Claude Skills by yanacuti1121

When the user wants to write an email to an investor — cold outreach, warm intro request, follow-up after a meeting, monthly investor update, or thank-you note. Also activates for "intro email", "investor email", "follow up with VC", or "investor update".

When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.

When the user wants to identify, evaluate, or prioritize potential investors for a fundraising round. Also activates when the user asks "who should I pitch?", "find me investors", "build an investor list", or mentions VC/angel targeting.

When the user needs to write, review, or improve a job posting for a startup role.

When the user needs to create, critique, or optimize a landing page for conversion -- including headline rewrites, CTA placement, layout restructuring, or full page copy drafts.

When the user needs to plan or execute a product launch — including pre-launch content sequences, launch funnels, JV/affiliate launches, cart open/close strategy, or evergreen launch funnels.

When a founder needs to qualify inbound leads, define their ICP, build a lead scoring model, set MQL criteria, or route prospects through pipeline stages. Activate when the user mentions lead scoring, ICP, MQL, SQL, lead qualification, inbound leads, or pipeline design.

When the user needs to estimate market size, understand market dynamics, or validate that a market opportunity is large enough to pursue.

When the user needs to decide what to build, cut, and defer for a first release or minimum viable version of a product or feature.

When the user needs to design, improve, or audit a post-signup activation flow to get new users to their first value moment. Activate when activation is lagging, time-to-value feels excessive, or first sessions lack impact.

When a founder needs to write partnership or BD emails, craft integration pitches, or create co-marketing proposals. Activate when the user mentions partnerships, business development, integration proposals, co-marketing, channel partnerships, or strategic alliances.

When the user wants to create, review, or restructure a fundraising pitch deck for seed or Series A. Also activates when the user mentions "deck", "pitch", "investor presentation", or "slide structure".

When the user needs to define a product feature, write a product requirements document, or translate an idea into a structured spec.

When the user needs to draft, review, or update a privacy policy for their product, or needs to understand data privacy obligations across jurisdictions.

When the user needs to create SOPs, playbooks, runbooks, or other operational documentation that defines how a recurring process should be executed.

When a founder needs to create a sales proposal, statement of work, contract, NDA, or master service agreement. Activate when the user mentions proposal, SOW, quote, contract, NDA, MSA, or needs to formalize a deal.

When the user wants to research customer pain points, complaints, or sentiment using review platforms like Trustpilot, G2, Capterra, or app stores. Also use when the user mentions "what are users saying", "competitor reviews", "pain points", or "voice of customer research".

When the user needs to organize product initiatives into a prioritized, time-sequenced plan with outcomes and dependencies.

When a founder needs demo scripts, discovery call frameworks, objection handling, RFP/RFI responses, competitive feature matrices, POC planning, or closing playbooks. Activate for sales calls, demo prep, talk tracks, bid responses, competitor comparisons, or pre-sales engineering.

When the user needs a security assessment — threat modeling, vulnerability review, auth flow audit, dependency scanning, or says "is this secure", "review for vulnerabilities", "threat model", "security audit", "pen test prep".

When the user wants to monitor reviews, mentions, and community sentiment about their own product. Also use when the user mentions "track our reviews", "what are people saying about us", "brand monitoring", "reputation management", or "review alerts".

When the user needs a technical SEO audit, on-page optimization guidance, or help resolving crawlability, indexation, or performance issues that affect search rankings.

When the user needs to prepare for SOC 2, build a compliance roadmap, assess security posture, quantify security risk, or says "we need SOC 2", "security audit", "compliance", "enterprise customer wants SOC 2", "CISO advice".

When the user needs to build a LinkedIn authority system, create social content strategy, define content pillars, write posts, or establish thought leadership positioning. Activate on "LinkedIn strategy," "content pillars," "what should I post," or "build my personal brand."

When the user needs to write recruiting outreach messages to attract passive candidates or request referrals.

When the user wants to create or update their startup context document. Also use when the user mentions "set up context", "tell you about my startup", or any other skill needs context that doesn't exist yet.

When the user needs to create help center articles, FAQs, troubleshooting guides, API documentation, or getting-started guides for customers.

When the user needs to choose between technologies, frameworks, or tools — or says "which framework should I use", "compare X vs Y", "should we migrate from X to Y", "what database should I use", "calculate TCO".

When the user needs to draft, review, or update terms of service for their SaaS product or web application.

When the user has raw customer interview transcripts, survey responses, support tickets, or other qualitative data and needs to extract actionable insights.

State machine and durable workflow patterns for AI agents. FSM-driven agent state, XState statecharts, Temporal durable execution, input validation at every transition, and memory-efficient state switches. Sources: statelyai/xstate, jakesgordon/javascript-state-machine, temporalio/temporal, chriso/validator.js, jlongster/fsm-utils.

Choose and implement state management — local state, Zustand, Redux Toolkit, Jotai, React Query/TanStack Query, URL state, and when to use each. Use when asked about "state management", "Zustand", "Redux Toolkit", "RTK", "React Query", "TanStack Query", "Jotai", "server state vs client state", "global state", "state colocation", "useQuery", "useMutation", "optimistic update", "cache invalidation", or "when to use Redux". Do NOT use for: React Server Components state — see nextjs-patterns. Do ...

Selective state persistence with transform filters. redux-persist patterns, blacklist/whitelist keys, migration versioning, custom serialize/deserialize, and ephemeral-vs-durable state separation. Sources: rt2zz/redux-persist.

Real-time metrics streaming via StatsD UDP protocol. Counter, gauge, timer, and set metrics; sampling rates; DogStatsD tags; flush intervals; and integration with Datadog/Graphite dashboards. Sources: besquare/node-statsd, statsd spec.

Use when asked to scrape a bot-protected website, bypass anti-bot detection, run Playwright with stealth patches, automate a site that blocks normal browsers, or simulate human-like browser behavior. Triggers on: 'scrape protected site', 'bypass bot detection', 'stealth playwright', 'anti-bot browser', 'cloudflare bypass', 'captcha avoidance', 'humanized browser', 'fingerprint evasion', 'botasaurus', 'python scraper', 'scraper ui', 'parallel scraping', 'trình duyệt chống phát hiện', 'vượt qua...

Machine Learning for Algorithmic Trading — complete codebase cho cuốn sách ML trading 2nd edition. 18.9K stars.

Detect and eliminate predictable AI writing tells from prose. Use when the user asks to "make this sound less like AI", "remove AI tells", "make it more human", "this sounds robotic", "clean up the writing", "too formal", "sounds generated", or requests a writing/copy review. Do NOT use for code — this skill targets prose, copy, and documentation only.

Cross-environment storage with automatic driver fallback. store.js patterns for browser/Node/Electron environments, storage backend selection, JSON serialization, namespace isolation, and graceful degradation. Sources: marcuswestin/store.js.

Node.js stream pipeline management with automatic cleanup. pump/pipeline error propagation, transform stream chains, backpressure handling, and preventing stream leaks when one stage errors. Sources: mafintosh/pump, Node.js stream.pipeline.

Safely collect stream data into a string or buffer. get-stream patterns, size limits to prevent OOM, encoding handling, binary vs text streams, and timeout guards. Sources: sindresorhus/get-stream.

StreamingLLM attention sink patterns for infinite-context LLM inference. Attention sink tokens, rolling KV cache window, no recomputation on eviction, and enabling agents to process arbitrarily long sessions. Sources: mit-han-lab/streaming-llm (MIT).

Comprehensive string validation for agent inputs and API boundaries. Email, URL, UUID, IP, credit card, hex, base64, JSON, and custom regex validation patterns. Sources: validatorjs/validator.js.

Use when orchestrating multiple subagents with dependencies between them, running agents in parallel, or managing complex multi-agent workflows. Triggers on: 'orchestrate agents', 'chạy song song', 'parallel agents', 'agent dependency', 'subagent graph', 'multi-agent flow', 'agent pipeline', 'which agents can run in parallel', 'agent coordination'.

Persistent memory + RAG + User Profile cho AI agents. #1 LongMemEval benchmark. Thay thế L1/L2 memory thủ công bằng API cloud chuẩn.

Secure the software supply chain — SBOM generation, dependency provenance verification, package integrity (Sigstore/npm provenance), lockfile auditing, typosquatting detection, CI artifact signing, and dependency update policy. Use when asked about "SBOM", "software bill of materials", "supply chain attack", "dependency provenance", "Sigstore", "npm provenance", "package integrity", "typosquatting", "dependency confusion", "artifact signing", "SLSA", "slsa framework", "lockfile security", or ...

Recognize and extract text from images or PDFs using Surya OCR (datalab-to/surya). Use when a user uploads a document, screenshot, scan, or photo and wants the text extracted or analyzed. Surya supports 90+ languages and works on both images and PDFs without an internet connection.

When 2+ independent perspectives must agree before a risky Yana AI action — dispatching review subagents synchronously via the Task tool, resolving their findings by priority (Safety > Correctness > Performance > Style), and blocking on any Safety-severity finding. Replaces an earlier async message-bus/vote design that was never actually wired into the running system.

Deploy full honeynet infrastructure within a multi-agent swarm. Decoy agent prompts, honey-vault canary tokens, ghost file-system monitoring, runtime mutation of compromised agents, and immune system rule generation from blocked attacks.

SWC (Speedy Web Compiler) Rust-based JS/TS transforms. Programmatic transpilation, custom plugins via WASM, minification, module format conversion, and performance-sensitive parse pipelines. Sources: swc-project/swc (Apache-2.0).

Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types.