Loading...
Loading...
Found 770 Skills
Two-layer autonomous conductor — design loop produces decision packets, dispatch loop routes to bounded issues with dedupe/cooldown/archive controls. Replaces v1's single-agent persistence with a durable control loop that stops only at real blockers.
Split Markdown documents into paragraph blocks with stable IDs and hashes, only replace blocks approved by the user, and output the retention ratio, modification reasons, and issue tracking report. Use when the user asks for "only modify these paragraphs", "partial modification according to review comments", "keep other content unchanged", "generate reviewable modification patch", or requests the rw-revision-patch workflow.
Write follow-up emails that re-engage without being annoying. Uses proven psychology for follow-up sequences. 42% of replies come from follow-ups.
Compose new Rails backend pages and refactor existing Rails UI to use premium blocks from templates/application-ui. Use when requests mention ERB views, Rails partials, admin/dashboard screens, Tailwind UI assembly, or replacing custom markup with existing premium blocks while preserving behavior, accessibility, and Turbo/Stimulus hooks.
This skill guides the agent in identifying and replacing AI model-specific cliches and formulaic expressions with more natural, human-like language, grounded in external search for better alternatives.
Resolve human PR review comments on current PR. Fetches unanswered human comments, evaluates each piece of feedback, applies fixes, and replies to every comment with the outcome.
Multi-agent coordination discipline: one-message-then-wait (send complete context, wait for reply before sending again), idle notifications are heartbeats (no action unless extended + blocking + user asked), no polling loops (event-driven only), never fabricate agent responses (wait for real system events), sequential agent spawning (acknowledge between each), and proper shutdown protocol (request, wait, respect rejection). Activate when orchestrating multiple agents, managing agent teams, coordinating handoffs between agents, spawning subagents, or building multi-agent workflows. Triggers on: "coordinate agents", "spawn multiple agents", "manage agent team", "agent keeps sending messages", "polling loop", "agent idle", "shut down agent", "multi-agent workflow", "agent handoff", "coordinate parallel work", "stop bothering the other agent". Also relevant when an agent is fabricating responses, sending follow-up messages before replies arrive, or reacting to idle notifications unnecessarily.
Discussion forum facilitator for Canvas LMS. Helps students and educators browse, read, reply to, and create discussion posts. Trigger phrases include "discussion posts", "reply to students", "check discussions", "forum participation", "post a discussion", or any discussion-related Canvas task.
MSVC cl.exe and clang-cl skill for Windows C/C++ projects. Use when configuring Visual Studio builds, MSBuild, or clang-cl as a drop-in MSVC replacement. Covers translating GCC/Clang flags to MSVC equivalents, runtime library selection, Windows SDK setup, and diagnosing MSVC-specific errors. Activates on queries about cl.exe, clang-cl, /O flags, /MT vs /MD, PDB files, Windows ABI, or MSVC project settings.
When the user wants to build or improve a sales bot's ability to reply fast enough to feel real-time but not unnaturally instant. Also use when the user mentions "response speed," "reply timing," "bot response delay," "natural pacing," or "message timing."
Community-powered growth for builders. Boost amplifies your social posts with authentic community engagement (replies, likes, reposts). Discover finds relevant conversations and generates AI-powered replies at scale. Use Boost when the user has a post URL. Use Discover when the user wants to find and engage in conversations about their product.
MiMo V2.5 TTS Text-to-Speech. Generate speech using Xiaomi MiMo V2.5 TTS series models. This skill is activated when text needs to be converted to speech, voice messages need to be sent, content needs to be read aloud, or when users request 'speak it out' or 'voice reply'. It supports three modes: preset voice, voice design, and voice cloning, as well as natural language control and director mode. It also supports style tag control for tone, emotion, and dialect, and preset voices support singing.