Skill rating

Write AI-citable content in proven formats including FAQ pages, definition articles ("What is X?"), comparison guides (A vs B), how-to guides, and original data/statistics roundups. Creates content op

Use when your agent needs to build, maintain, or run the local `audiobook` skill for voice-library management, Step official voice sync, clone voice analysis, LLM casting, replayable TTS requests, seg

Manage accountability items on the configured Monday.com board. Use when creating new accountability items, checking on existing ones, running work sessions, or when a cron job fires. Also use when th

Patterns for building dark-themed financial charts and data visualizations. Covers chart theming, color scales for gains/losses, and real-time data display. Use when building trading dashboards or fin

Build or improve a bilingual email translation and notification workflow that converts raw emails into Chinese-friendly bilingual output. Use when designing prompt-driven email formatting, subject/dat

Create company-internal skills interactively. Use when users want to create a skill for internal company workflows, APIs, business processes, or tools. Guides the user through providing requirements,

Auto-triggers Context Engineering compliance and Lobster enforcement when proposing, creating, or formalizing rules, policies, processes, or behavioral constraints. Implements the principle: the act o

Generate polished corporate PPTs using a light-themed company template. Activate when: (1) User asks to create/make/generate a PPT/PowerPoint/幻灯片/演示文稿 (2) User provides content and wants it turned int

ScrapeBox-style candidate discovery for link building and outreach. Rotates Tor exit nodes (and optionally public HTTP proxies) so the server's datacenter IP never touches the search engine, harvests

Spawn OpenCode as an ACP (Agent Client Protocol) subagent for complex coding tasks. Use when building games, web apps, multi-file projects, or when the user says "use opencode", "spawn opencode", "cod

Create realtime **passthrough** AI avatar sessions (LiveKit WebRTC — you bring STT/LLM/TTS and publish audio), view-only viewer tokens for multi-viewer watch, and offline lip-sync avatar videos using

A unified AI Engineering Operating System that orchestrates the full lifecycle of agent creation - extracting tacit knowledge, structuring the Agent OS, and enforcing pre-deployment governance. Use th

Tutorial patterns for documentation - learning-oriented guides that teach through guided doing. Use when writing a tutorial, learning guide, getting-started or onboarding guide, beginner/introductory

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric a

完整创建一个 OpenClaw Agent，包括：一次性问卷收集配置信息、自动生成 workspace 文件（SOUL.md/AGENTS.md/IDENTITY.md/USER.md/MEMORY.md/HEARTBEAT.md）、 执行 `openclaw agents add` CLI 注册、内置 capability-evolver 自我进化（--review 模式）、 以及向用户输出完整

Text-to-speech using Kokoro local TTS. Use when the user wants to convert text to audio, read aloud, or generate speech.

Build-in-public companion for indie hackers — content workflow, Twitter engagement, project soul creation. A living assistant, not a tool.

Build or restyle interfaces with a curated library of bundled DESIGN.md references extracted from public websites. Use when the user asks for a landing page, dashboard, redesign, design system, UI pol

Set the shared-space norms that end the small daily frictions — meeting room booking discipline (the ghost-booking cure), hybrid-call room behavior, the shared kitchen/space contracts, and the enforce

Write the purchase request that gets approved — the cost-of-not-buying framing, the ROI math at the approver's altitude, the alternatives-considered section that preempts the obvious pushback, and the

Design an expense-tracking sheet that survives real receipts — the capture-at-spend habit, the category set that matches reimbursement or tax rules, the receipt-link discipline, and the month-end clos

Cap your work-in-progress so things finish — the personal WIP limit (3 active outcomes, defended), the finish-before-start rule with its exceptions named, the parking lot for the overflow, and the thr

Set up a research repository the team actually reuses — the atomic-insight format (finding + evidence + source + date), the tagging that makes old research findable by new questions, and the check-the

Track a team's budget so surprises die young — the commitment-based view (spent + committed + planned, not just invoiced), the category grain that matches how the team actually spends, the monthly clo

Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules (what moves a block, what never), the entry ritual that beats the blank-stare s

Write a team's working agreements — the small set of explicit norms (communication, meetings, decisions, conflict) that replace the assumptions people were silently violating, built from the team's ac

Run a company event — the launch party, the customer day, the team celebration — as the operation it is: the goal that shapes every choice, the budget with its forgotten lines, the vendor and venue co

Design slides where the data makes the argument — the takeaway-titled chart, the one-chart-per-slide rule, the annotation layer that guides the eye to the point, and the honesty pass on projected data

Schedule work by energy, not just time — the week of self-observation that maps your real peaks and troughs, the work-to-energy matching (hard creative work on peaks, admin on slopes, meetings on shou

Delegate so the work comes back right the first time — the brief that transfers outcome, context, and constraints (not just the task), the autonomy level stated explicitly, and the check-in design tha

Grade the evidence behind a claim before betting on it — the hierarchy for business evidence (experiments > usage data > surveys > interviews > anecdotes > opinion), the fit-for-decision test, and the

Turn a folder of accumulated documents into one decision-ready brief — the skim-map pass over the pile, the extraction against the brief's actual questions, the conflict reconciliation when documents

Write presenter notes that actually help mid-talk — cue-grain phrases instead of scripts, the transitions and numbers that deserve verbatim capture, the timing marks that keep the talk on schedule, an

End the workday on purpose — the ten-minute shutdown that closes open loops, stages tomorrow's start, and gives the brain permission to actually stop (the incomplete-task hum has an off switch, and it

Build an all-hands that lands with everyone from intern to VP — the mixed-altitude structure (the story for all, the numbers for some), the wins-with-names section done right, the hard-news slide hand

Write the handbook page that ends the repeated explanation — the answer-shaped structure (task-first, context second), the ownership and freshness header, and the write-once-point-forever discipline t

Get the five questions that matter before you sign, buy, or agree to anything — the front door to the decoder family, routed by situation. Use when asked what should I ask before signing this, I'm abo

Clear the desktop that's become a hundred-icon guilt mosaic — the fast triage that empties it today, the honest read of what the desktop was being used for (it's a to-do list wearing icons), and the r

Turn a business trip into a one-page brief that runs itself — the itinerary with buffers and failure modes, the meeting logistics pre-solved (addresses, contacts, backup numbers), the packing-and-prep

Write a PRD for an AI-powered feature, covering the things normal PRDs miss. Use when asked to spec an AI/LLM feature, write a PRD for a feature that uses a model, or plan an AI capability (assistant,

Decline requests without damaging relationships or your standing — the fast-clear-warm formula, the alternative-attached no, the no-to-the-boss version (tradeoffs, not refusal), and scripts for the as