macos-harness
Observe, act, and check a Mac through persistent model-neutral guarded Accessibility, with raw screenshots, PID-targeted input, Apple Events, browser CDP, and…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-18 00:15
54,096 results
Observe, act, and check a Mac through persistent model-neutral guarded Accessibility, with raw screenshots, PID-targeted input, Apple Events, browser CDP, and…
Inspect one git branch vs main: overview of commits, diff, merge/PR status, staleness; user picks delete/archive/PR/keep; emit action plan. Use for 'review…
Use when generating changesets in the kimi-code repository — deciding whether to write one, which package to list, the bump level, the wording, and the…
Use after a release succeeds, when maintainers need to sync apps/kimi-code/CHANGELOG.md into docs/en/release-notes/changelog.md and…
Write authentic UGC (user-generated content) ad scripts that sound like real people sharing real experiences. Produces talking points — not word-for-word…
Bulk-post anchored comments (with @-mentions) to a Google Doc from a JSON plan. Use when adding many Google Docs comments at once — checklist audits, doc…
Always-on operational guardrails, model-independent. Apply on EVERY task and EVERY model (Opus, Sonnet, Haiku, and any future tier) whether or not fable-mode's…
[user] Use when explicitly assigning an exploratory task of discovering new questions based on investigation results and continuously adjusting research milestones. Do not use for one-off comparative investigations with predetermined questions, for establishing milestones in an agreed direction, or for preparing a selected implementation.
[user/auto] Use this when you have moved between sessions and lost the context of the current task, or want to briefly confirm how far you have gotten, and then end the turn. Do not use it for explaining code behavior, investigating remote PR status, or writing handoff files.
Makes a UI pull request autonomously verifiable. `author` generates a step-by-step UI verification spec for the PR's visual change and injects it into the PR…
Triage MUI GitHub issues from a mui/<repo>/issues/<num> URL or issue number - fetch context, classify state/type labels, prepare a durable summary comment, and…
Use this skill whenever the user wants ADHD-friendly outputs, low-cognitive-load communication, action-first responses, or minimal friction execution. Triggers…
Shared patterns for Nango actions and syncs - working directory verification, inline schemas, parameter naming, type safety, and registration requirements.…
Make Feishu docs not plain — when creating or updating Feishu/Lark documents, enforce the use of visually friendly rich-text formats such as callouts, columns (grid), enhanced tables (lark-table), whiteboards, and charts, and eliminate plain-text stacking. Triggered when the user asks to write Feishu documents, organize documents, beautify documents, or output any Feishu/Lark document content. With the lark-doc skill…
Downloads Xiaoyuzhou podcasts, transcribes using FunASR, and generates raw, structured, and optimized text files. Invoke when user provides a Xiaoyuzhou…
Structurally extract concepts, definitions, tacit knowledge, important quotations, and teaching patterns from lecture transcripts to generate knowledge.json and knowledge-graph.json. Takes the course-bundle from course-ingest as input. "Concept extraction," "knowledge extraction," "concept…
Converts video courses and documents into a standard format (course-bundle), and orchestrates the entire pipeline from knowledge extraction to manual generation to skill creation. Supports UTAGE / YouTube / Udemy / Notion / local files, etc. After ingestion, prompts the user for the processing level (knowledge only /...
Automatically create manuals from UTAGE video courses. Use Chrome operations to understand the course structure and formulate a processing plan, download with ffmpeg, transcribe with Groq Whisper, extract screenshots with scene detection, generate a Markdown manual in a readable writing style, and even check the consistency between images and text—all in one batch.
Catalog all screenshots in the course-bundle. Perform image classification for each frame (slide/browser/diagram/talking head, etc.), OCR extraction of text content, and keyword assignment, generating visual-index.json and visual-catalog.json. "Image index" "Screenshot classification" "visual…
One or two sentences stating what this skill covers and when to use it. Keep under 500 characters.
A Socratic interview skill for thinking through technical ideas like apps, products, tools, and projects. Use this when the user says "think through [idea]",…
Perform post-task traceback, drift detection, and top-down recalibration to keep execution aligned with goals, requirements, architecture, milestones, and…
Caddy
chrony