مهارات وكلاء موثّقة وجاهزة للتثبيت — الصفحة 14

Insurance guidance for mainland China: needs analysis, product comparison, premium calculation, and plan design.

Turn creative briefs into industry-standard storyboards through a gated four-state workflow with per-step user confirmation.

Generate videos from text prompts and reference images using the Kling v3 Omni model via the dLazy CLI.

Generate a digital human broadcast video from a portrait image plus audio or text, using the Jimeng OmniHuman 1.5 model.

A guided three-stage workflow for co-authoring documents with iterative refinement and reader testing.

Create, edit, and analyze .pptx decks with bundled tools and a vetted list of pptxgenjs footguns.

Build a Figma design system from a codebase in phased, checkpointed steps.

Generate Codex-compatible animated pets from text, references, or brand cues into a packaged atlas with QA.

Generate or edit raster images for project assets through a built-in image tool, with an optional CLI fallback for path-controlled or batch work.

Get authoritative, current answers about OpenAI products, APIs, and Codex with citations from official docs.

Generate a security ownership map from git history, exposing bus factor, sensitive hotspots, and co-change clusters.

Scaffold a Codex plugin folder with `.codex-plugin/plugin.json`, optional companion dirs, and marketplace entries.

Get language-specific security guidance and prioritized vulnerability reports for Python, JavaScript/TypeScript, and Go projects.

Route SendGrid requests to the right sub-skill for sending transactional email or receiving via Inbound Parse Webhook.

A curated, weekly-updated collection of 11211+ OpenClaw agent skills across 14 categories.

Writes and corrects English that reads like a native wrote it — any variety, any register. Use when text sounds stiff, robotic, translated, or AI-generated; when a sentence is grammatically fine but "sounds wrong"; when choosing between US, UK, Australian, Canadian, Irish or Indian spelling, vocabulary and punctuation, or when a document mixes them; when a first language keeps leaking through — articles, prepositions, tense, false friends, word order; when formality must be calibrated for an email, a client, or a meeting; when idioms, phrasal verbs, slang or collocations land wrong or sound dated; when commas, hyphens, capitalization, quotes, dates or numbers need a house rule; when confusable words, jargon or hedging blur the meaning; and for pronunciation, small talk, and improving on purpose. Not for grammar-only fixes (`grammar`), translation (`translate`), IELTS or TOEFL prep (`ielts`, `toefl`), or drafting in your own voice (`writing`).

Maintain agent continuity, durable memory, and identity state across sessions through Notion-backed journals and LTM.

Model-led arXiv collection: author queries, judge relevance per result, then merge and dedupe into a final paper set.

Coaches a person toward a goal, and runs the professional coaching craft: sessions, questions, accountability, and clients who will not move. Use when someone asks to be coached, held accountable, or pushed on a goal; when they restate the same intention for weeks without acting, over-plan instead of starting, answer every option with "yes, but", or miss the same commitment again; when a session needs an arc, an opening question, or a closing commitment; when the user is a coach and needs a chemistry call, intake, a coaching agreement, pricing and packages, a stalled client, group or team work, supervision, or credential hours; and when the line between coaching, therapy, consulting, and mentoring has to be drawn. Covers executive, career, business, health, life, creative, and ADHD coaching. Not for clinical care (`therapist`, `psychologist`), personal productivity systems (`productivity`), or habit streaks (`habits`).

Expert SurrealDB 3 architect and developer skill (tracks v3.1.4+). SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospa...

Get a repo-specific AppSec threat model with evidence-backed abuse paths and prioritized mitigations.

Installs the NEXO Desktop runtime with local memory, guard checks, Deep Sleep, and MCP tools.

Turn a fuzzy intention into a measurable, verifiable objective before an agent starts work.

Designs, runs, records, and closes out meetings: agendas, facilitation, decisions, minutes, and follow-up. Use when preparing or chairing a 1-on-1, standup, retro, planning session, all-hands, kickoff, design review, client or board call, or offsite; when a meeting ends with no decision, runs long, or relitigates last week; when action items vanish, owners are vague, or nobody chased them; when a transcript or raw notes must become a record with owners and dates; when a recap or formal minutes have to go out; when a recurring meeting has outlived its purpose or the calendar is too full to build anything; when an invite should be declined or replaced by a written update; when a remote or hybrid room leaves half the attendees silent; and when bad news, conflict, or an escalation has to be handled live. Not for note apps and vaults (`notes`), day and calendar planning (`calendar-planner`), or the address book itself (`people`).