Loading...
Loading...
Found 196 Skills
Write, rewrite, or edit user-facing text in the repo's preferred plain human style. Use for any prose task: docs, README sections, comments, release notes, PRDs, posts, emails, explanations, and requests to humanize or tighten text. Default to general prose rules; read references/documentation.md only for README, technical docs, usage guides, CLI/API docs, or documentation audits.
Command-line interface for Anygen - A stateful command-line interface for AnyGen OpenAPI — generate professional slides, documents, webs...
Command-line interface for ComfyUI - AI image generation workflow management via ComfyUI REST API. Designed for AI agents and power users who need to queue workflows, manage models, download generated images, and monitor the generation queue without a GUI.
Agent-native CLI for the s&box game engine (Facepunch Studios, Source 2): project management, scene/prefab editing, material/sound/localization configs, C# code generation, asset graph queries, project validation, and editor launch.
Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes `macro run <name>` and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).
Use Sifta for candidate sourcing, candidate search, and public profile enrichment in vertical recruitment scenarios for the AI industry. This skill is intended for users looking to find, screen, enrich, or evaluate AI engineers/developers, embodied intelligence talents, solopreneurs/independent developers, founders, AI product managers, GTM/GMT/global expansion/AI marketing talents, and research-focused paper talents. This skill is NOT applicable to general talent search outside these personas, company intelligence, sales leads, outreach, ATS, KOL collaborations, or general web research.
Observe one target or scan reachable Orca sessions for limits, overload, failures, questions, work, and completion. Use only when the user explicitly names Meta-O watchdog or mo-watchdog; nudge only an explicitly authorized exact target.
Run a whole feature from task or spec to one verified candidate SHA through Orca orchestration workers, with two independent reviews and applicable E2E.
Apply repository-grounded senior engineering judgment to substantial Python work and bounded Python changes with production or cross-boundary risk. Do not use for trivial syntax questions, generic tutoring, or tasks with no Python artifact unless explicitly invoked. Use for writing, review, diagnosis, design, refactoring, or maintenance where correctness, state, effects, concurrency, compatibility, security, reuse, testing, or long-term ownership materially matters.
Run the end-to-end scenarios that genuinely require an agent against one frozen full candidate SHA and report complete per-scenario evidence without editing the candidate.
Apply repository-grounded senior engineering judgment to substantial JavaScript or TypeScript work and bounded JS/TS changes with production or cross-boundary risk. Do not use for trivial syntax questions, generic tutoring, or tasks with no JS/TS artifact unless explicitly invoked. Use for Node, browser, frontend, worker, and edge work where correctness, contracts, state, effects, concurrency, compatibility, security, reuse, runtime alignment, or long-term ownership materially matters.
Produce a portable, read-only evidence report about whether to reuse, extend, or build. Run only for an explicit reuse-research request; do not trigger for ordinary package questions.