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. 79 566 files from 1 758 authors, of which 61 913 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.
Use when the user wants to prepare for one or more upcoming meetings with customers, prospects, partners, accounts, or important stakeholders; requests daily or date-based meeting preparation; asks to organize a same-day customer call queue; asks for the most important qualifying meeting of the day; or identifies meetings only by company, attendee, topic, or date. Produce an individual meeting brief or a chronological multi-meeting agenda as appropriate.
Use when the user wants forecast posture, forecast accuracy, commit, upside, forecast-call preparation, or a pipeline or deal-risk review for a seller book, team, period, report, or named deal set. Produce a manager-ready forecast rollup, risk posture, recommendation changes, evidence gaps, and follow-up actions.
Use when the user wants to understand how a sales or customer-facing rep's call behavior is changing over time. Produce an evidence-backed trend readout with improvements, regressions, stable patterns, coaching actions, and calls to re-listen.
Use only when a focused Sales workflow has selected a present and connected ZoomInfo connector, or the user explicitly asks for ZoomInfo company search, contact search, enrichment, intent, similarity, recommendations, or research. Do not use when another enrichment source is selected.
Research companies, partners, and referral channels to shape draft outreach approaches, messages, or partner motions; exclude descriptive company profiling, list enrichment, and internal source finding.
Use when a focused Sales workflow needs Salesforce-backed CRM reads, links, drafts, notes, account plans, Agentforce assignments, or explicitly requested Salesforce connector/query guidance. Do not use for generic CRM app construction or when another CRM is authoritative.
Use when the user asks which existing accounts to work now, which leads are hottest in a grounded list or pipeline, how to rank a territory, book, pipeline, ICP list, or account list, where to focus this week, or what rep-ready next actions to take. Prioritize accounts using current evidence, suppress or account for in-flight motion, and identify reachable contacts when supported. Use enrichment instead for net-new company discovery or missing-data completion.
Clone a live URL as a runnable frontend-only local app.
Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the `browser-harness-js` CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP `Session`, and every call (`browser-harness-js 'await session.Page.navigate(...)'`) executes against the same persistent connection. Session, active target, and globals survive across calls. Use when the user wants to automate, script, or inspect a Chrome browser via CDP — single tab or multi-tab, attach to existing Chrome or to a new one launched with --remote-debugging-port.
Reverse-engineer the hook formula from a viral LinkedIn post URL. Returns which of the 16 canonical 2026 formulas it uses (anaphora, R.I.P., year-pivot, time-anchor, curiosity-gap, contrarian, comment-gate, emotional cold-open, named-gratitude, and 7 more), why it worked, and a blank template. Use to learn from a competitor's post, not to write your own (use linkedin-post-writer).
Stand up and run a LinkedIn employee advocacy program for a marketing or sales team. Covers 14-day launch playbook, brand-guideline governance, per-post time budget, cadence benchmarks, and team ROI (reach, engagement, pipeline). Triggers on "employee advocacy", "get the team posting", "scale LinkedIn across team", "advocacy ROI".
Draft a LinkedIn comment on someone else's post from its URL, or reshare (repost) it to your feed with optional commentary. Use when the user pastes a post URL and asks to comment, engage, be first commenter, or repost with their thoughts. Produces 1-3 variants in the user's voice, picks a reaction, and publishes via Publora on approval. Not for replying to existing comments (use linkedin-reply-handler).
Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post.
Scrub AI tells from any text draft OR audit a finished post against the 2026 algorithm heuristic checklist. Tier-based rewriter (forensic / strict / aesthetic / all) plus `--mode audit` for detection-only pass-fail review covering length, hook, CTA, format penalties, AI vocab. Also `--mode profile` builds a reusable Voice and Brand Profile from a few of the user's real posts, so every writing skill drafts in their voice. Sub-tools: emoji-pattern detector, multi-detector spread tester (GPTZero, Originality.ai, ZeroGPT, Sapling, Copyleaks), rule explainer. Triggers on "humanize", "de-AI", "review this draft", "audit before posting", "is this ready", "build my voice profile", "learn my voice".
Draft a new LinkedIn post from scratch using one of 16 2026 hook formulas (anaphora, R.I.P., year-pivot, time-anchor, curiosity-gap, contrarian, emotional cold-open, named-gratitude, and more), picked by engagement goal (comments, reposts, likes, saves). Runs the humanizer pass and schedules via Publora on approval. Use when the user asks to write a post, needs a hook, or wants a proven format. Not for reviewing existing drafts (use linkedin-humanizer --mode audit).
Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the Publora API for publishing. User provides post/comment URLs, skill drafts content, user approves, then publishes.
Pull the people who liked or commented on any LinkedIn post and segment them by ICP fit (peer / aspirational / prospect / other). Produces an engager roster, tier breakdown, and outbound action lists (follow back, comment-drop, DM-able with one-line openers). Powered by Apify, no LinkedIn login. Triggers on "who liked my post", "who engaged", "engagers report", "audience analytics". Not for tracking author replies to your comments (use linkedin-thread-monitor).
Repurpose existing content into a native LinkedIn post. Take a tweet, thread, YouTube video, blog, or newsletter and rebuild it for LinkedIn: re-hook before the fold, expand to the 900 to 1300 char sweet spot, add whitespace and a CTA, move links to the first comment, run the humanizer, publish via Publora on approval. Not for writing from scratch (use linkedin-post-writer), not for auditing a draft (use linkedin-humanizer --mode audit).
Audit and rewrite a LinkedIn profile end-to-end for 2026: headline, About 7-step, Featured, banner, photo, Experience metrics, Skills, custom URL, recommendations. Triggers on "review my profile", "rewrite my headline", "fix my About", "optimize banner", "profile audit", "LinkedIn bio". Converts resume-style profiles to ones that convert 3-5x better.
Draft a reply to a specific existing LinkedIn comment from its URL. Use when the user wants to reply to a comment on any post, or follow up after an author replied to them. Parses the commentUrn, resolves the correct parentComment target (LinkedIn flattens threads to 2 levels), and posts via Publora on approval. Not for top-level comments (use linkedin-comment-drafter).
Track which of your LinkedIn comments earned author replies. Flags the 6-24h warm-reply window where thread momentum peaks, classifies threads as hot/warm/cool/dormant, and routes warm ones to linkedin-reply-handler for follow-up drafts. Powered by Apify, no LinkedIn login. Triggers on "what threads need follow-up", "author replied", "monitor my comments". Not for analyzing likers on a post (use linkedin-engager-analytics).
| Orchestration spine and "what do I do next?" router for the BMAD Planning & Orchestrator plugin. Detects current planning state by scanning the output folder for which artifacts exist (project-context.md, decision-log.md, product-brief, prd/tech-spec, architecture, ux, epics, stories), infers the current phase and track, then recommends the next BMAD skill to run — skipping optional phases (Analysis is always optional; UX only when there is a UI). Use when the user asks "what's next", "what do I do next", "where am I", "what's my status", "continue", "resume planning", "which skill should I run", "what BMAD step is next", or types "/bmad-help" / "/status". Auto-invoke at the start of any BMAD planning session to orient. This skill ROUTES only — it never writes planning documents itself.
| Emits a dev-tool-agnostic handoff manifest from ready-for-dev stories so an external dev plugin or runner can pick up and execute the work. Use when the user says "generate a handoff", "create handoff manifest", "export stories for dev", "hand off to dev tool", "produce handoff manifest", "ready to hand off", "prepare handoff for external tool", "export ready-for-dev stories", or "create the handoff package". Also trigger when the user asks "what stories are ready for dev?" and wants an exportable artifact rather than a status report. path, status, owned file/module scope, wave/parallel_set, dependencies, acceptance-criteria summary, locked-sections note, and a schemaVersion field. See REFERENCE.md (bundled) for the full manifest schema and adapter notes for git-worktree parallel development and autonomous dependency-graph orchestrators.
|
| Solutioning skill (Winston, the Architect). Produces architecture.md with ADRs and systematic NFR coverage, mapping every FR/NFR from the PRD to a concrete design decision. ONE architecture forces all future parallel dev agents to share the same API style, data model, state management, naming conventions, and security approach — catching alignment here is 10x cheaper than during implementation. Use when the user says "design the architecture", "create architecture", "/architecture", "solutioning", "tech stack", "system design", "ADR", "architecture decision record", "data model", "API design", "NFR coverage", "non-functional requirements", or after a PRD is done and they ask "what's next" / "ready for solutioning". Supports Create (new architecture.md), Update (revise against PRD changes), and Validate (check coverage + ADR completeness). PLANS only — never writes application code, runs tests, lints, or builds.
| Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas (add techniques or deepen coverage), Validate (confirm insights align with project goals). "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.
| BROWNFIELD planning input. Scans an existing codebase READ-ONLY and writes project-documentation.md — ground truth for stack, structure, key flows, conventions, and integration points — so downstream BMAD planning skills start from reality. Does NOT modify code; produces only the doc artifact. "document my app", "scan the existing code", "brownfield planning", "we have existing code, start planning", "map what's already built", "document current state", "capture the current architecture", "understand the existing system before planning", "write project-documentation.md", or before a PRD or architecture doc when the user already has code written. Validate (check completeness). Plans only — reads code but never writes it, runs no tests, no linters, no build tools, no application code.
| Solutioning flagship — shards a PRD + architecture into epics.md and individual {epic}.{story}.{slug}.story.md context objects, the LAST planning artifact before Dev Notes with SOURCE CITATIONS back to prd.md/architecture.md, Acceptance Criteria, Tasks/Subtasks mapped to ACs, Testing strategy, Dependency Maps, an explicit Owned File/Module Scope list (the lever for parallel-conflict-free scheduling), and Learnings from Previous Stories. Sized to one dev-day; split if larger; NO story points. Use when the user says "shard the PRD", "create epics", "break the PRD into epics", "break this epic into stories", "create stories", "create a story", "draft story files", "generate the story for X", "prepare stories for dev", "mark the story ready for dev", epics/stories, Update an existing story, or Validate a draft against the contract.
| CROSS-PHASE mid-stream scope correction. Re-enters planning when requirements, features, architecture, or constraints change after planning has started. Re-shards affected epics/stories, re-sequences sprint-status.yaml, appends rationale to decision-log.md. Routes to bmad-epics-and-stories, bmad-sprint-planning, or bmad-parallel-plan as needed. Changes the PLAN, never code. "we're dropping feature X", "we need to pivot", "re-plan after the change", "requirements changed mid-sprint", "correct course", "architecture changed", "re-scope the backlog", "update epics after feedback", "cancel story X", "add epic for Y", "change the plan", "we got new constraints", or when stories are split/merged/reordered due to a decision not in the original plan. sprint-status.yaml, new decision-log.md entry. NEVER writes code or runs tests.
| BMad Method / Enterprise) interactively, then scaffold the output folder, a config file, an empty decision-log.md, and a project-context.md "constitution". Use when the user says "initialize BMAD", "set up BMAD", "start a new BMAD project", "scaffold the planning workspace", "bmad init", "create the bmad config", or is beginning planning and has no bmad-output/ folder yet. Also use when the user asks "which track should I use?" or "what scale is my project?". This is the FIRST skill to run before any other planning workflow (brief, PRD, architecture, stories).
| symptoms, evidence (graded A/B/C by confidence), ranked hypotheses, suspected components, and a recommended planning response. INVESTIGATES and DOCUMENTS only — does NOT fix code, run tests, or implement. Hands off as a story to an external dev tool. Validate (check draft for completeness before handoff). Output lands in bmad-output/; a fix story is drafted on handoff.
| Turns a sequential, ready-for-dev story backlog into conflict-free CONCURRENT WAVES. Builds a dependency DAG from epic order, per-story dependency maps, and Owned File/Module Scope overlaps, then topologically sorts it into parallel waves of mutually disjoint, dependency-satisfied stories (capped by maxParallel), and emits a parallelization-plan.md with per-story git-worktree branch names and an ordered merge sequence. Use when the user says "plan parallel work", "which stories can run in parallel", "parallelize the backlog", "build the wave plan", "parallelization plan", "conflict-free workstreams", "what can we run concurrently", "split into worktrees", "dependency graph for the stories", "merge order", or "how do I fan this backlog out to multiple dev agents". Run AFTER stories are ready-for-dev (scrum-master) and an architecture exists. This skill PLANS parallelism only — it does NOT run agents, spawn worktrees, write code, run tests, or perform git operations.
|
| SOLUTIONING GATE — validates cohesion across planning artifacts before any implementation begins. Cross-references PRD (or tech-spec), architecture document, and epics/stories for coverage consistency and missing pieces. Returns a verdict of PASS, CONCERNS, or FAIL with specifics. Does NOT touch code. (PRD + architecture + epics), and Enterprise (all of the above + optional security/DevOps addenda).
| external FAQs that stress-test a product concept before any building begins. Produces prfaq.md in the configured output folder. "future press release", "stress-test the concept", "validate the idea before building", "internal FAQ", "external FAQ", "Amazon-style product brief", or "PRFAQ for [product/feature]". Also use when someone wants to clarify or update an existing PRFAQ, or validate a draft against the Working-Backwards
| Conducts market, competitive, domain, and technical research using live web sources, producing a cited research-report.md to inform BMAD planning decisions. sources), Validate (cross-check claims in an existing report against live sources). Output lands in bmad-output/ as a cited research-report.md ready for downstream planning skills (business-analyst, product-manager, system-architect).
| Lean facilitator for creating, updating, and validating a product brief — the Analysis-phase foundation of the BMAD Method. Captures problem statement, target users, core features, goals, constraints, and success metrics. "let's do discovery", "help me define my product", "what problem are we solving", "capture our product vision", "update the product brief", "validate the brief", "check if the brief is complete", "run discovery", "start a product brief", "brainstorm the product", or "I want to plan a product". Output is a planning artifact only — no code is written or run.
| sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.
| Solutioning-phase UX planning skill (optional; activate when the project has a UI). palette, typography, spacing, component specs, WCAG 2.1 AA contract) and EXPERIENCE.md (user journeys, flow diagrams, screen states, error/empty/loading handling). Use when the user says "design the UX", "create UX planning docs", "define the design system", "map the user flows", "UX for this feature", "wireframe the flows", "what are the user journeys", "accessibility design", "WCAG compliance", "design tokens", "responsive design plan", "mobile-first design", or "create DESIGN.md / EXPERIENCE.md". Runs after architecture is drafted and before stories are created. Supports Create / Update / Validate intents.
| Quick Flow lightweight technical specification for small-scope work (1-15 stories). Replaces the full PRD + architecture pair when scope is small and requirements are clear. Produces bmad-output/tech-spec.md as the single planning artifact before story creation. "I need a tech spec for this feature", "quick spec", "small project spec", "we don't need a full PRD", "just a tech spec", "spec out this change", "document this feature". QUICK FLOW TRACK ONLY (1-15 stories). If scope grows beyond ~15 stories or involves multiple teams / external integrations at scale, stop and redirect to bmad-prd + bmad-architecture instead — those skills are built for that complexity. Validate (review a draft for completeness against BMAD criteria).
| Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any Constraints, Non-Goals, Success Metrics. Use when the user says "create a spec", "write a spec for", "distill this into a spec", "I have a brain dump", "turn this into something structured", "clean up these notes", "make a SPEC from", "I want to define the problem", "help me scope this", "summarize what we're building", "I have a PRD but need a kernel", "what are we actually solving?", or drops raw text/transcript and asks for structure. Also use when starting any new initiative and a clean shared definition is missing.
Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and more — without manual paste. Use when the user wants a colleague skill, digital twin of a coworker, or capture of someone's technical voice from workplace systems. Requires tool_connections + 10xProductivity verified_connections (or equivalent .env).
> Operate the 10xProductivity assistant inbox workflow. Use when running or debugging 10x-host, Slack self-DM polling, macOS notification triggers, scheduling runtime, or trigger-to-workflow routing.
Automated LinkedIn engagement workflow. The agent finds a relevant post on your chosen topic, drafts a comment with a genuine insight, gets your approval in chat, and posts it — all in one loop. You approve once before anything is posted. Use when asked to "engage on LinkedIn", "find a post to comment on", "post a LinkedIn comment", or "engage on [topic]". Requires LinkedIn session credentials in .env. Everything runs locally — credentials never leave your machine.
Walk through a UI flow once manually and capture a durable interaction map — which DOM elements to click, which network requests they trigger, and what field shapes they expose. Produces a reusable selector+endpoint reference for automation scripts. Use before writing any browser automation block for a JS-heavy SPA, design app, productivity app, or internal portal where selectors and API paths are not obvious from source inspection alone. Modes include Agent Browser for low-token interactive reconnaissance, Chrome DevTools Recorder, Playwright observer, and Playwright codegen+trace.
Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and more — without manual paste. Use when the user wants a colleague skill, digital twin of a coworker, or capture of someone's technical voice from workplace systems. Requires tool_connections + 10xProductivity verified_connections (or equivalent .env).
Design and build automation workflows using building blocks — clarify outcomes, decompose by dependencies, reuse prior art, verify each block before chaining, and research when stuck. Covers generic divide-and-conquer (problem framing, observable surfaces, investigation vs shipping, CLI contracts) plus human-like pacing for social and communication platforms. Use when automating multi-step processes across tools or platforms.
Design and build automation workflows using building blocks — clarify outcomes, decompose by dependencies, reuse prior art, verify each block before chaining, and research when stuck. Covers generic divide-and-conquer (problem framing, observable surfaces, investigation vs shipping, CLI contracts) plus human-like pacing for social and communication platforms. Use when automating multi-step processes across tools or platforms.
Walk through a UI flow once manually and capture a durable interaction map — which DOM elements to click, which network requests they trigger, and what field shapes they expose. Produces a reusable selector+endpoint reference for automation scripts. Use before writing any browser automation block for a JS-heavy SPA, design app, productivity app, or internal portal where selectors and API paths are not obvious from source inspection alone. Modes include Agent Browser for low-token interactive reconnaissance, Chrome DevTools Recorder, Playwright observer, and Playwright codegen+trace.
Automated LinkedIn engagement workflow. The agent finds a relevant post on your chosen topic, drafts a comment with a genuine insight, gets your approval in chat, and posts it — all in one loop. You approve once before anything is posted. Use when asked to "engage on LinkedIn", "find a post to comment on", "post a LinkedIn comment", or "engage on [topic]". Requires LinkedIn session credentials in .env. Everything runs locally — credentials never leave your machine.
> Search your entire company's institutional knowledge in one query — Slack, Confluence, Jira, Linear, Notion, GitHub, plus any AI or multi-source search tool listed in verified_connections.md. Follow workflows/enterprise-search. One question, every connected tool, synthesized answer in seconds. No tab switching. No copy-paste. Use when the user asks about a decision, an incident, a topic, a person, a past discussion, or anything that might be documented "what was the decision about", "is there a doc on", "any Slack about".
Connect any tool you use at work to your agent — including internal company tools, custom-built systems, deployment portals, incident trackers, internal knowledge bases, HR systems, and commercial tools like Slack, Confluence, Jira, Linear, GitHub, Outlook, Datadog, and PagerDuty. Use when the user wants to set up a tool connection, connect an internal or custom-built tool, or add a new tool integration from scratch.
>- Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube link defaults to saving a note.
公众号运营｜微信公众号｜公众号一条龙｜公众号全流程｜自媒体运营｜wechat automation｜content pipeline｜AIGC workflow — 公众号一条龙运营总控入口，选题→写稿→审稿→排版→配图→发布串联 8 个子 skill，单条指令完成整篇图文从 0 到上架。面向公众号小编、自媒体、品牌内容。触发词分层：**一条龙流程**「一条龙」「完整流程」「从头做」「从 0 到发布」；**新做新发**「帮我写篇公众号文章」「做一篇公众号文章」「我想发一篇」「帮我发一篇」「再来一篇」；**选题起点**「今天写什么好」「有什么好写的」「找个话题」「爆款选题」「热点选题」「起个爆款标题」；**策划起点**「内容日历」「系列策划」「专栏规划」「连载」；**流程恢复**「接着上次那篇」「继续昨天的」「继续上次的」「接着之前的进度」；**显式模型新写**「用 GPT 写一篇」「用 DeepSeek 写一篇」「把提纲写成文章」。子 skill（topics/writing/review/formatting/images/publish/sticker/assets）单独触发仅限对**已有产物**的修改场景（如"改标题""润色这段""排版""审稿""加封面""发布"）；新做/策划/多环节串联一律走本入口。
公众号排版｜Markdown 转 HTML｜排版主题｜段落样式 — 公众号一键排版工具，Markdown 文稿转微信后台可粘贴 HTML，多主题、多字号、段落样式切换，所见即所得。面向公众号编辑、独立作者、排版岗。触发词：「排版」「版式」「美化」「格式化」「字号」「段落样式」「换个排版主题」「换个版式」「转 HTML」「弄好看点」「调整格式」。换预设包/品牌包/整套主题配色请走 aws-wechat-article-assets；需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。
公众号素材｜业务资料库｜预设包｜.aws 预设包｜主题包｜品牌包｜aiworkskills.cn — 用户业务资料库与预设包管理：业务资料按产品名组织在 `.aws-article/products/{产品名}/`（介绍 .md 直挂产品根 + 配图归 `images/` 子目录含同名说明 .md），AI 与用户对话产出业务介绍内容时引导用户保存；图片入库走 `product_image_ingest.py --product <产品名> --stem <中文名>`。导入 .aws ZIP 预设包（本地文件或 `https://aiworkskills.cn/**/*.aws` URL）合并主题/配色/字体配置到 `.aws-article/presets/`；`config.yaml` 仅本地不存在时从包内复制，已存在则 stdout 输出差异 JSON 不覆盖。面向内容运营、品牌团队、设计支持岗。触发词：「素材库入库」「stock images」「上传图到素材库」「.aws」「预设包」「导入预设」「主题包」「aiworkskills.cn 链接」「.aws 下载地址」。
公众号审稿｜公众号校对｜敏感词检测｜内容合规 — 公众号发布前合规审查：敏感词扫描、错别字检测、政治合规、平台规范校验，一次性输出修改清单。面向公众号编辑、自媒体作者、合规岗。触发词：「审稿」「审核」「校对」「合规」「敏感词」「错别字」「稿子检查一下」「稿子帮我看看」「稿子写完了」「文章检查一下」「检查下有没有问题」「能不能发」「发布前检查」。需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。
公众号封面｜公众号配图｜公众号插图｜AI 生图 — 公众号 AI 封面与配图生成，按文章标题与内容自动匹配画风，一稿多方案，多风格预设可复用。面向公众号编辑、自媒体、品牌设计。触发词：「封面」「配图」「插图」「生成图片」「给文章加图」「做个封面」「文章插图」「配个图」。不写正文只发一组图请走 aws-wechat-sticker；需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。
公众号写稿｜长文写作｜文章润色｜改写续写 — 公众号长文 AI 写作，从话题或提纲生成完整初稿，支持改写、续写、润色、开头结尾优化，可调 DeepSeek / GPT / Claude 或由 Agent 代写。面向自媒体作者、公众号运营、品牌文案。触发词（**单独触发仅限对已有稿子的修改**）：「改写」「润色」「续写」「续一段」「往下写」「接着这段写」「重写开头」「改结尾」「调整语气」「这段润色下」「把这段改活泼点」「优化用词」「用 GPT 重写」「用 DeepSeek 重写」。新写一篇请走 aws-wechat-article-main（main 内部会调用本 skill 生成初稿）；需要多环节串联（写+审+排+配图+发）也走 main。
Claude Skills — questions
Answers built from the skills we actually parsed.