Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Collect read-only evidence about PlanetScale org, database, branches, webhooks, backups, roles, Insights, recommendations, and traffic configuration.
Use PlanetScale Insights and SQLCommenter-style query tags to attribute database load, identify risky queries, and prepare safe Traffic Control or schema recommendations.
Master skill that runs the full PlanetScale safe best-practices assessment — inventory, engine review, Insights, Traffic Control, webhooks, schema recommendations, codebase instrumentation, and agent operating model — then produces a unified recommendations report. Never applies changes without explicit approval. Use when the user asks to run the full assessment, all skills, or PlanetScale best-practices review.
Safely triage PlanetScale schema recommendations and turn them into reviewed branches, migrations, issues, or pull requests without applying production changes.
Review PlanetScale Postgres for Traffic Control, query tags, roles, pg_strict, backups/PITR, private connectivity, webhooks, branches, and safe agent operation.
Recommend webhook subscriptions and safe automation patterns for PlanetScale alerts, anomalies, schema recommendations, deploy requests, and agent workflows.
Review a PlanetScale Vitess database for safe migrations, deploy requests, schema recommendations, Insights, webhooks, and operational safety.
>- Use the PlanetScale CLI (pscale) from automated agents with --format json, auth check, pscale sql, and per-command --force. Run before other PlanetScale skills when driving pscale directly. Use when the user asks to automate pscale, run CLI commands headless, or verify pscale auth from an agent.
Enforce explicit approval gates for any PlanetScale, database, repository, credential, network, or automation mutation.
Inspect an application repository connected to PlanetScale and recommend SQLCommenter-compatible query tagging packages and conventions.
Configure safe agent behavior around PlanetScale MCP, Insights, schema recommendations, and repository work without autonomous production mutation.
A concise feature matrix for deciding which PlanetScale safety, observability, and automation recommendations apply by engine.
Execute approved PlanetScale changes end-to-end without per-step approval when the operator has explicitly acknowledged the risk. Defines the risk-acknowledgment contract, scoped autonomy levels, sensible execution ordering, continuous status reporting, halt conditions, and rollback discipline. Extremely safe, very enabling.
Choose the right local verification steps before claiming a ROSA change is complete.
Cross-check AWS-facing code and docs against official ROSA and AWS references before changing behavior.
Add or edit Cobra commands in openshift/rosa while keeping command wiring thin and package logic aligned with repo structure.
Keep CLI docs, structure tests, and user-facing guidance in sync when commands or workflow docs change.
Personal assistant workflow for durable memory, connected actions, decisions, planning and review. Use whenever the user discusses their life, commitments, goals, notes, choices, follow-ups, or schedule.
Turn whatever the agent just produced — a conversation, an analysis, an artifact, a markdown file — into a live shareable URL in seconds, published as-is via ReportRoom. Use when the user says "share this", "give me a link", "put this online", "make this a page", "send this to someone". This is the fast, verbatim path — for a restructured, designed report use report-publisher; for a view-tracked proposal use proposal-tracker.
Create or receive human-first AI task handoffs across chats, models, devices, and languages. Use when the user asks to hand off, export context, resume from a handoff, switch sessions while preserving work, says "交接一下", "接收交接", or supplies handoff.md, handoff.zip, handoff-audit.zip, an LCH Bundle/T0 package, OCH Snapshot, or LTM Packet. Default to one readable handoff.md; upgrade to handoff.zip only when required files must travel, and to handoff-audit.zip only for formal audit, cross-organization delivery, or proof. Preserve current intent, stop point, next action, decisions, constraints, rejected and failed paths, answered questions, materials, omissions, and revalidation needs. Do not use for generic summaries, memory lookup, hidden reasoning, completed trivial chats, or after the user declines.
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
Use FIRST when any new piece of work arrives — a request, feature, change, fix, question, or idea — before starting on it or choosing an approach. Not for continuing work already routed to a workflow skill.
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming skill.
Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.
Use when composing an ask_user_question round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo_* tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose the plan FIRST (todo_write before you ask questions or start work), work tasks strictly in order with one step in_progress, keep statuses current, re-read the list (source of truth) to catch the user's edits, respect removals, and never delete done items.
The project's specs are its ground truth: durable documents describing the architecture, decisions, contracts, and boundaries behind the code, organized as a connected graph. Read this skill and reach for the spec tools FIRST — before reading code — whenever you explore the project, plan or start a task, add or change a feature, implement anything, investigate an area, check work against recorded decisions and contracts, or otherwise work with specs. Also use it to create or maintain specs.
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
> Craft long-form generative art for onchain platforms — Art Blocks, 256ART, Verse, Highlight, Plottables, bootloader.art, or a self-hosted drop. Covers hash-seeded determinism, resolution-agnostic rendering, features and rarity design, preview capture signals, debug GUIs and image/video export shortcuts, verification of a sketch before minting, and the ethics of the field. Use when the user mentions generative art, gen art, creative coding, long-form, onchain art, a seeded sketch, a PRNG or deterministic randomness, traits, rarity, features, a mint, a plotter or SVG output, or pastes platform APIs such as tokenData, $features, inputData, $bootloader, BTLDR, hl-gen, or a base64 payload query param.
Comprehensive App UI/UX design best practices. Supports two tracks: Convention Track (adopt a proven design language for SaaS/utility products) and Innovation Track (multiple brand-driven design methodologies — Material Metaphor, archetype-driven, narrative-driven, cultural-semiotic — for brand-driven products). Use when users want to: (1) Define visual identity for a new product, (2) Create design specifications and tokens, (3) Establish UI component guidelines, (4) Build a cohesive design language, (5) Review UI/UX quality, (6) Refine existing designs, (7) Audit design quality. Triggers: 'design system', 'UI design', 'UX design', 'visual identity', 'design specs', 'design tokens', 'component guidelines', 'look and feel', 'app design', 'design refine', 'design audit', '视觉设计', '设计规范', '设计系统', 'UI最佳实践', 'UX最佳实践'.
Use when three or more AI agents are available and a task needs coordinated execution, role assignment, independent verification, risk controls, or lower token/API cost. Activation is configurable: global, keyword-triggered, or manual.
多智能体团队协作与任务交接工作流。多个 AI 助手/代理（跨工具、跨会话）共同推进项目时，用「共享交接单」协调分工：先读再动、接续不重做、进展留痕、单写入者边界、完成必须附验收证据。内置多 Agent 协同调度防翻车指南：上下文爆炸、协作死锁、状态不一致、幻觉传染、通信风暴、Agent 蔓延、意图漂移、无验收聚合等八大问题的工程化解法。当用户提到 agent 协作、多开接力、任务交接、团队代理、协同调度、多Agent编排、换助手继续干活时使用。
Research and plan Amazon consumer-electronics category growth across wireless, electronics, PC, camera, office products, and musical instruments in North America, Europe, and Japan, with current-demand validation, compliance, logistics, promotion, and lifecycle-ad gates. Use for 消费电子选品, CE品类攻略, wireless/PC/camera/office/musical instruments, AI设备/智能穿戴/耳机, FCC/UL/CE/EPR/EEL/METI, 带电物流, 促销日历, 电子品类生命周期广告, or converting the authorized 2025 guide into an evidence-backed plan. This is not legal advice; all 2025 claims and policies require current official verification.
Diagnose and draft Amazon Canada apparel advertising plans with lifecycle and seasonal timing, English/French search coverage, account evidence, profitability guardrails, and approval-ready experiments. Use for 加拿大站服饰广告, Amazon.ca Coat 外套夹克, Underpants 内衣文胸, 季节性长生命周期, 长生命周期, 新品期成长期成熟期, 广告预算配比, SP/SB/SBV/SD/商品投放, 法语关键词, 旺季预热, 复购再营销, CPC/ROAS/ACOS 异常, or when converting the authorized course material into an account-specific plan. Default to diagnosis and draft; never write live advertising changes without explicit human approval.
Diagnose and plan privacy-safe Amazon Marketing Cloud (AMC) analytics and audience activation, especially for European and peak-season accounts, including journey/time-to-conversion analysis, reach/frequency, overlap, new-to-brand, rule-based and lookalike audiences, no-code audience templates, and SP/SB/SD/DSP activation. Use for AMC, 亚马逊营销云, 欧洲站 AMC, 旺季高潜人群, 购物车/浏览未购, 高价值新客, 潮汐人群, 转化路径, 购买周期, 受众竞价加成, or turning the authorized AMC courses into an approval-ready plan. Default to read-only analysis and drafts; never expose user-level data or mutate audiences/campaigns without verified scope and explicit human approval.
Turn verified Amazon product and audience evidence into reviewable AI-assisted advertising concepts, copy, image/video briefs, variants, and controlled creative tests. Use for 对话式AI广告素材, Creative Agent, Creative Studio, AI爆款素材, AI视频脚本, 商品广告创意, prompt共创, 素材A/B测试, POE/ABA insight-to-creative, or converting the authorized conversational-AI seller case into a repeatable workflow. Verify current tool availability and policy, keep human fact/brand/compliance review, and never publish generated assets or change live ads without explicit approval.
Plan and diagnose Amazon Europe multi-market advertising for standard, non-standard, high-ticket, and seasonal products across mature and emerging marketplaces, with localization, logistics, decision-cycle, and profitability gates. Use for 欧洲多站点广告, UK/DE向FR/IT/ES/NL/SE/PL/BE/IE拓站, 标品vs非标品, 欧洲高客单, 返校季, multi-market SP/SB/SD, Pan-European inventory, 本地化素材, or converting the authorized EU posters into a staged experiment. Historical claims and bid/budget examples are source snapshots; verify current marketplace availability and require approval before live changes.
Build and diagnose a profit-aware Amazon advertising architecture by working backward from stage-level sales and profit goals into inventory, keyword priorities, campaign roles, budgets, and measurable experiments across SP, SB, SBV, SD, keyword targeting, product targeting, and seasonal launch phases. Use for 精品广告架构, 亚马逊广告架构搭建, ASIN 推广计划, 季节性新品预算, 销量利润倒推, 关键词分层/竞争度/SPR/CPR, SP SB SBV SD 组合, 红海类目投放, 广告预算分配, 关键词首页计划, 周复盘, 或根据《如何搭建一个精品的广告架构》形成可审批方案. Default to analysis and draft; do not change live campaigns or claim organic-rank causality without verified account evidence and human approval.
Diagnose Amazon Ads ACOS with reconciled CTR, CPC, CVR, AOV, ROAS, TACOS, placement, search-term, benchmark, attribution, and contribution-margin evidence, then produce a single-variable optimization experiment. Use for ACOS 高低判断, 广告亏损, CTR/CVR/CPC 异常, 盈亏平衡 ACOS, 广告报告诊断, Benchmark 基准, placement 浪费, 搜索词不精准, Listing 转化问题, 广告利润优化, or converting the authorized Amazon Ads metrics course into an account-specific plan. Default to read-only diagnosis and draft; never change live campaigns without explicit human approval.
Diagnose and plan Amazon Japan apparel advertising with Japan-specific consumer behavior, seasonality, and ASIN lifecycle playbooks for long-lifecycle, short-lifecycle, and seasonal products. Use for 日本站服饰广告, JP apparel ads, 背包/内衣/泳装投放, ASIN 生命周期判断, 日本站新品冷启动, 品牌推广启动时机, Amazon Points, 日文功能词, 季节性备货与预热, 广告预算结构, ACOS/ROAS 诊断, 复购再营销, 或根据《亚马逊日本站服饰品类广告运营手册》输出可审批的投放方案. Default to analysis and draft; do not mutate live campaigns without explicit human approval.
Audit, diagnose, rewrite, creatively brief, test, and safely prepare updates for Amazon product detail pages using live marketplace and product-type requirements, verified product facts, Brand Analytics, Search Query Performance, Ads search terms, customer feedback, competitor observations, and optional third-party estimates. Use when asked to improve or evaluate Amazon titles, bullets, descriptions, backend search terms, attributes, images, video, A+ Content, Brand Story, variations, indexing, CTR, CVR, return prevention, ad-to-listing relevance, or to prepare an approval-ready Listings Items API PATCH. Default to draft and review; never invent product facts, copy competitors, manipulate reviews, or silently publish changes.
Research and plan Amazon fashion-category growth across the US, Europe, and Japan using trend validation, marketplace-specific selection, brand/store/content tools, promotion economics, inventory routing, and return-reduction gates. Use for 时尚品类选品, 美欧日服饰趋势, fashion opportunity scan, 女装男装童装鞋靴箱包珠宝, 品牌旗舰店与帖子, 促销组合, AWD/FBA库存, 尺码退货, or converting the authorized 2025 fashion guide into a current evidence plan. Route lifecycle campaign execution to the apparel-ads Skills; treat all 2025 trends, product lists, tools, and case figures as snapshots until currently verified.
Plan and diagnose evidence-based Amazon full-funnel growth across awareness, consideration, conversion, and loyalty without collapsing brand media, retail readiness, and performance ads into one metric. Use for 全流域营销, 全漏斗营销, 品牌出海, media mix, non-linear customer journey, CTV/online video/social/search coordination, new-to-brand, high-ticket decision journeys, brand-plus-performance measurement, or turning the authorized 2025 Ipsos/Amazon study into an account-specific plan. Default to read-only analysis and a test plan; current availability, policy, and live media changes require verification and explicit approval.
Research and plan Amazon home-and-lifestyle category growth across home, home improvement, kitchen, furniture, automotive, lawn and garden, sports, toys, and pets in North America, Europe, and Japan, with demand, fitment/safety, sustainability, logistics, and lifecycle-ad gates. Use for 生活百货选品, 家居/厨房/家具/汽配/花园/运动/玩具/宠物, OHL category, A+ Gen AI, Creator Connections, Climate Pledge Friendly, Amazon Custom, Part Finder/ACES, AWD/SFP, 大件物流, or converting the authorized 2025 guide into an evidence-backed plan. All product lists, programs, policies, and figures are snapshots requiring current validation.
Localize Amazon listings, search terms, advertising copy, images, and video for a target marketplace by combining verified product facts, native-language search evidence, cultural context, policy, and controlled tests. Use for 亚马逊本土化营销, listing翻译, 广告翻译, 多语言关键词, 日德法意西文案, creative translation, keyword localization, 非美国站拓词, culture-to-conversion, or converting the authorized localization course into an approval-ready localization brief. Do not treat literal translation, AI output, or historical tool claims as publishable content; verify current marketplace rules and require native/fact/policy review before release.
Build a human-governed global Amazon growth roadmap that connects AI-assisted insights, product/listing/localization/operations workflows, marketplace sequencing, and a verified opportunity calendar. Use for 亚马逊全球开店趋势, 跨境电商AI转型, AI智能体工作流, 全球站点布局, 节日商机日历, 复活节/樱花季/地球日/墨西哥儿童节, operator-to-decision-maker transition, or converting the authorized 2026 whitepaper and April poster into a measurable plan. Treat trend statistics, cases, dates, tools, and opportunity lists as snapshots; never automate protected business writes without explicit human approval.
Diagnose and plan Amazon US apparel advertising with an ASIN lifecycle playbook covering long-lifecycle, short-lifecycle, and seasonal products. Use for 美国站服饰广告投放, 女装/内衣/泳装/西装/配饰广告打法, ASIN 生命周期判断, 服饰非标品找词, 广告预算结构, 旺季预热与淡季保温, 主身份/标签/流量池诊断, ACOS 高, 点击高不转化, 大词首页不转化, 断货后重启, SB/SBV/SPV/SD/商品投放组合, 否词与复盘. Default to analysis and draft; do not mutate live campaigns without explicit human approval.
Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell, upsell, self-defense, negative targeting, placement analysis, and single-variable experiments. Use for 商品投放, ASIN 定向, 品类定向, Product Targeting, 关键词引流遇到瓶颈, 关联流量, 互补品/替代品, 竞品详情页抢流量, 自家 ASIN 防御, Best Sellers/New Releases 候选, 自动与手动广告联动, or the local file named 如何提升关键词引流效率. Default to research and draft; verify current marketplace capabilities and never mutate live campaigns without explicit human approval.
Filter, interpret, and turn the authorized 2025 Amazon Prime Day advertising insight records into a qualified event plan without averaging incompatible slices or treating historical benchmarks as forecasts. Use for Prime Day/会员日广告规划, 旺季预算, ROAS/DPV/Units/Sales benchmark, marketplace insight lookup, Sponsored Ads/SP/SB/Display mix, event baseline comparison, preheat/peak/tail plan, or querying the included 116-row insight dataset. Default to analysis and draft; verify the current event dates, eligibility, policies, inventory, economics, and account data before any live change.
Diagnose and plan Amazon UK apparel advertising with UK-specific consumer behavior, seasonality, compliance gates, and ASIN lifecycle playbooks for long-lifecycle, short-lifecycle, and seasonal products. Use for 英国站服饰广告, UK apparel ads, 睡衣/泳衣/外套投放, ASIN 生命周期判断, Black Friday/Boxing Day 节奏, UK/EU 尺码, 品牌推广与视频, 季节性预算日历, 退货率与广告利润, ACOS/ROAS 诊断, 复购再营销, 或根据《亚马逊英国站服饰品类广告运营手册》输出可审批的投放方案. Default to analysis and draft; do not mutate live campaigns without explicit human approval.
Manage Amazon ads at the whole-ASIN level before pruning individual targets, separating multi-touch traffic contribution from genuinely irrelevant queries and product-page conversion gaps. Use for 为什么只留出单词后订单更少、自动词移出后变差、整体广告怎么调、词级归因误判.
Plan, review, diagnose, and safely launch Amazon Sponsored Products video-format ads (SP video/SPV), including eligibility, video briefs, policy checks, ASIN and thumbnail mapping, bid adjustments, measurement, and controlled tests. Use for 商品推广视频, SPV, Sponsored Products video, 静音商品视频, 搜索结果视频素材, 视频竞价加成, 3–5条视频测试, video CTR/CVR/ACOS, or converting the authorized SPV intro, shooting, and syndication materials into an approval-ready plan. Treat all specs and availability as source snapshots until verified in the current marketplace and console; never upload or change live ads without explicit approval.
Design Amazon ad architecture around product searchability, query intent, ASIN substitutability, placements, and evidence quality while separating architecture from conversion root causes. Use for 广告架构怎么搭、有精准词或泛词怎么分、无关键词产品、自动和ASIN投放. Not for blaming architecture for every conversion issue.
Review Amazon ad performance as a time sequence and explain how bid, placement, click velocity, conversion, and contribution profit changed after each intervention. Use for 广告日报复盘、调价后为什么变好或变差、点击速度分析、ACOS变化归因. Do not use for isolated one-day judgments.
Diagnose Amazon ad conversion that declines, stays weak, or fluctuates by separating placement expansion, price-value fit, query relevance, product-page differentiation, and market events. Use for 广告转化越来越差、一直不出单、转化忽高忽低、点击增加但订单不增. Do not use to make live campaign changes without approval.
Optimize Amazon ads in an attribution-safe order: placement allocation first, irrelevant-query controls second, and target-level bid changes last. Use for 先调广告位还是先否词、竞价越调越乱、商品页流量差、搜索词清理. Do not apply negatives mechanically.
Route an Amazon product into precise-attribute, broad-intent, or no-clear-keyword advertising structures based on product truth, search behavior, conversion, and unit economics. Use for 不同产品怎么选广告打法、服装多变体、泛流量品、无明确关键词产品、保守或进攻策略.
Claude Skills — questions
Answers built from the skills we actually parsed.