Explore

Prove model-disabled skills stay outside the model catalog.

Exercise project skill discovery and loading in snapshot tests.

Prove user-disabled skills remain available to the model.

Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.

Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider, then define, run, repair, or roll back the Plugin.

Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as "used to", "no longer", "this cut"; stack or review vantage ("a later PR in this stack", "rejected in review"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.

Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.

Use when writing, reviewing, restoring, trimming, or auditing prose in the deepseek-harness repo, including deciding where documentation or comments are required across Markdown, JSDoc, code and test comments, prompts, descriptions, diagnostics, and CLI or UI strings.

Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository suite.

Use when landing a stack of dependent GitHub PRs (A ← B ← C, where each bases on the one below) onto master, merging a PR whose base is another open PR's branch, or whenever a request mentions "stacked PRs", "PR stack", "dependent PRs", or merging several related PRs in sequence. Requires every same-repository dependency chain to use GitHub's official stacked-PR feature before landing so GitHub owns stack-wide rules, CI, ordering, retargeting, and merge state.

Use when working in the deepseek-harness repo to find non-obvious simplification candidates, write proposed Agent Notes or inline TODO/FIXME/XXX notes, audit or coalesce superseded Agent Notes, or fold worthwhile simplification ideas from another PR; especially for dead, duplicated, speculative, over-built, added-then-removed, or hand-rolled-where-a-dependency-exists surfaces.

Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.

Adopt govctl in an existing project by discovering and confirming historical decisions, specifications, and active work before backfilling a governed baseline

Set up govctl in the current project with explicit installation and overwrite authorization

Record a focused VCS commit with govctl validation and Work Item traceability

Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.

Use when the user wants to discover, evaluate, and install external agent skills from the open skills ecosystem, especially through the Vercel Skills CLI.

Use when the user wants browser-backed web data access, authenticated fetches, website adapters, or safe browser automation through a local bb-browser installation.

当 NextClaw 产品更新后需要生成、替换、挑毛病或检查官网、GitHub README、用户文档或社交传播中的真实截图、AI 宣传视觉、整页 HTML 宣传预览、社区二维码等对外视觉资产时使用；也用于“更新截图”“重新截一批图”“做宣传页”“生成 campaign 页面”“视觉审稿”“五星挑刺法”或发布前检查视觉资产。普通站点布局开发或只写文章不触发。

Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then publish to a dedicated assets branch when the task includes attaching the GIF to a pull request. Use when asked to make, record, or generate a GIF that demonstrates a browser workflow, and for every pull request that changes product-user-visible GUI behavior, which MUST include a GIF recorded from the pull request's real server and model flow.

Use when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset and Python search runtime.

通用开发生命周期的「验证与测试」阶段 owner；当实现或产物需要证明行为、合同和运行链路时使用，负责按 L0-L4 选择最小充分证据，不负责可维护性 Review 或发布决策。

通用开发生命周期的「任务理解与现状调查」阶段 owner；当需要理解用户输入、明确目标、成功条件、影响面、当前链路或根因时使用，负责形成可决策证据，不负责主动发现新需求、冻结方案或修改实现。

开发结束前判断经验是否值得沉淀，区分事实、方法、流程和沟通约定；优先修正、合并与退场，无增量不落盘，不接管实现或整体完成。

通用开发流程的唯一 Meta Skill；理解后选择 initialization、standard、trivial 或 bugfix，管理阶段门、返工、验收与整体完成；阶段 Skill 提供方法，知识库提供事实。

通用开发生命周期的「方案设计」阶段 owner；当用户明确要求设计、风险达到 L3-L4，或用户可见 L2 功能存在真实方案空间时使用，负责冻结可执行设计，不负责实现、验证或发布。

通用开发生命周期的「交付、发布与部署」阶段 owner；当结果已经达到交付条件，或用户明确要求提交、发布、部署时使用，负责授权边界、结果交接和专项发布路由，不负责实现或 Review。

当用户明确要求领取、处理、批量清空或定时扫描 Linear 的 `Delegated to Agent` issue 时使用；按队列状态、领取竞争、交付路径和收尾四个阶段渐进读取。

仅当用户明确要求 AI 从产品方向、愿景、真实现状或用户信号中主动发现值得解决的问题、形成候选需求，或降低对详细需求输入的依赖时使用；负责形成有证据、可验证的需求假设，不负责实现、排期或自动纳入路线图。

仅当用户明确要求跨上下文、整夜或低监督持续执行可维护性治理战役，且治理规则已明确时使用；普通重构、bugfix 和一次性清理不触发。

Reproduce a live website from its URL as a clean, deployable Vite + React project by running the complete agent-driven Perfect Web Clone harness: capture source evidence, plan the full page, author every section, implement common interactions, build, compare, repair, and hand the measured result to the user for review. Use whenever the user asks an agent to clone, copy, reproduce, replicate, rebuild, or 复刻 a website or web page, including a minimal request containing only an action and URL. The user gives one natural language instruction; the current agent runs the internal multi-step loop through the deterministic pwc hands and eyes.

Android/Termux constraints reference. Prevents Claude Code from suggesting commands that fail silently on Android (sudo, systemd, non-Termux paths, etc.).

Before starting any research task, define what decision the research serves, what "done" looks like, and what is out of scope. Prevents research that answers the technically correct question but not the operationally relevant one.

Before building anything, justify the tool choice and complexity level. Could a shell script do this? Does it need Node.js? A full application? Prevents over-engineering by requiring explicit justification before choosing a heavier approach.

Export, write, and manage Feishu/Lark cloud documents. Supports docx, sheets, bitable, wiki, WeChat article import/export, drive management, and browser-based export for public or browser-readable docs. Use this skill when you need to read, analyze, write, or manage content in a Feishu knowledge base.

Plan Southeast Asia market entry including mode selection, regulatory requirements, cultural research, and go-to-market timeline. Use this skill when the user is considering expansion to SEA, evaluating entry modes (marketplace vs direct vs distributor), or conducting market feasibility studies — even if they say 'should we enter Vietnam', 'how to sell in Indonesia', 'SEA expansion plan', or 'find a local distributor'.

Design cross-border logistics strategies including direct mail, overseas warehousing, and bonded warehouse models for international e-commerce. Use this skill when the user needs to ship products internationally, choose a logistics model for cross-border sales, optimize shipping costs, or set up fulfillment in a foreign market — even if they say 'ship to Southeast Asia', 'overseas warehouse vs direct shipping', 'customs clearance', or 'reduce international shipping time'.

Apply Lean Startup methodology — Build-Measure-Learn loop, MVP, validated learning, and pivot decisions. Use this skill when the user is launching a new product or startup and needs to validate ideas quickly, design an MVP, decide whether to pivot or persevere, or reduce wasted effort on unvalidated assumptions — even if they say 'should we build this', 'how do we test this idea', 'when should we pivot', or 'we're burning cash with no traction'.

Apply Jobs to Be Done (JTBD) framework to understand customer motivation through functional, emotional, and social jobs. Use this skill when the user needs to understand why customers hire or fire a product, discover unmet needs, write job stories, or reframe product strategy around customer outcomes — even if they say 'why do customers buy this', 'what need does this serve', or 'customers aren't using our product as intended'.

Conduct heuristic evaluation of user interfaces using Nielsen's 10 usability principles. Use this skill when the user needs to audit a website, app, or interface for usability issues, prioritize UX improvements, or conduct a quick expert review without user testing — even if they say 'review this UI', 'find usability problems', or 'why do users struggle with our app'.

Apply Design Thinking's five stages — Empathize, Define, Ideate, Prototype, Test — to solve user-centered problems. Use this skill when the user needs to solve an ambiguous problem, redesign a user experience, facilitate an innovation workshop, or develop a new product concept from scratch — even if they say 'we don't know what to build', 'how do we innovate', or 'the users aren't happy but we're not sure why'.

Navigate Taiwan's tax system including corporate income tax (營所稅), business tax (營業稅), personal income tax, withholding obligations, and startup tax incentives. Use this skill when the user needs to understand Taiwan tax obligations, calculate tax liability, file taxes, or plan for tax efficiency — even if they say 'how much tax do we owe', 'what's the corporate tax rate in Taiwan', 'tax filing deadlines', or 'are there startup tax breaks'.

Analyze Taiwan-listed stocks using fundamental analysis including EPS, P/E ratio, dividend yield, and financial statement review. Use this skill when the user needs to evaluate a Taiwan stock, compare TWSE/TPEx-listed companies, assess valuation, or review earnings — even if they say 'should I buy this stock', 'analyze 台積電', 'is this stock overvalued', or 'compare these two Taiwan companies'.

Guide Taiwan company registration and legal setup including business entity selection, commercial registration, company registration, and tax ID application. Use this skill when the user is starting a business in Taiwan, choosing between sole proprietorship and company, or navigating the registration process — even if they say 'how do I set up a company in Taiwan', 'what's the registration process', 'sole proprietorship vs company', or 'I want to start a business'.

Analyze Taiwan's retail industry including convenience stores, department stores, supermarkets, hypermarkets, and e-commerce with omnichannel trends. Use this skill when the user needs to understand Taiwan's unique retail ecosystem, plan a retail strategy for Taiwan, or evaluate retail channels — even if they say 'how does retail work in Taiwan', 'convenience store strategy', 'Taiwan omnichannel', or 'where should we sell in Taiwan'.

Integrate Taiwan payment service providers including credit card, ATM transfer, convenience store payment, and mobile wallets (LINE Pay, JKoPay). Use this skill when the user needs to accept payments online in Taiwan, choose a payment gateway, understand payment flows, or handle refunds — even if they say 'accept payments on our site', 'which payment provider in Taiwan', 'integrate credit card payments', or 'set up LINE Pay'.

Analyze Taiwan's manufacturing industry structure including semiconductor, electronics, machinery, and petrochemical sectors. Use this skill when the user needs to understand Taiwan's industrial landscape, evaluate manufacturing sector opportunities, assess supply chain positioning, or contextualize Taiwan in global manufacturing — even if they say 'Taiwan manufacturing overview', 'semiconductor supply chain', 'what does Taiwan make', or 'industrial analysis of Taiwan'.

Navigate Taiwan healthcare regulations including NHI system, medical device classification, drug registration, telemedicine rules, and health data protection. Use this skill when the user is building a health tech product for Taiwan, needs to understand NHI, evaluate medical device regulatory pathways, or assess telemedicine compliance — even if they say 'sell a medical device in Taiwan', 'how does NHI work', 'telemedicine regulations', or 'health data privacy in Taiwan'.

Navigate Taiwan fintech regulations including FSC oversight, electronic payment laws, VASP rules, AML/KYC requirements, and the regulatory sandbox. Use this skill when the user is building a fintech product in Taiwan, needs to understand licensing requirements, assess crypto/VASP compliance, or apply for the regulatory sandbox — even if they say 'do we need a license', 'crypto regulation in Taiwan', 'KYC requirements', or 'fintech sandbox application'.

Implement Taiwan's e-invoice (電子發票) system including platform integration, B2B vs B2C formats, carrier consolidation, and tax filing reconciliation. Use this skill when the user needs to set up e-invoicing for a Taiwan business, integrate with the MOF platform, understand carrier codes, or troubleshoot invoice issues — even if they say 'set up e-invoice', 'how does 電子發票 work', 'integrate with 財政部', or 'carrier barcode scanning'.

Integrate TapPay for Taiwan e-commerce — TapPay Web/iOS/Android SDK, 3DS 2.0 flow, Apple Pay / Google Pay / LINE Pay integration via TapPay, TCS (TapPay Card Service) for tokenized recurring payments. Use when TapPay is chosen as PSP, comparing TapPay vs NewebPay, or debugging 3DS flows. Do NOT use for other gateways. STATUS: SKELETON — body pending.

Integrate NewebPay (藍新金流) for Taiwan e-commerce via mcp-newebpay. Use when accepting credit card / ATM / CVS / LINE Pay / periodical payments on NewebPay, handling 3DS 2.0 flows, computing TradeSha signatures, or reconciling callback webhooks. Do NOT use for comparing gateways (see tw-payment-integration) or for non-NewebPay providers (TapPay, ECPay have their own skills).

Integrate 街口支付 (JKOPay) for Taiwan e-commerce — web/app flow, JKO 幣 rewards, merchant settlement cycle, and scan-to-pay vs app-to-pay UX. Use when targeting younger TW demographic or integrating in-app JKO flow. Do NOT use for generic wallet integration (LINE Pay / Apple Pay handled elsewhere). STATUS: SKELETON — body pending.

Integrate 綠界 (ECPay) for Taiwan e-commerce — credit card, ATM, CVS 代碼, 超商取貨付款, and CheckMacValue signature. Use when ECPay is the chosen PSP, setting up logistics-payment combined flows (超取+COD), computing or verifying CheckMacValue, or handling ECPay callbacks. Do NOT use for gateway selection or comparison (see tw-payment-integration). Do NOT use for non-ECPay providers. STATUS: SKELETON — body pending.

Handle Taiwan e-commerce payment disputes — credit card chargebacks (扣款爭議), refund across bimonthly boundaries (retro 折讓 trigger), acquirer dispute timelines, and evidence packets. Use when a customer files a chargeback, when issuing cross-period refunds that affect invoices, or when building internal dispute SOP. Do NOT use for simple in-period refunds (gateway-specific skills handle those). STATUS: SKELETON — body pending.

Run Taiwan e-commerce promotional campaigns — 雙11, 618, 年中慶, 雙12, 週年慶, 母親節. Covers promo calendar, stacking rules across platforms, 檔期 pricing strategy, inventory allocation, and post-campaign 退貨 handling. Use when planning a specific campaign or building a year-round 檔期 schedule. Do NOT use for ad ROI measurement (use `ecom-promo-roi`). STATUS: SKELETON — body pending.

Set prices for Taiwan e-commerce — 含稅 vs 未稅 presentation, price-ending conventions (0/8/9 endings), marketplace price-match rules (momo best-price), 檔期 discount planning, and cross-channel price-parity. Use when pricing a new SKU for TW, rebalancing prices across platforms, or designing a 檔期 discount ladder. Do NOT use for generic pricing theory (use `biz-pricing-strategy`). STATUS: SKELETON — body pending.

Run CRM and member retention via LINE Official Account — broadcast cost model, rich menu, auto-response, tagging, 1-to-1 chat, and LINE Pay integration. Use when designing LINE OA strategy for a TW brand, segmenting members for broadcasts, or measuring LINE OA ROI. Do NOT use for generic CRM (use `ecom-rfm-analysis` or `biz-cac-ltv`). STATUS: SKELETON — body pending.

Taiwan e-commerce customer service — LINE / Messenger / email / phone channel mix, 消保法鑑賞期 scripts, PTT/Dcard reputation monitoring, 負評 response, and SLA targets for the TW market. Use when designing CS SOP, training CS agents, or responding to viral 負評. Do NOT use for generic chatbot design (use `cs-chatbot-design`). STATUS: SKELETON — body pending.