When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but don't use the product," "time to value," or "first session experience." Use this whenever users are signing up but not sticking around. For signup/registration optimization, see signup. For ongoing email sequences, see emails.

When the user needs a comprehensive marketing plan for a client, a company they advise, or their own product. Also use when the user mentions "marketing plan," "growth plan," "GTM plan," "go-to-market plan," "AARRR plan," "90-day marketing plan," "12-month marketing roadmap," "fractional CMO plan," "fCMO plan," "market sizing," "TAM SAM SOM," "how big is this market," or "market research." Generates an exhaustive 13-section plan structured by AARRR (Acquisition, Activation, Retention, Referral, Revenue), customized to the client's current budget, team, and stage, mapped to future funding milestones, cross-referenced with the 139-idea marketing-ideas library and an embedded 17-section current-state audit rubric, with a marketing operations stack showing which skills and MCP/API integrations execute each part. Outputs a Notion-paste-ready markdown document. For positioning and ICP context before planning, see product-marketing. For stage-specific deep work, see onboarding, signup, emails, referrals, pricing.

Designs customer interviews and turns the transcripts into decisions. Produces an interview guide plus a synthesis (forces of progress, jobs, pathways, opportunities) you can paste into a doc. Use for 'customer interviews', 'discovery calls', 'JTBD', 'switch interview', 'who should I talk to', 'how many interviews', 'synthesize these transcripts', or 'why do customers churn/buy'. Draws on 140 Lenny's Podcast guests incl. Teresa Torres, Bob Moesta and Judd Antin.

Pick the single highest-priority unresolved Sentry issue and hand it off to a fixer skill. Use when triaging Sentry errors, running automated issue triage, or when asked to fix the top Sentry issue in a project.

Use this skill to guide a developer or designer through a BRAVE framework breakdown of a task before they start work. Trigger whenever someone wants to think through a ticket, break down a card, plan their approach before starting, validate a task before picking it up, or prepare a breakdown to share with a teammate or client. Also trigger for any of these phrases or close variations: "BRAVE this", "brave it", "break down this card", "think through this ticket", "help me plan this out before I start", "want to make sure I understand this before I start coding", "want to revalidate this card", "help me think through this before my standup/meeting", or "I'm about to pick up a card and want to break it down". If someone mentions starting work on a card and wants help planning, validating, or understanding it first — this skill should run.

张雪峰的思维框架与表达方式。基于5本著作、15+篇权威媒体深度采访、 30+条一手语录、11个关键决策记录和完整人生时间线的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用张雪峰的视角分析教育选择、职业规划、阶层流动等问题。 当用户提到「用张雪峰的视角」「张雪峰会怎么看」「张雪峰模式」「雪峰视角」时使用。 即使用户只是说「帮我用张雪峰的角度想想」「如果张雪峰会怎么说」「切换到张雪峰」也应触发。

Audit codebases or Git changes for engineering risks and repository health using concrete evidence, coverage limits, and prioritized fixes. Use for comprehensive audits, focused quality or security reviews, and incremental PR audits. Ordinary feature implementation and quick code explanations do not need this skill.

Assess and address review feedback on GitHub PRs, GitLab MRs, or in conversation. Use when checking new reviews, responding to comments, rechecking after a push, or following up on approvals and change requests.

Generate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts — for justifying Claude Code usage/spend to a manager, self-review, or "what have I been using this for" check-ins. Mines ~/.claude/projects locally (no extra API calls beyond one final write-up), cross-references local git history, and writes a markdown report plus a self-contained HTML receipt to your home directory. Use when the user asks for "receipts", an "impact report", "usage report", wants to "show my Claude Code activity", "prove the value of Claude Code", or runs `/receipts`.

Implement Server-Sent Events streaming from Cloudflare Workers to browser clients with reconnection, state persistence, and progress tracking. Use when building "SSE streaming", "real-time updates", "server push", or "event streaming".

Force an AI work thread to be actively tracked on the thread registry/board even if the auto-classifier left it in Funnel / Triage or marked it wait-for-threshold. Use when a session matters but did not trip the automatic tracking heuristics.

Run one-shot multi-AI fleet dispatch with quintet — fan a single prompt to several coding-agent CLIs (claude/codex/agy/copilot/qwen/opencode) in parallel, run a two-round cross-model debate, or get a multi-model code review, with circuit-breaker and fallback reliability. Use proactively when fanning a prompt out to several models, when running an AI debate, when seeking consensus, or for reviewing a diff across models. Trigger on "quintet fleet", "AI debate", "run a debate between models", "consult the models", "get consensus from the models", "multi-model review", "what do all the models think". Not for parallel file-editing work — use quintet-team-runtime.

Review fetched papers and write evidence-based recommendations with reading priorities. English triggers: "review fetched papers", "generate paper recommendations". This is pipeline stage 2. 论文点评（3 步流水线的第 2 步）。读取富化后的论文数据，扫描笔记库，生成有态度的推荐点评， 保存推荐文件到 Obsidian，更新 history；git 自动化默认关闭。 触发词："论文点评"、"跑一下论文点评"

Fetch, rank, and enrich recent arXiv and Hugging Face papers. English triggers: "fetch papers", "fetch papers from the last three days". This is pipeline stage 1. 论文抓取（3 步流水线的第 1 步）。抓取 arXiv + HuggingFace 最新论文，打分筛选，富化信息， 输出 daily_papers_enriched.json 到共享临时目录，供后续 skill 使用。 触发词："论文抓取"、"跑一下论文抓取" 支持多天模式："过去3天论文推荐"、"过去一周论文推荐"、"过去一周的论文"、"抓 3 天的论文"、"最近5天"

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending LLM platform support. Do NOT use for fixing bugs in existing providers, modifying existing provider behavior, or changing the LLMProvider interface.

Migrate an existing Django API from Django REST Framework to django-modern-rest while preserving routes, request/response contracts, auth, permissions, throttling, pagination, and test coverage. Use when replacing APIView/ViewSet/GenericAPIView and DRF serializers/routers with dmr controllers/routers and typed DTOs.

Send one of the user's own Minutes meetings to their X1 household for review. Use when the user wants a meeting's summary, decisions, action items, and open questions to reach X1 so they can confirm what belongs in their household record. X1 asks the user to approve the send, and nothing reaches the household record until they confirm each item. Never use it for a restricted meeting, a transcript, or someone else's meeting.

Send one of the user's own Minutes meetings to their X1 household for review. Use when the user wants a meeting's summary, decisions, action items, and open questions to reach X1 so they can confirm what belongs in their household record. X1 asks the user to approve the send, and nothing reaches the household record until they confirm each item. Never use it for a restricted meeting, a transcript, or someone else's meeting.

Prepare a sourced Minutes meeting outcome for human-governed closeout of existing X1 work. Use when the user wants a meeting decision or commitment to close, defer, escalate, or retire a specific X1 coordination thread. Never use it to infer settlement, move money, contact anyone, or close X1 work automatically.

Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag configurations between environments. Use when the user wants to change who sees a flag, roll out to a percentage, add targeting rules, or promote config between environments.