「sel」の検索結果

Use when recurring process failures, obsolete rules, or an explicit user request call for harness improvement.

日本語の概要は準備中です。原文の説明を表示しています。

Use when selecting skills for a task or resolving how skill workflows apply

日本語の概要は準備中です。原文の説明を表示しています。

Run a project's GitHub Issues through Orca Workers from a coordinating session in the project's Hub folder. The Orchestrator reads Issues, claims one, dispatches an Orca Task into a fresh worktree of the target repo, supervises until worker_done, and writes the outcome back to the Issue — it never edits code itself. Use when the user says "take

日本語の概要は準備中です。原文の説明を表示しています。

penpotを含む場合は必ず読み込む。セルフホスト環境管理、MCP経由デザインシステム構築・ UI/UXデザイン作成・プロトタイプ参照、デザインからのアプリケーション生成、 外部パイプライン（トークン同期・Style Dictionary・Storybook）、デザインレビュー・コメント操作。

Investigate model specifications, requirements, and evaluation strategy. Use when researching a model before benchmarking: reading HuggingFace model cards, estimating VRAM requirements, selecting GPU providers, and determining evaluation approach. Triggers on "model research", "investigate model", "model info", "VRAM estimate", "which provider", "model card".

日本語の概要は準備中です。原文の説明を表示しています。

Use when helping users configure LoRA training — select presets, understand parameters, and pick the right settings for their model type. Covers SD1.5, SDXL, SD3, and Flux1 with real-world presets.

日本語の概要は準備中です。原文の説明を表示しています。

Create a construction plan for a multi-step engineering task that requires multiple PRs or a phased approach. Produces a self-contained plan file with dependency graph, review gates, and step-by-step execution instructions for coding agents. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex task, or describes work that clearly needs multiple PRs. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, user asks to modify/update an existing plan, user says "just do it", or user asks for code review/audit.

日本語の概要は準備中です。原文の説明を表示しています。

Curate Busabase training examples, create immutable dataset snapshots, run reproducible LoRA or QLoRA fine-tunes on a local Apple Silicon Mac with MLX-LM, compare the untouched baseline and adapter on locked evaluations, and register approved adapters. Use when the user wants to train, fine-tune, evaluate, compare, promote, or manage a local language model with Busabase as the workflow source of truth. Do not use for RAG-only knowledge retrieval, cloud training, or training a foundation model from scratch.

日本語の概要は準備中です。原文の説明を表示しています。

Music-video production skill for turning an existing MP3 into a pure-visual (no-voiceover) music video through a bundled Busabase App-in-Skill UI. Use when the user wants to build an MV from a song they upload: write a one-line concept, keep a cast of characters with reference cards, and break the song into storyboard shots where each shot has a scene description and an image + video that can be either AI-generated (image-to-image from the character cards, draft video via local LTX) or uploaded by the user. Same character/storyboard management model as kelly-drama. Song generation (creating the song itself, incl. voice-cloned singing) is a documented future capability.

日本語の概要は準備中です。原文の説明を表示しています。

Run a Busabase-backed sales prospecting and first-touch outreach desk with a bundled Hono App-in-Skill deployable to AirApp. Use whenever the user invokes $kelly-sales-outreach or /kelly-sales-outreach, wants to enter a product or service and discover its ideal customers, asks to continuously find target accounts or public business contacts, needs evidence-based ICP scoring and personalized outreach drafts, or wants to review and send cold outreach safely. Four subcommands - setup, profile, research, send - plus the desk itself. Every first-touch message requires human approval; one company receives one initial email; guessed addresses, purchased lists, secret exposure, automated spam, and unreviewed external sends are forbidden.

日本語の概要は準備中です。原文の説明を表示しています。

Product-research (选品) desk (Busabase App-in-Skill) for a cross-border e-commerce seller. The agent sweeps trend sources — Amazon BSR movers, TikTok viral product videos, Temu/AliExpress rising items, Google Trends terms, competitor new launches — and files product candidates with margin cards (landed cost, fees, breakeven ACOS) and competition reads; Kelly verdicts them develop / watch / drop, and develop items become sourcing and listing briefs handed to kelly-listing. Use when the user invokes $kelly-picks or /kelly-picks, or asks for 选品, product research, a product sourcing radar, BSR movers, TikTok viral products, a margin calculator, breakeven ACOS, competition reads, or product candidate triage.

日本語の概要は準備中です。原文の説明を表示しています。

Goal-driven WeChat relationship strategy App-in-Skill. Reads the operator's own local WeChat through wechat-cli-rs, discovers candidates against an explicit goal, promotes only user-selected people into Busabase, and builds relationship snapshots and next-action suggestions without sending messages or modifying WeChat.

日本語の概要は準備中です。原文の説明を表示しています。

Listing factory (上架工作台, Busabase App-in-Skill) for a cross-border e-commerce seller. Use when the user invokes $kelly-listing or /kelly-listing, mentions 上架, listing, Amazon title bullets, A+ content, flat file, TikTok Shop listing, listing compliance, 禁用词, multi-locale listings, wants platform listings drafted from product source material or a kelly-picks brief, deterministic compliance checks against per-platform rule sets, a review queue for approving drafts, or approved listings exported as Markdown/CSV for upload.

日本語の概要は準備中です。原文の説明を表示しています。

Personal App-in-Skill inbound-inquiry reception desk (Busabase App-in-Skill) for cross-border/foreign-trade sellers, aggregating WhatsApp, Instagram, Messenger, and email inquiries into a pipeline with a product knowledge base, quote worksheet, approval queue, and follow-up reminders. Use when the user invokes $kelly-inquiry or /kelly-inquiry, mentions 询盘, inquiry desk, WhatsApp leads, quote management, 报价, foreign trade sales, follow-up reminders, or a lead pipeline, wants inquiries triaged into new/replied/quoted/negotiating/won/lost stages, agent-drafted replies and quotes reviewed before sending, or stale deals surfaced.

日本語の概要は準備中です。原文の説明を表示しています。

Run a Busabase-backed sandbox desk for scoring and triaging course-instructor ("讲师") candidates found on a recruiting-style platform. Use whenever the user invokes $kelly-instructor-sourcing or /kelly-instructor-sourcing, wants a lightweight instructor candidate tracker, needs to score sourcing-platform leads against a three-axis rubric (background endorsement, expertise depth/breadth, teaching-service ability) before reaching out, or wants to log a WeChat add without building a live-connected outreach tool. Three subcommands - setup, criteria, review - plus the desk itself. v1 is sandbox-only — every dataset is deterministic mock data, it never connects to a real sourcing-platform or messaging account, and it never sends a message or automates a WeChat add - that stays entirely human-performed outside the app.

日本語の概要は準備中です。原文の説明を表示しています。

Ad-campaign command desk (投放指挥台, Busabase App-in-Skill) for a cross-border e-commerce seller running Amazon Ads, Meta (FB/IG), TikTok Ads, and Google Ads. Use when the user invokes $kelly-ads or /kelly-ads, or asks about 投放, ad campaigns, ad spend, ACOS, ROAS, Amazon Ads, TikTok ads, Meta ads, Google Ads, search terms, negative keywords, bid adjustment, budget pacing, CPC spikes, rejected ads, ad anomaly detection, 广告优化, or reviewing agent-proposed adjustment cards (negative keyword, bid down/up, pause target, budget shift, creative refresh).

日本語の概要は準備中です。原文の説明を表示しています。

Run a Busabase-backed job-search outreach desk with a bundled Hono App-in-Skill deployable to AirApp. Use when the user invokes $kelly-jobhunt or /kelly-jobhunt, wants to turn a resume into a structured profile and a typeset PDF, wants to find target companies and their contact addresses instead of applying through a job board, wants one tailored application email drafted per company, or wants to review and approve each send. Four subcommands - setup, profile, research, send - plus the desk itself. One company receives exactly one email; mailbox credentials live in the Busabase Vault and never reach browser code.

日本語の概要は準備中です。原文の説明を表示しています。

Generates and maintains competitive battlecards from win/loss data, competitor intel, G2 reviews, and sales feedback. Use when building battlecards for a specific competitor, updating existing battlecards with new intel, preparing BDRs or AEs for competitive deals, analyzing win/loss patterns against a competitor, or responding to a competitor's product launch or pricing change. Also use when asked to "build a battlecard," "update competitive intel," "how do we beat [competitor]," "what do we say when a prospect mentions [competitor]," or "analyze our win/loss against [competitor]." Designed for B2B SaaS teams selling against known competitors in deals with multi-persona buying committees.

日本語の概要は準備中です。原文の説明を表示しています。

End-to-end ABM program design and orchestration for B2B SaaS mid-market and enterprise motions. Use when building a target account list, designing account tiering criteria, planning ABM channel orchestration, coordinating BDR outreach with marketing campaigns, defining ABM measurement frameworks, or running an ABM program review. Also use when asked to "build an ABM program," "set up account-based marketing," "design a target account strategy," "plan ABM campaigns," or "measure ABM results." Designed for demand gen teams selling to Mid-Market companies with $10K-$50K+ ACV, multi-persona buying committees, and 3-6 month sales cycles.

日本語の概要は準備中です。原文の説明を表示しています。

Generates account research briefs, personalized outreach sequences, persona-specific talk tracks, and objection handling frameworks for B2B SaaS BDR teams. Use when preparing BDR outreach for target accounts, building prospecting sequences, creating call scripts, developing objection responses, onboarding new BDRs, or reviewing outreach performance. Also use when asked to "write outreach emails," "build a prospecting sequence," "create a call script," "handle objections," or "research an account for outreach." Designed for BDR teams selling compliance, security, and GRC platforms to mid-market and enterprise buyers with multi-persona buying committees.

日本語の概要は準備中です。原文の説明を表示しています。

Generates sourced, BDR-ready account research briefs for named target accounts in B2B SaaS ABM and outbound motions. Use after a target account list is built and before outreach sequences are written. Best for Tier 1, Tier 2, and intent-qualified accounts where BDRs need a clear "why this account, why now, why this persona" hypothesis. Designed for B2B SaaS teams selling compliance, security, GRC, risk, or other technical platforms into mid-market and enterprise buyers. Not intended for broad list building or mass enrichment.

日本語の概要は準備中です。原文の説明を表示しています。

Design a GitHub social-preview card (og:image, 1280x640) for a repository. Use when the user asks for a social preview, repo cover, og image, link card, opengraph image, or README hero. Five editorial moods (editorial, poster, blueprint, gallery, terminal), CJK-first typography, one self-contained HTML file, deterministic checks, crisp PNG export. No image model needed.

日本語の概要は準備中です。原文の説明を表示しています。

Use when edit_blueprint.yaml and selects_candidates.yaml are ready and the user asks to compile the rough cut, generate timeline.json, or apply a review patch.

日本語の概要は準備中です。原文の説明を表示しています。

Select an evidence-backed platform delivery profile, preserve organic and ads scope boundaries, and produce safe-zone QA input with an explicit human preview gate when evidence is unknown or stale.

日本語の概要は準備中です。原文の説明を表示しています。