills · sorted by relevance
Create financial Excel workbooks with Python, using formulas, color-coded inputs, source comments, and consistency checks. Build models that reviewers can trace and users can adjust by changing assumptions.
Let an AI play Pokemon through an emulator, using screenshots and game memory to guide movement, dialogue, and battles. The skill covers browser viewing, progress tracking, and saving or resuming play with a user-provided ROM.
Create PowerPoint files from Excel financial models using Python. Build slides with figures linked to source cells, apply a firm template, and embed chart images for pitch decks, investment memos, or earnings presentations.
Build animated videos with HTML and CSS for appearance and GSAP for motion, then export MP4 or WebM files. Create captioned narration, product tours, animated titles, and website-based videos, with checks for contrast and layout.
Turn articles, papers, and notes into an interlinked Markdown knowledge base. Summarize sources, update topic pages, answer questions with references, preserve useful comparisons, and audit broken links, conflicting claims, and outdated content.
Display a text scoreboard of published Ponytail 5 benchmark results, comparing code volume, generated text tokens, cost, time, and check results against an agent without the skill. The figures describe benchmark averages, not savings in the current project.
View published benchmark results comparing ponytail with the same agent without the skill. A simple bar chart shows code volume, output tokens, cost, time, and quality checks, clearly separated from results for the current project.
Create logos, business card mockups, HTML presentations, banners, social images, and SVG icons. Define shared brand colors and typography, then carry those choices into visual assets and interface styling.
Automatically repair source code against a failing test while preserving the test itself. Set a spending limit and attempt count, then receive verification results and usage costs based on rerunning the test command.
Manage Contentful spaces, the containers used to organize content, from Claude Code through Composio. List accessible spaces, inspect creation dates and current versions, rename spaces, and review the organization's space inventory.
Benchmark how CodeGraph affects an agent investigating a real codebase. Choose a version, language, repository, and execution mode, then compare cost, tool calls, file reads, and answer correctness with and without CodeGraph.
Operate and test terminal apps without a display using named background sessions. Wait for visible screen changes, send keystrokes, reproduce Cline CLI bugs, capture text or PNG evidence, and write automated tests of interactive behavior.
Turn a website's screenshots and brand assets into a HyperFrames site tour or social clip. Develop a storyboard and script, add optional narration and captions, then validate the video and deliver a Studio preview.
Coordinate work between AI agents through MemPalace’s event log. Create tasks with clear goals and completion criteria, generate pasteable handoffs, track claims, and deliver patches for verification. Explicitly requested launches support Codex and Claude.
Create and edit FreeCAD models using commands for dimension-controlled sketches, solid parts, assemblies, and technical drawings. Check geometry through previews, measure models, and export files for CAD exchange, 3D printing, or documentation.
Test a product idea by writing its launch press release before building it, then answering customer and internal questions. Research informs a complete PRFAQ, a press release with frequently asked questions, plus a product requirements summary.
Analyze 2D fluorescence microscopy images to detect nuclei and measure their counts, intensity, and area. Run repeatable CellProfiler batches, inspect nucleus outlines, and review measurement tables with recorded pipeline settings and quality checks.
Delegates repository analysis or coding tasks to MiniMax Code without opening its interactive interface. It runs one task in the specified project with a time limit, then uses the final response as the result.
Delegate repository analysis and coding tasks to Antigravity CLI without an interactive session. The skill checks structured results and errors, and supports comparing its work with results from another coding agent.
Delegate repository analysis or coding tasks to Qwen Code without opening its interactive interface. Run within a specified project and time limit, then check the JSON response and exit status before summarizing the result.
Delegate repository analysis and coding tasks to Gemini CLI without an interactive session. The skill reads its structured results, summarizes responses and errors, and supports comparing Gemini’s work with another coding agent.
Resume pending deliberation saved by unattended acc runs. The skill guides the agent through reading each queued item and its context, submitting a proposal, and reporting resolution identifiers and supporting references until the queue is cleared.
Automate website navigation, form filling, content collection, and Windows desktop interactions. The skill selects browser or desktop tools for the task and guides screenshot capture and desktop network traffic observation when needed.
Generate an Excel workbook file in an agent session without an open Office app. Use Python and openpyxl to organize inputs, formulas, and checks, then save the .xlsx file and return its relative path.