Chatchat Skills

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Use this skill when making Binance Spot API requests, signing authenticated calls, choosing testnet versus mainnet endpoints, handling API keys and secrets, or working with Spot market data and orders.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

Use this skill when giving yoga guidance on pose alignment, sequencing, breathwork, modifications, props, level-appropriate practice planning, and safety-aware instruction.

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.

Use this skill when users ask about BAP-578, Non-Fungible Agents, or hands-on engineering for the BAP-578 reference implementation on BNB Chain, including identity, memory, learning proofs, vaults, AI integration, and contract architecture.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Use this skill when generating or editing raster images for project assets, mockups, photos, illustrations, textures, sprites, transparent-background cutouts, or visual variants where bitmap output is more appropriate than repo-native SVG, vector, HTML, CSS, or canvas work.

TikTok MCP-first advertising orchestrator with 8-step analysis workflow. Use when the user asks colloquially to list/查看广告账户或campaign ("我有哪些广告账户", "列出campaign", "看看我的广告", "有哪些账户"), find top/worst performers ("哪个广告效果最好", "表现最好的campaign", "最差的广告", "浪费预算的广告", "best/worst performing ads", "top campaigns"), or wants to inspect, plan, launch, diagnose, report, or optimize — including daily pulse/日报/weekly report/周报, vertical/user type classification/垂类诊断, creative fatigue analysis/创意素材分析, audience optimization/受众分析, landing page & W2A path/落地页分析, budget & bid/预算出价优化, measurement & SKAN attribution/归因分析, activity changelog/操作记录, cross-account rebuild/账户迁移, error & review handling/审核报错诊断, or generate HTML reports/出报告/生成报告. Also use for any of 13 verticals: ecommerce, short_drama/短剧, utility_or_w2a/工具, casual_game/休闲游戏, midcore_or_hardcore_game/中重度游戏, novel/小说, social/社交, entertainment/泛娱乐, financial_leads/金融借贷, search_arbitrage/搜索套利, earnings_or_offerwall, regulated_high_risk, agency_or_mixed/代理商. Covers TikTok, Smart

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically.

Use this skill when answering gardening questions about plant care, soil management, seasonal timing, pest control, pruning, propagation, or garden planning.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Use this skill when managing GitHub issues with structured triage, prioritization, assignment, labels, status tracking, duplicates, and actionable next steps.

Use this skill when tracking meme-token launches, hot narratives, migration status, holder counts, net inflow, and fast market filters around early token activity.

Use this skill when giving parenting guidance on age-appropriate behavior support, family routines, communication strategies, child context, burnout, and avoiding common advice pitfalls.

Use this skill when monitoring CI pipelines for failures, regressions, instability, flaky jobs, and ownership signals, then prioritizing fixes with clear evidence and next actions.

Use this skill when giving management guidance on team leadership, operating cadence, delegation, feedback, planning, organizational effectiveness, or manager decision-making.

Use this skill when screening incoming NDAs and classifying clauses or whole agreements as standard, needs review, or significant risk based on practical legal triage signals.

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Use this skill when designing and building durable command-line tools from API docs, OpenAPI specs, SDKs, curl examples, admin tools, web apps, or local scripts, especially when the CLI should expose composable commands, stable JSON output, auth/config handling, install-on-PATH behavior, and a companion skill.

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.

Use this skill when setting up or troubleshooting Bonero mining, wallets, daemons, RandomX CPU mining, or Monero-style private cryptocurrency workflows for AI agents.

Use this skill when supporting alcohol reduction or sobriety with planning, craving management, trigger review, safer next steps, relapse prevention, and recovery milestones.

Use this skill when supporting cigarette or nicotine cessation with craving support, practical replacement strategies, trigger planning, smoke-free routines, relapse prevention, and recovery guidance.

Use this skill when setting up, improving, or auditing analytics measurement for experiments, conversion tracking, event instrumentation, funnel analysis, or A/B test readiness.

Use this skill when deploying, verifying, configuring, or validating BAP-578 Non-Fungible Agent contracts on BNB Chain testnet or mainnet, from environment setup through post-deployment checks.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Use this skill when turning actual code changes into focused commit plans or commit messages, splitting unrelated changes, applying Conventional Commits, or adding reviewer-ready scope and risk notes.

Use this skill when containerizing services or debugging Docker workflows, including production Dockerfiles, Compose setups, reproducible builds, secure defaults, image size, caching, and runtime behavior.

Use this skill when helping reduce caffeine gradually, manage withdrawal, replace the habit with lower-friction alternatives, protect sleep, and maintain energy during tapering.

Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Use this skill when reading, verifying, scanning, querying, indexing, or monitoring BAP-578 agent data directly from BNB Chain, including metadata, event history, vault integrity, and bulk RPC workflows.

Use this skill when writing, running, debugging, or extending BAP-578 Non-Fungible Agent tests, including infrastructure setup, function coverage, edge cases, upgrades, gas profiling, and Hardhat workflows.

Use this skill when planning, implementing, testing, or executing safe BAP-578 contract upgrades with the UUPS proxy pattern, including storage layout discipline, V2 implementations, deployment, and rollback planning.

Use this skill when turning goals, priorities, and meeting notes into executive operating plans with owners, dates, metrics, decisions, cadences, and follow-through artifacts.

A set of resources for writing internal communications using company-preferred formats, including status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, and project updates.

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

Use this skill when creating or loading AI session handoffs, saving context before pausing, nearing context limits, resuming complex work, or preserving decisions, files changed, blockers, and next steps.

Use this skill when retrieving or interpreting on-chain smart-money trading signals, including buy or sell direction, trigger price, current price, max gain, exit rate, and token tags.

Use this skill when turning messy workout information into clear logs, comparing user-provided sessions, surfacing trends or likely PRs, and suggesting realistic next-session steps.

Use this skill when planning monetization, pricing, treasury flows, growth strategy, unit economics, go-to-market, or commercial sustainability for BAP-578 Non-Fungible Agents.

Use this skill when creating audience-focused blog posts, social posts, newsletters, marketing copy, hooks, outlines, and calls to action.

Use this skill when reviewing contracts against an organization-specific negotiation playbook, flagging deviations, summarizing risk, and drafting redline or fallback language.

Use this skill when planning or executing desktop application releases, including repeatable builds, signing, packaging, release candidates, rollout checks, and cross-platform production readiness.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Use this skill when creating personalized triathlon, marathon, ultra-endurance, or long-distance training plans with periodization, recovery, intensity zones, and race-specific preparation.

Use this skill when implementing or reviewing Go code that needs idiomatic concurrency, error handling, interface design, package structure, service patterns, readability, correctness, or maintainability.

Use this skill when producing provider documentation that must be accurate, actionable, and support-friendly, including setup, usage, limits, troubleshooting, and release-ready structure.

Use this skill when keeping analytics instrumentation accurate, consistent, and release-ready across event definitions, tracking plans, schemas, implementation, QA, and governance.

Use this skill when defining metrics, building indexers, creating dashboards, or generating reports for BAP-578 Non-Fungible Agents from minting, vault funding, treasury, engagement, and event data.

Use this skill when translating a book, chapter, or long-form document into another language while preserving structure, formatting, terminology consistency, and document continuity.

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Use this skill when planning or executing mutation testing to evaluate whether a test suite catches meaningful defects, especially when coverage is high but confidence is low.

Use this skill when designing workout programs, explaining exercises, tracking progress, adapting training based on feedback, or planning strength and conditioning routines.

Use this skill when searching or researching tokens by keyword, contract address, or chain, including metadata, social links, real-time market data, holder/liquidity signals, and K-line candlestick data.