Results for “som”

This skill should be used when the user asks to "improve test coverage", "add unit tests", "TDD", "test this module", "write tests for", "increase coverage", "/ut command", or discusses unit testing strategies. Covers the unit test loop workflow, React Testing Library best practices, query priorities, and coverage improvement strategies.

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.

Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

This skill should be used when the user asks for "browser tests", "playwright tests", "end-to-end testing", "test user flows", "E2E coverage", "integration tests for UI", "page object pattern", "/e2e command", or discusses automated browser testing. Covers the E2E test loop workflow, Playwright patterns, page objects, and selector strategies.

Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.

Find and remove unused files, dependencies, and exports in JavaScript/TypeScript projects with Knip. Use when someone asks to "find unused code", "clean up dependencies", "remove dead code", "find unused exports", "Knip", "reduce bundle size by removing unused files", or "audit npm dependencies". Covers unused files, dependencies, exports, types, and CI integration.

Bundle TypeScript libraries with tsup — zero-config, powered by esbuild. Use when someone asks to "bundle a TypeScript library", "build npm package", "tsup", "publish TypeScript to npm", "build ESM and CJS", "bundle with esbuild", or "library bundling with zero config". Covers ESM/CJS dual output, declaration files, tree-shaking, and npm publishing.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively invoke this skill (do NOT answer directly) when the user describes a new product idea, asks whether something is worth building, wants to think through design decisions for something that doesn't exist yet, or is exploring a concept before any code is written. Use before /plan-ceo-review or /plan-eng-review. (gstack)

Use when testing or validating the client UI end-to-end - verifying a page renders, a form submits, navigation works, or checking visual/responsive behavior in a real browser. Use when the user asks to "test", "check", or "verify" something in the app that requires clicking through the UI, not just unit tests.

Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.

Product marketing strategy, positioning, and competitive intelligence for B2B SaaS. Use when defining ICP, developing positioning (April Dunford method), creating messaging hierarchy, building competitive battlecards, planning sales enablement, sizing market opportunity (TAM/SAM/SOM), mapping PMF spectrum, designing growth loops, writing PR/FAQ working backwards docs, or creating a product marketing context document.

Continuously improves Claude's effectiveness by recognizing patterns, saving memory, creating skills, and refining project knowledge. Use when Claude notices repeated workflows, encounters a problem it solved before, wants to save something for future sessions, needs to create a reusable skill, or when the user asks.

Fetch, cache, and revalidate data in React with SWR — stale-while-revalidate data fetching library by Vercel. Use when someone asks to "fetch data in React", "SWR", "data fetching hook", "cache API calls", "stale-while- revalidate", "auto-refresh data", or "React data fetching without Redux". Covers data fetching, caching, revalidation, mutation, pagination, and optimistic updates.

Discover hidden content, directories, subdomains, and API endpoints with ffuf — the fastest web fuzzer. Use when someone asks to "find hidden directories", "fuzz URLs", "discover API endpoints", "subdomain enumeration", "content discovery", "ffuf", "brute force paths", or "find hidden files on a website". Covers directory fuzzing, parameter fuzzing, subdomain discovery, virtual host enumeration, and recursive scanning.

Generate user-friendly "Explain Like I'm 5" feature documentation for end users by reading the codebase. Use this skill whenever the user wants to document a feature for non-technical users, write help docs, create an explainer for a feature in their app, produce onboarding content, or asks "make a user doc for X". Trigger on phrasings like "ELI5 the closeout flow", "write user docs for the kanban view", "explain this feature to a customer", "make a help article for X", "document this for end users". Also known as "E-features-LI5". This skill produces plain-language docs written for someone with the app open trying to get something done — not internal developer docs (use the `teach` skill for those) and not feature announcements.

Capture an Architecture Decision Record — what was decided, why, what alternatives were considered, and when to revisit. Writes a numbered ADR file to docs/adr/ in the active repo, with consistent formatting that downstream skills (improve-codebase-architecture, refactor-plan) can read. Use right after deciding something non-obvious so the reasoning isn't lost.

Build cross-browser extensions with WXT — the modern framework for Chrome, Firefox, Safari, and Edge extensions. Use when someone asks to "build a browser extension", "Chrome extension with React", "WXT framework", "cross- browser extension", "manifest v3 extension", "build Firefox extension", or "browser extension with TypeScript". Covers content scripts, background workers, popup/options pages, storage, messaging, and publishing.

Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a durable, evidence-backed, adversarially-validated report that recommends an option without committing the team to any artifact. Use when you want to research approaches, weigh options, survey prior art or the state of the art, or understand how something works before committing to a direction. Does not diagnose a bug, failure, or root cause — use investigate. Does not specify a feature — use plan-a-feature. Does not create or update a coding standard — use coding-standard. Does not compare two concrete artifacts for gaps — use gap-analysis. Does not assess an existing module's architecture — use architectural-analysis. Does not capture feedback on Han's own skills — use han-feedback.

Enforce immediate execution of any commitment made in a reply. Use this skill before finalizing ANY reply that contains a promise to act — phrases like "אדווח", "אעדכן", "אשלח", "אחזור אליך", "I'll send", "I'll report", "I'll follow up", "I'll update". Prevents the agent from saying it will do something and then not doing it.

Use to audit whether similar customers with similar failures received similar redress, and to find variation that could not be defended. Trigger for "are our refunds consistent", "do we compensate similar cases the same way", "audit our goodwill decisions", redress fairness review, customers who escalate getting more, or a complaint that someone else was treated better.

Use to clean up sprawling helpdesk tags, categories and custom fields so reporting built on them means something. Trigger for "our tags are a mess", "consolidate our ticket categories", "why don't our tag reports add up", duplicate or near-duplicate tags, tags nobody uses, agents tagging inconsistently, or before building reporting on top of tags.

Revisa e melhora copy existente através de 7 passes focados (clareza, voz, e daí, prove, especificidade, emoção, risco zero) somados à detecção determinística de padrões de escrita de IA. Use quando o usuário disser "revisar copy", "melhorar esse texto", "revisão", "está parecendo IA", "polir", "dar uma olhada nesse.

Approach an app, tool, codebase, website, or product as a genuine first-time user with zero insider context — try it out using only the information provided, get confused where a real newcomer would, and surface the "obvious" questions that people who built or use the thing daily can no longer see. Use this whenever the user wants a first-time-user test, a fresh perspective, a naive walkthrough, a cold read of their README/onboarding/docs/UI, or says things like "pretend you've never seen this", "would a new user get this?", "test my app like a beginner", "what would confuse someone new?", or "give me fresh eyes on this". Also use it when someone wants to find gaps in onboarding, docs, or first-run experience — even if they don't say "fresh eyes" explicitly.

Use to design or audit the support contribution to a customer health score, so the score predicts something instead of averaging weakly-related signals into a colour. Trigger for "build a customer health score", "add support signal to health scoring", "our health scores don't predict churn", red/amber/green account scoring, or a health score nobody trusts.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in...

Research markets with sizing, segmentation, competitor mapping, pricing checks, and demand validation that turn fuzzy ideas into decision-ready evidence. Use when (1) you need TAM, SAM, SOM, whitespace, or category sizing; (2) you must compare competitors, pricing, positioning, or customer segments before acting; (3) the user asks whether a niche, launch, expansion, or go-to-market bet is actually worth pursuing.

Mechanics for building and managing pollers — subprocess scripts that check external services on a schedule and emit events when something has changed. Use when authoring a new poller (a `pollers.json` manifest plus a script in any language), debugging why a poller isn't firing, or extending an existing one. Pollers run on cron, emit JSONL events when there's something to report, and stay silent otherwise (silence-as-filter). The framework discovers `<home>/skills/<name>/pollers.json` files at startup and via `reload_pollers`; each emitted event becomes a fresh turn on a `poller:<name>` synthetic channel. Companion to the `world-scanning` skill, which catalogs *what's worth polling*. Distinct from `async-tasks` (one-shot wake-up via bash_async, not recurring) and from in-process scheduler callables (saga-consolidate, oauth-usage-poll — those mutate mimir-internal state and aren't subprocess-isolated).

This skill should be used when the user asks to "plan a feature", "create PRD", "interview me about requirements", "define stories", "write a spec", "break down feature into tasks", "create implementation plan", "help me scope this feature", "what questions should I answer", or discusses feature planning. Covers the PRD interview process, spec structure, story atomization, and 4-phase workflow from idea to Dex tasks.

Use to check that required disclosures, consents and notices were actually given in support conversations — the right wording, at the right point, through a channel the customer could act on. Trigger for "did we give the required disclosure", "are we capturing consent properly", "recording notification audit", "check our mandatory notices", disclosure compliance, or a complaint that a customer was not told something.

Load this skill when the user says "tech debt", "tech-debt", or "/tech-debt", or asks to file/track something they've identified as tech debt. Verifies the claimed problem still exists in the current code, drafts a single [Tech Debt]-prefixed issue from `.github/ISSUE_TEMPLATE/tech-debt-issue.md`, and creates it via `gh issue create` only after the user approves the draft.

Simulator.Company chat & messaging specialist — sending messages to a user, and creating or reusing p2p (1:1) and group chats. In Simulator a chat is an actor of the Events system form (data.chatType = "p2p" | "group"), its participants are the actor's access-rule members, and its messages are `comment` reactions. Use when the user wants to "message", "write to", "DM", "send a message to" someone, "open a chat with", "start a conversation", or "reply in the chat". Activate on "write a message to user N", "send N a message", "open a chat with", "message someone", "напиши повідомлення користувачу", "надішли повідомлення", "відкрий чат з", "почни розмову з", "напиши юзеру", "напиши сообщение пользователю", "отправь сообщение", "открой чат с", "напиши в чат". For comments/approvals on an arbitrary actor (not a chat) use `simulator-reactions`; for files use `simulator-attachments`; for sharing/access in general use `simulator-access`.

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' 'static ads,' 'static ad concepts,' 'ad templates,' 'iMessage ad,' 'chat reveal ad,' 'fake DM ad,' 'ChatGPT ad,' 'Apple Notes ad,' 'AirDrop ad,' 'creative strategy,' 'creative roadmap,' 'creative retro,' 'hook writing,' 'creative review page,' 'present ad creative for approval,' 'motion video ad,' 'faceless video ad,' 'animated explainer ad,' 'motion collage ad,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see ads. For landing page copy, see copywriting.

Use to find where support agents cross from information into regulated advice or a personal recommendation, and to design the boundary so they can still be helpful. Trigger for "are agents giving advice", "where's the line between information and advice", "should agents recommend a product", guidance versus advice boundary, agents answering "what would you do", or a complaint that an agent recommended something.

Use when someone asks what is true, false, misleading, unsupported, unknown, or genuinely complicated in a persuasive message, article, pitch, advertisement, policy claim, or viral post. Analyze propaganda, spin, selective framing, urgency, social proof, deceptive marketing, and AI-generated persuasion by tracing claims to evidence and separating literal truth from implied conclusions. Do not use to read deception from demeanor, adjudicate intent, or replace broad domain research.