Marketplace

Use when building or reviewing interactive UI, forms, navigation, or dynamic content. Covers semantic HTML, keyboard access, focus management, labeling, state-change announcement, and reduced-motion / high-contrast preferences. Do NOT use for color-palette creation, visual branding, feedback-state staging, or prose reading-level accessibility - those belong to `visual-design-foundations`, `interaction-feedback`, and documentation respectively. Do NOT use for rewrite this error message at a 6th-grade reading level. Do NOT use for clean up this accessibility code without changing how it behaves.

Use when working with Etsy listings — Etsy's own title/tag/category/attribute/description/photo/video model and two-phase search (query matching → ranking on relevancy, listing engagement, recency, shipping price, customer-and-market experience, and personalization); the 13-tag and 20-character-per-tag limits and 140-character title cap; Etsy's 2026 natural-readable-title guidance; the description as an indexed/semantic and Google-snippet surface; free-shipping/shipping-price visibility thresholds; listing-video specs; the first-party Search Visibility diagnostic; the Etsy Open API listing surface; and editing Etsy listings managed by an upstream POD platform (Printify/Printful) including the publish/lock lifecycle, selective publishing, and publish-failure diagnostics. Do NOT use for generic Shopify storefront work, non-Etsy marketplaces, deep keyword-research methodology, the POD product/blueprint/variant model itself, or print-file/artwork generation.

Objectives and Key Results goal-setting methodology for turning strategy, quarterly priorities, product goals, or team focus areas into outcome-oriented Objectives, measurable Key Results, review cadences, and learning loops. Do NOT use for Decide our winning aspiration, where to play, and how to win. Do NOT use for Use constraint-awareness to identify hard constraints before choosing a strategy or goal.

Use when evaluating whether a firm's resources or capabilities can create sustained competitive advantage with VRIO: Valuable, Rare, costly to Imitate, and Organized to capture value. Covers resource/capability inventory, sequential VRIO testing, competitive implication classification, inimitability mechanisms, organization gaps, investment/protection priorities, and handoff to broader strategy methods. Do NOT use for external industry profit-pressure diagnosis (use porters-five-forces), generic internal/external factor inventory (use swot-tows), durable moat-source taxonomy (use seven-powers), portfolio allocation (use bcg-matrix), product-market growth paths (use ansoff-matrix), or quantified option valuation (use expected-value). Do NOT use for Analyze buyer power, supplier power, substitutes, entrants, and rivalry for this industry. Do NOT use for Turn strengths, weaknesses, opportunities, and threats into TOWS strategy options.

Use when deciding whether to run a task in the Codex CLI agent harness (which drives a frontier GPT model), when scoping work to its native capabilities (resumable `codex exec resume` sessions, non-interactive `exec` stdout-piping, in-process dispatch, `/permissions` sandbox modes, MCP, on-demand subagents, the `/review` code-review agent), or when choosing Codex versus the Claude Code harness for a piece of work — and when avoiding its known failure modes (non-autonomous subagents, Full-Access network reach, cold-one-shot context loss). Do NOT use for routing a task to the GPT MODEL versus Claude (use `gpt-5-5`), for the Claude Code harness decision (use `claude-code`), or for designing a generic resumable agent loop (use `autonomous-loop-patterns`). Do NOT use for is GPT-5.5 or Opus the better model for this task? Do NOT use for what is Claude Code good at? Do NOT use for design a resumable supervised loop from scratch.

Use when scanning an external macro environment with PESTEL/PESTLE and variants such as STEEPLE, STEEPLED, PESTLIED, STEEP, DESTEP, and LoNGPESTLE: political, economic, social, technological, environmental, and legal forces; evidence quality and recency; geography/jurisdiction and local/national/global level; time horizon; uncertainty; weak signals; impact/probability scoring; factor interactions; bias checks; opportunity/threat implications; assumptions; action conversion; and monitoring triggers. Covers external-environment scanning before strategy choices, market-entry reviews, strategic planning, product/service context, policy-aware planning, and risk/opportunity surfacing. Do NOT use for internal capability diagnosis (use swot-tows), industry profit-pressure diagnosis (use porters-five-forces), value-curve redesign (use blue-ocean-strategy), integrated strategy cascades (use playing-to-win), product positioning (use positioning), or quantified option comparison (use expected-value).

Use when deciding whether to route a task to OpenAI's GPT-5.5 frontier model versus Claude Opus or Sonnet — picking the model lane for infrastructure scripts, CI pipelines, concrete implementation, analytical code review, security review, or CLI/terminal-heavy work, and weighing GPT-5.5's context window, pricing, and per-benchmark strengths against the Claude tiers for the same task. Covers the decision-useful capability and pricing facts, and the boundary against the Claude routing skills. Do NOT use for running the GPT model through a harness (use `codex`), for choosing among the Claude tiers themselves (use `claude-opus` / `claude-sonnet`), or for routing among local skills at request time (use `skill-router`). Do NOT use for resume my last Codex session and keep going. Do NOT use for is Opus or Sonnet the right Claude tier for this? Do NOT use for which of my skills handles webhook tasks?

Use when working with Shopify — Admin API, Storefront API, OAuth scopes, HMAC SHA-256 webhook verification, GraphQL query-cost handling, Online Store 2.0 themes (sections, blocks, Liquid), metafields and metaobjects, and App Proxy. Do NOT use for generic e-commerce design, non-Shopify storefronts, or internal event-contract design. Do NOT use for Design the event payload schema for our internal order-processing pipeline. Do NOT use for Implement Stripe Connect onboarding for a marketplace. Do NOT use for Refactor a generic shopping cart component that isn't Shopify-specific.

Use when generating a wide range of solution concepts before converging on a direction, running structured idea-generation sessions, breaking out of solution fixation, or moving from divergent to convergent selection with explicit criteria. Do NOT use for collaborative engineering domain discovery (event-storming), solo deep technical design, or making final go/no-go investment decisions — those require different methods. Do NOT use for Decide whether to invest in this feature for the next quarter. Do NOT use for Model the bounded contexts for the order-fulfillment domain. Do NOT use for Write the production code for the selected concept.

Use when doing keyword research, evidence-quality triage of keyword sources, query normalization, mapping search intent, building topical clusters, choosing terms for product or marketplace listings, researching question/answer-intent and entity demand for AI search (AEO/GEO), detecting cannibalization, or translating query demand into page/listing targets. Covers seed expansion, intent classification, clustering, entity/topic research, platform field translation for Etsy, Amazon, Shopify, SaaS/content sites, long-tail marketplace strategy, marketplace semantic-intent (Amazon COSMO/Rufus) checks, cannibalization resolution, and rank/AI-citation tracking cadence. Do NOT use for building SEO pages, schema strategy, or AI-search content implementation (use `seo-strategy`), writing the finished prose (use `writing-humanizer`), or designing navigation/page hierarchy (use `information-architecture`). Do NOT use for build the SEO landing page, JSON-LD schema, and internal-linking plan from these keywords.

Use when deciding whether to run a task on the OpenCode agent runtime, how to invoke it non-interactively, how to pick a provider/model string, or how OpenCode differs from Claude Code and Codex. Covers terminal TUI, opencode run, ACP/IDE bridge, desktop beta, web UI, opencode serve, provider/model routing, OpenCode Zen and OpenCode Go lanes, config precedence, JSONL output, CLI command surface, build/plan agents, LSP code intelligence, permissions, Agent Skills, MCP, references, commands, plugins, local models, and scripting/automation. Do NOT use for choosing which free model fits a task (use opencode-free-models), writing the agent loop itself (use autonomous-loop-patterns), or GitHub Copilot premium-request economics (use github-copilot). Do NOT use for which free model should I use for this classification job? Do NOT use for how do I structure the autonomous agent loop itself? Do NOT use for how many Copilot premium requests will this burn?

Use when working with Printify — the print-on-demand REST API, catalog model (blueprints, print providers, variants, print areas), product creation and publish lifecycle to connected channels, order routing, shipping cost queries, and HMAC SHA-256 webhook verification. Do NOT use for non-Printify POD vendors, generic Shopify storefront work, or print-file (artwork) generation. Do NOT use for Generate the artwork PNG file that gets uploaded as a print file. Do NOT use for Implement the Shopify side of the Printify-to-Shopify sync. Do NOT use for Design a generic POD-vendor-agnostic product schema.

Use when reorganizing existing code without changing external behavior — extracting functions, reducing duplication, renaming for clarity, splitting modules, or tightening structure. Covers behavior preservation, duplication reduction, decomposition, naming improvements, structural reorganization, and before/after verification. Do NOT use for bug investigation, adding new product behavior, or writing documentation (even when the docs describe the refactored code). Do NOT use for the test is failing after my edit — what did I break? Do NOT use for write an architecture note explaining this pattern for new team members. Do NOT use for reproduce why this function retries three times on transient network errors.

Use when behavior is broken, a test is failing, or runtime output contradicts expectations. Covers failure reproduction, scope reduction by bisection, evidence capture at the moment of failure, root-cause isolation (not symptom patching), fix verification against the same evidence path, and regression-test creation. Do NOT use for feature planning, architectural design, or behavior-preserving refactor. Do NOT use for plan test coverage for a new feature. Do NOT use for document what this function does for future readers. Do NOT use for refactor this messy code while the test suite is green.

Use when facing an unknown software failure, when symptoms point to different root causes, or when an initial debugging attempt has not converged. Provides a triage-first diagnostic routing framework: classify the failure, collect the right evidence, choose a technique, track confidence, and escalate when stuck. Do NOT use for executing scientific debugging after triage (use `debugging`), code-quality review (use `code-review`), or proactive observability setup. Do NOT use for actually execute scientific-method debugging on this stack trace. Do NOT use for review this AI-generated PR for correctness. Do NOT use for scan this repo for OWASP top 10 vulnerabilities. Do NOT use for design observability instrumentation for this service. Do NOT use for decide which agent should pick up this ticket. Do NOT use for what's the right test pyramid for this feature.

Use when a goal, plan, design, strategy, or assumption should be examined by reversing it: ask how to guarantee failure, how the opposite could be true, or what would have to happen for the desired outcome not to occur. Covers objective reversal, failure-path enumeration, obstacle-first planning, opposite-hypothesis testing, and prevention design. Do NOT use for decomposing a problem to irreducible premises (use first-principles-thinking), post-failure root-cause analysis (use debugging), recurring failure clustering (use pattern-recognition), or claim/source grounding (use epistemic-grounding). Do NOT use for Break this pricing model down to irreducible assumptions. Do NOT use for This incident already happened; find the root cause. Do NOT use for Score every webhook failure mode with severity, occurrence, and detectability. Do NOT use for Facilitate a team pre-mortem session with independent written generation.

Use when writing or reviewing functional UI text: button labels, empty states, tooltips, dialogs, placeholders, loading/progress messages, toasts, inline validation, permission copy, or onboarding steps. Covers interface-copy patterns such as verb-first action labels, acknowledge-explain-guide empty states, one-sentence tooltips, consequence-first confirmations, progressive loading language, and blur/fix validation messages. Do NOT use for marketing persuasion, documentation prose/guide structure, feedback-state staging, or general linguistic rationale behind wording. Do NOT use for write the marketing headline for the pricing page. Do NOT use for review this WCAG 2.2 contrast violation on the dashboard. Do NOT use for explain the morphology rule behind verb-first function names. Do NOT use for restructure this help-center article into a tutorial. Do NOT use for decide the kebab-case format for this new CSS class. Do NOT use for rename this React component across all call-sites.

Semantics: choosing and auditing the meaning encoded by names, status codes, versions, commits, tokens, and signals across code, APIs, and UIs. Do NOT use for Should onboarding be hyphenated, and how does English compound morphology affect that decision? Do NOT use for What casing should a new database timestamp column use -- kebab, snake, or camel? Do NOT use for Rename this function and update every call-site across the repo. Do NOT use for Type the relation between refund and payment as IS-A, PART-OF, causal, or thematic. Do NOT use for Design the full REST resource surface with pagination, idempotency keys, and auth boundaries.

Use when designing or auditing icon systems, colors/badges/shapes, visual metaphors, interface signs, or naming-plus-visual surfaces that users misread. Covers semiotic reasoning across icon/index/symbol, signifier/signified, denotation/connotation/myth, color/shape/position/iconography, affordances, code/API signifiers, and semiotic-coherence audits. Do NOT use for actual UI wording (use `microcopy`), palette/typography craft (use `visual-design-foundations`), accessibility or contrast compliance (use `a11y`), formal class hierarchies, or word morphology rules. Do NOT use for I need formal class hierarchies, axioms, and what-exists rules for our knowledge base. Do NOT use for I need physical database schema design and relationship constraints. Do NOT use for I need the relation type between two concepts — synonymy, polysemy, or meronymy. Do NOT use for draft the exact wording for a button label or tooltip after the sign system is chosen.

Use when turning internal/external situation analysis into strategic options with SWOT and TOWS: strengths, weaknesses, opportunities, threats, evidence quality, SO/WO/ST/WT option generation, and action hypotheses. Covers separating internal from external factors, avoiding unsupported laundry lists, crossing quadrants into strategy options, and naming what evidence or method should follow. Do NOT use for industry profit-pressure diagnosis (use porters-five-forces), durable moat classification (use seven-powers), value-curve redesign (use blue-ocean-strategy), integrated strategy cascades (use playing-to-win), or quantified option comparison (use expected-value). Do NOT use for Analyze supplier power, buyer power, entrants, substitutes, and rivalry. Do NOT use for Classify this company's durable moat source. Do NOT use for Create a strategy canvas and ERRC grid for a new market space. Do NOT use for Turn this strategy into winning aspiration, where to play, how to win, capabilities, and systems.

Use when designing or reviewing HTTP API surfaces: consumer tasks, audience class, protocol/paradigm fit, resources/actions, route taxonomy, request and response schemas, status codes in context, pagination, filtering, sorting, field selection, idempotency, auth and tenant boundaries, error envelopes, rate-limit signals, versioning, deprecation, discovery, and contract artifacts. Do NOT use for pure HTTP protocol semantics (use `http-semantics`), framework-specific route handler mechanics (use `route-handler-design`), non-HTTP system contracts (use `system-interface-contracts`), async event contracts (use `event-contract-design`), database design (use `entity-relationship-modeling`), inbound provider webhook mechanics (use `webhook-integration`), or post-failure diagnosis (use `debugging`). Do NOT use for define the broader contract between a job, service, and dashboard. Do NOT use for design database tables, foreign keys, and views.

Use when analyzing product, brand, business-unit, or investment portfolio allocation with the BCG Growth-Share Matrix: market growth, relative market share, stars, cash cows, question marks, dogs/pets, cash generation, invest/harvest/divest/reposition choices, portfolio balance, and modern limitations. Covers defining portfolio units and markets, choosing comparable metrics, plotting quadrants, interpreting cash-flow logic, challenging share-growth assumptions, and handing off to valuation or strategy methods. Do NOT use for product-market growth paths (use ansoff-matrix), macro-environment scanning (use pestel), industry profit-pressure diagnosis (use porters-five-forces), internal/external factor inventory (use swot-tows), durable moat classification (use seven-powers), or quantified option valuation (use expected-value). Do NOT use for Classify growth ideas as market penetration, market development, product development, or diversification.

Use when scoring a completed agent task, implementation, document, skill upgrade, or other deliverable against the original request, acceptance criteria, verification evidence, quality rubric, and residual risks before calling it done. Covers skeptical critic review, 1-5 scoring, score ceilings, evidence sufficiency, finding/action capture, and the evaluation-revision loop. Do NOT use for designing eval datasets or graders (use eval-driven-development), line-by-line diff review (use code-review), choosing test levels (use testing-strategy), or designing the overall process and gates before work starts (use methodology). Do NOT use for design a new eval dataset, grader, and hard negatives for this router. Do NOT use for review this pull request line by line for bugs and security issues. Do NOT use for choose unit versus integration versus end-to-end tests for this feature. Do NOT use for design the whole implementation methodology and quality gate sequence before work starts.

Use when deciding whether to route a task to Google's Gemini Pro frontier model (current Gemini 3.1 Pro generation, moving to Gemini 3.5 Pro) instead of Claude Opus or GPT-5 — especially for very-large-context reasoning (1M-token input), whole-codebase or long-document analysis, native multimodal input (audio/video/PDF/image in one call), or capability-per-dollar at the frontier. Covers the context window, the 200K context-tier pricing cliff, multimodal support, and the per-lane comparison against Claude Opus / GPT-5. Do NOT use for choosing the cheap/fast tier (use `gemini-flash`), for general agent-system architecture (use `agent-engineering`), or for dispatching among local skills (use `skill-router`). Do NOT use for I just need a cheap classifier for 10k rows. Do NOT use for design the multi-agent orchestration for this system. Do NOT use for which of my local skills should handle this request?

Use when planning or executing agent/tool operations that touch protected files, credentials, destructive git commands, destructive SQL, PII, secrets, deployments, package publication, or irreversible system mutations. Covers proactive safety policy, tool-call tripwires, blocking vs advisory enforcement, secret-exposure prevention, and excessive-agency containment. Do NOT use for application input validation, routine git workflow design, migration authoring, or general code correctness review (use `code-review`, `version-control`, or `database-migration`).

Use when classifying product features, service attributes, customer needs, or roadmap candidates with the Kano model: must-be/basic quality, performance/one-dimensional quality, attractive/delighter quality, indifferent quality, reverse quality, and questionable responses. Covers paired functional/dysfunctional survey design, segment-specific classification, feature-priority implications, category migration over time, and the boundary between Kano analysis and general backlog scoring. Do NOT use for generic RICE/ICE/MoSCoW ranking without customer-response evidence (use prioritization), open-ended research synthesis (use user-research or research-synthesis), or product-market positioning (use positioning). Do NOT use for Rank this backlog by reach, impact, confidence, and effort. Do NOT use for Synthesize these interview transcripts into research themes. Do NOT use for Design a generic quality-improvement process with DMAIC or PDCA.

Use when disciplined, complete, evidence-backed execution matters more than brevity: audits, diagnostic reports, tracked-task creation from findings, acceptance-criteria verification, research briefs, and enumerated outputs future work depends on. Covers why agents fail at completeness (sycophancy, premise adoption, summary-first compression, instruction-density loss, long-horizon attention decay, self-critique echo chambers, reasoning-masked agreement, verification theater, delegation-as-proof) and countermeasures: pre-task scope declaration, count-preserving enumeration, evidence receipts, externally grounded critique, provenance labels, explicit completeness/partial receipts, and runtime enforcement. Do NOT use for shortest-route selection (use task-path-optimization), broad artifact-quality standards (use best-practice), scoring results (use evaluation), compact pre-output enforcement (use no-cutting-corners), or post-enumeration compression (use summarization).

Use when deciding whether to run a task in the Claude Code agent harness, when scoping work to its native capabilities (skills, hooks, subagents, MCP, plan mode, 1M-context Opus, background tasks, slash commands), or when choosing Claude Code versus a different harness (Codex, OpenCode, Copilot) for a given piece of work. Covers what the harness is good at, the extensibility stack and when each layer earns its keep, and the decision boundaries against rival harnesses. Do NOT use for writing Anthropic SDK / API code (use `claude-api`), for choosing which Claude MODEL to route a task to versus GPT (use `gpt-5-5`), or for designing a generic autonomous agent loop (use `autonomous-loop-patterns`). Do NOT use for write a Python script that calls the Anthropic Messages API. Do NOT use for is GPT-5.5 or Opus better for this code review? Do NOT use for design a resumable autonomous loop with a supervisor.

Use when deciding whether to route a task to Anthropic's frontier reasoning tier (Claude Opus) — architecture, multi-file synthesis, hard debugging, security reasoning, long-horizon agentic planning — and when NOT to (mechanical work belongs on a cheaper tier). Covers the Opus capability profile: 1M-token context, the cost/latency premium, adaptive thinking, the Opus-only effort ceiling (xhigh/max), task budgets, prompt-caching minimums, and high-resolution vision. Do NOT use for picking the balanced implementation tier (use claude-sonnet), the fast/cheap tier (use claude-haiku), designing the loop the model runs inside (use autonomous-loop-patterns), or for Claude API request syntax (read the claude-api reference).

Use when reviewing a pull request, diff, or proposed code change for correctness, clarity, security, performance, maintainability, test evidence, and project-convention fit, whether the author is a human, an AI agent, or a peer. Covers pre-review fact gathering, verifying AI-written PR summaries against the diff, reading tests before implementation, tracing call sites and blast radius, review size and attention budget, severity grading with Conventional Comments, comment phrasing, reviewer qualification, treating diff content as evidence rather than instructions, refusing rubber-stamp approval for AI-generated diffs, and making an explicit approve/request-changes/close merge decision. Do NOT use for authoring the code (use refactor for behavior-preserving changes or skill-scaffold for new skills), chasing a known bug after merge (use debugging), security-only audits (use owasp-security), or explaining a patch without a merge verdict (use diff-analysis).

This skill provides expertise in data and context compression: SaaS payload optimization (Zstd, Brotli, Gzip), database storage compression, and AI context window compression (Semantic Summarization, Token Pruning). Use when optimizing API latency, reducing storage costs, or managing long-running agent sessions near context limits. Do NOT use for image/video lossy compression (use product-photo) or file archiving.

Enforces the documentation-sync discipline: every code or behavior change ships its documentation in the SAME commit, never after. Provides the five-step workflow — diff the change, route each changed file to the doc that OWNS that behavior (document by ownership, not convenience), update each owning doc, verify the update actually landed, and report what was changed — plus the doc-type-purity and stale-reference gates that keep a docs corpus from drifting as code moves. Use at the pre-commit step of any task that changes code, when a change touches several docs, when renaming or deleting something that is referenced elsewhere, or whenever you are unsure which doc owns a change. Do NOT use for how to WRITE good documentation prose or pick a doc's Diátaxis type (that is a documentation-authoring skill), for choosing clear names (use `naming-conventions`), or for the broad cross-domain quality catalog (use `best-practice`).

Use when choosing semantically precise names for files/functions/variables/types/columns, resolving overloaded terms, reviewing error messages or UI copy for blame/register clarity, or adapting language for end-user/agent/developer/global-audience contexts. Covers morphology, compound-word order, abbreviation policy, verb-noun naming, polysemy qualification, audience register, blame-free error structure, and cross-cultural language awareness. Do NOT use for casing convention policy (use `naming-conventions`), call-site-wide renames (use `refactor`), docs/navigation structure (use `information-architecture`), specialized UI text pattern catalogs (use `microcopy`), or final prose humanization (use `writing-humanizer`). Do NOT use for decide kebab-case vs snake_case vs camelCase for new database columns. Do NOT use for restructure this doc into a tutorial format with progressive disclosure. Do NOT use for implement Intl.NumberFormat for DKK vs USD currency formatting.

Use when diagnosing organizational alignment with the McKinsey 7S framework: shared values, strategy, structure, systems, style, staff, and skills; how the seven elements reinforce or conflict; change-readiness gaps; and implementation risks. Covers internal organization effectiveness, operating-model alignment, transformation diagnostics, post-merger integration checks, and strategy-to-execution gap analysis. Do NOT use for external industry profit-pressure diagnosis (use porters-five-forces), activity-level value and cost mapping (use value-chain-analysis), durable resource advantage testing (use vrio), broad internal/external option generation (use swot-tows), or execution goal-setting alone (use okrs). Do NOT use for Analyze buyer power, supplier power, substitutes, entrants, and rivalry in this industry. Do NOT use for Map the value chain activities that create customer value and drive cost. Do NOT use for Use VRIO to test whether our data, brand, and process are durable advantages.

Use when serializing merges across multiple agent branches, resolving conflicts between agent outputs, or cleaning stale task branches. Covers atomic locking, idempotency checks, non-fast-forward handling, and worktree cleanup. Do NOT use for ordinary git operations outside an agent merge queue (use `version-control`).

Use when planning multi-step implementations, designing quality gates, establishing verification protocols, or building agent checklists calibrated to known failure modes. Covers methodology/method/process distinctions, Cleanroom, PSP/TSP, hypothesis-driven development, DMAIC, checklist design, V&V frameworks, EDDOps, quality gates, and PDCA. Do NOT use for code-review verdicts (use `code-review`), behavior-preserving implementation work (use `refactor`), or test strategy (use `testing-strategy`). Do NOT use for review this PR and decide whether to approve it. Do NOT use for refactor this file while preserving behavior. Do NOT use for decide unit vs integration vs e2e coverage for this feature. Do NOT use for write the eval cases and grader rubric for this router. Do NOT use for block this dangerous git command or secret-bearing tool call.

Use when applying April Dunford-style product positioning to make a product's differentiated value obvious to the right buyers: competitive alternatives, unique attributes, value themes, best-fit target segments, market category, trend context, and reusable positioning output. Covers the Obviously Awesome 10-step workflow, positioning canvas logic, category choice, value-to-segment fit, and positioning-to-sales-message translation. Do NOT use for full strategy-cascade formulation (use playing-to-win), market-creating value innovation (use blue-ocean-strategy), industry-structure diagnosis (use porters-five-forces), or durable moat classification (use seven-powers). Do NOT use for Turn this whole company plan into winning aspiration, where to play, how to win, capabilities, and systems. Do NOT use for Create a blue ocean strategy canvas and ERRC grid for this market. Do NOT use for Analyze rivalry, buyer power, supplier power, entrants, and substitutes.

Use when building an artifact whose purpose is to answer a specific question — paper sketch, wireframe, clickable mockup, wizard-of-oz, role-play, service prototype, or code spike — at the lowest fidelity sufficient to produce that learning. Do NOT use for production-grade component construction, design-system contribution, or building the actual ship-ready feature — those are design-module-composition and engineering implementation. Do NOT use for Build the production React component for the new dashboard widget. Do NOT use for Add this component to the design system library. Do NOT use for Write the migration script for the production database.

Use when reasoning about types as a quality property of code: what guarantees the type system actually provides, the difference between sound and unsound systems, structural vs nominal typing, type narrowing and exhaustiveness, the runtime/compile-time boundary, and where validation must happen because the type system cannot. Covers TypeScript, Flow, Hindley-Milner languages, and gradual typing in general. Do NOT use for runtime input validation library choice (use api-design for API surface validation; use individual library docs for library mechanics), for SQL type mapping (use entity-relationship-modeling), or for type system implementation (compilers — out of scope). Do NOT use for implement HMAC verification for an inbound webhook (use webhook-integration). Do NOT use for design the JSON shape of an API endpoint (use api-design).

Use when deciding whether to route a task to the fast/cheap tier (Claude Haiku) — transcription, polling, format conversion, structured-output slot-filling, small-diff review, high-volume low-latency work — and where the boundary is that should escalate to Sonnet/Opus. Covers the cost/latency floor, the 200K context ceiling (vs the upper tiers' 1M), the absence of the effort knob, the separate rate-limit pool, and when to drop below Haiku to a script. Do NOT use for ordinary multi-step feature work (use claude-sonnet), the hardest reasoning (use claude-opus), loop design (use autonomous-loop-patterns), or Claude API request syntax (read the claude-api reference).

Use when applying Lean Startup methodology to validate a new venture, product, feature, program, or business model under high uncertainty: build-measure-learn loops, minimum viable products, validated learning, riskiest assumptions, actionable metrics, innovation accounting, learning milestones, and pivot/persevere decisions. Covers experiment design and learning discipline before scaling. Do NOT use for generative customer interviews alone (use user-research), synthesizing existing research (use research-synthesis), feature satisfaction classification (use kano-model), OKR goal-setting, product positioning, or quantified option valuation. Do NOT use for Plan interviews to discover what users need before we have a product concept. Do NOT use for Synthesize these interview transcripts into themes and insights. Do NOT use for Classify these roadmap items as must-be, performance, delighter, indifferent, or reverse features. Do NOT use for Turn this strategy into quarterly Objectives and Key Results.

Use when adding or enforcing lint rules as part of a test or verification plan. Extends testing-strategy with lint-specific guidance: rule selection, gate placement, failure triage, and migration planning when introducing rules to an existing codebase. Do NOT use standalone — load the base testing-strategy skill alongside it — and do NOT use for chasing a specific lint failure in one file (that is debugging). Do NOT use for decide whether to unit-test or integration-test this handler. Do NOT use for extract this repeated code pattern into a shared util.

Use when writing, tightening, evaluating, or repairing an LLM prompt or reusable prompt template for completion, agent dispatch, grading, structured extraction, tool use, or prompt-engineered workflows. Covers instruction hierarchy, message roles, context placement, few-shot examples, structured output, positive constraints, reasoning guidance, prompt-injection resistance, provider differences, and eval-driven iteration. Do NOT use for whole context-system design (use context-engineering), eval dataset or grader design (use eval-driven-development), reviewing generated code (use code-review), authoring SKILL.md files (use skill-scaffold), choosing which skill or agent should activate (use skill-router), or root-causing a deployed failure after outputs already exist (use debugging). Do NOT use for review this AI-generated PR for correctness. Do NOT use for scaffold a new skill that teaches prompt engineering.

Use when designing or reviewing React ref usage: refs as mutable handles that survive renders without triggering them, useRef for DOM access and instance values, ref callbacks for mount/unmount hooks, forwardRef and React 19 ref-as-prop, useImperativeHandle for controlled imperative APIs, and ref forwarding through compound-component primitives such as Radix Slot. Use for focus, measurement, animation, third-party DOM integration, and sparse imperative APIs; never as a substitute for reactive state. Do NOT use for the broader hook discipline (use react-hooks-patterns), state ownership decisions (use state-management), component-layering strategy (use component-architecture), Client/Server serialization boundaries (use client-server-boundary), or form validation UX (use form-ux-architecture). Do NOT use for design the Rules of Hooks and dependency-array discipline for useEffect (use hooks-patterns).

Use when diagnosing whether a business has, can build, or is falsely claiming durable strategic power using Hamilton Helmer's Seven Powers: scale economies, network economies, counter-positioning, switching costs, branding, cornered resource, and process power. Covers Power as benefit plus barrier, persistent differential returns, moat-source classification, Power Progression by company phase, false-positive checks, and strategy implications. Do NOT use for industry-structure analysis alone (use porters-five-forces), integrated strategy-cascade formulation (use playing-to-win), generic prioritization, financial valuation, or surface-level SWOT lists. Do NOT use for analyze the attractiveness of this industry using entrants, suppliers, buyers, substitutes, and rivalry. Do NOT use for turn this market-entry plan into a winning aspiration, where to play, how to win, capabilities, and systems. Do NOT use for rank these roadmap items by impact and effort. Do NOT use for make a SWOT table for this company.

Use when choosing or reviewing growth strategy options with the Ansoff product-market matrix: market penetration, market development, product development, diversification, existing vs new products, existing vs new markets, strategic distance, risk, assumptions, and sequencing. Covers growth-option framing, quadrant classification, evidence needs, option comparison, and handoff to deeper validation methods. Do NOT use for internal/external factor inventory (use swot-tows), macro-environment scanning (use pestel), industry profit-pressure diagnosis (use porters-five-forces), integrated strategy cascades (use playing-to-win), durable moat classification (use seven-powers), or quantified option valuation (use expected-value). Do NOT use for Allocate our R&D budget across existing business units based on market growth rate and relative market share. Do NOT use for Turn strengths, weaknesses, opportunities, and threats into SO, WO, ST, and WT options.

Cross-cutting best practices enforcement across code, templates, skills, prompts, scripts, documentation, pages, and design. The enforcement layer that catches violations any specialist might miss. Do NOT use for deep code review methodology (use code-review), application security depth (use owasp-security), accessibility implementation depth (use a11y), or specialist design-system work (use design-system-architecture, color-system-design, or typography-system). Do NOT use for designing the color system and contrast model (use color-system-design). Do NOT use for implementing font loading and vertical rhythm (use typography-system). Do NOT use for designing a skill's comprehension or application eval suite (use eval-driven-development).

Use when deciding whether to route a task to the balanced implementation tier (Claude Sonnet) — feature work, bug fixes, test writing, multi-step code — as the default lane that is cheaper/faster than the frontier tier and more capable than the fast tier. Covers the cost/quality tradeoff vs Opus and Haiku, the shared 1M context window, effort behavior, and the 1M-context subscription billing caveat. Do NOT use for the hardest reasoning/architecture/security work (use claude-opus), high-volume mechanical or low-latency work (use claude-haiku), loop design (use autonomous-loop-patterns), or Claude API request syntax (read the claude-api reference).

Use when designing or auditing the multi-graph context architecture of an AI-coding workspace: skill graph, document routing graph, memory index, script registry, and the cross-graph edges between them. Covers edge typing, orphan detection, connectivity health, deterministic graph synthesis signals, change-propagation checks, and drift or hub-and-spoke anti-patterns. Do NOT use for authoring one SKILL.md (use `skill-scaffold`), validating one skill (use `skill-infrastructure`), live routing decisions (use `skill-router`), context-window budgeting (use `context-window`), or session load/drop choices (use `context-management`). Do NOT use for scaffold a new SKILL.md from a template. Do NOT use for validate that this single skill's frontmatter matches the schema. Do NOT use for decide which skill to inject for this query right now. Do NOT use for this skill says 'use orgQuery'; that one says 'never use orgQuery' — fix the conflict.

Use when analyzing `git diff`, reviewing a patch before commit, or explaining what a changeset does. Covers unified diff anatomy, hunk interpretation, semantic-vs-formatting separation, blast-radius tracing, hidden-risk scanning, and intent-vs-diff comparison. Do NOT use for full code-review verdicts (use `code-review`), git workflow decisions (use `version-control`), or visual diffs.

Use when reasoning about the pattern where a language model emits structured output describing UI components or a UI sub-tree that an application renders for the user. Covers the typed-schema component palette, JSON Schema/function-calling constraints, two render substrates (typed component tree vs sandboxed iframe), the app-side render pipeline, bidirectional interaction loop via postMessage/JSON-RPC, the security boundary between model author and application renderer, and distinctions from chat markdown, prebuilt-widget routing, RSC streaming, and model-emits-code patterns. Do NOT use for page-level rendering taxonomy (use rendering-models), the tool-call protocol cycle (use tool-call-flow), untrusted-content defenses (use prompt-injection-defense), or general component-library architecture (use design-system-architecture). Do NOT use for design the JSON shape of an HTTP API endpoint (use api-design).

Use when reasoning about how a system, user, or designer's internal model of behavior may diverge from reality — applies across UX, distributed systems, type systems, API design, and team collaboration. Covers the three-model frame (designer / system image / user), the two gulfs (execution and evaluation), analogy and metaphor as model-seeding, the five failure modes (transfer, overgeneralization, underspecification, drift, invariant blindness), the surface/operational/architectural/domain layering, and the discipline of validating a model against the system it claims to represent. Do NOT use for the visual representation of a model (use knowledge-modeling), for the formal-domain entities-attributes-relationships of conceptual modeling (use conceptual-modeling), for cognitive biases in decision-making (out of scope), or for empirically eliciting user models via research methods (use user-research). Do NOT use for name the React hook for managing form state (tactical implementation choice).

Use when building, reviewing, or repairing an STP marketing strategy: segmentation, targeting, and positioning as one linked sequence from market definition to segment profiles, target selection, positioning statement, and marketing-mix implications. Covers consumer, B2B, nonprofit, and product-led contexts; segment bases; segment attractiveness; fit; primary/secondary targets; differentiated versus concentrated targeting; perceptual maps; positioning statements; evidence gaps; and handoff to campaign, product, pricing, channel, or sales work. Do NOT use for standalone product positioning/category design without segmentation and target choice (use positioning), macro-environment scanning (use pestel), industry profit-pressure diagnosis (use porters-five-forces), value-curve redesign/new-demand creation (use blue-ocean-strategy), product-market growth-path selection (use ansoff-matrix), or tactical marketing-mix design alone.

Use when condensing prose while preserving meaning: session findings, wrap reports, research briefs, executive summaries, TLDRs, agent handoffs, progressive summaries, audit summaries, and long-document distillation. Covers extractive vs abstractive summarization, what to keep vs drop, evidence preservation, summary levels, handoff summaries, and audit-report condensation without hiding findings. Do NOT use for byte/data compression algorithms (use `compression`), context-window budget math or compaction triggers (use `context-window`), working-set selection (use `context-management`), prose tone repair (use `writing-humanizer`), or quality scoring (use `evaluation`).

Use when auditing a route, defining a route contract, reviewing onboarding or setup flows, diagnosing why a page feels confusing, or when the user asks about top tasks, time-to-value, branching, dead ends, or task complexity. Provides goal-driven UX analysis that turns vague critique into explicit goal -> task -> subtask decomposition and a primary / secondary / supporting hierarchy contract for the first viewport. Do NOT use for control-pattern choice (use `interaction-patterns`), visual craft (use `visual-design-foundations`), responsive layout (use `layout-composition`), or accessibility-only QA (use `a11y`). Do NOT use for review this PR for code quality. Do NOT use for audit this UI for WCAG 2.2 violations. Do NOT use for decide the CSS grid layout for this hero section. Do NOT use for pick the right colors for this status badge. Do NOT use for build the navigation taxonomy for the whole product. Do NOT use for should we use a dropdown or a stepper here.

Use when planning or conducting generative qualitative research with real users — interviews, contextual inquiry, ethnographic observation, diary studies — to learn what people do, think, and need in their own context. Do NOT use for analytics review, survey statistics, A/B test interpretation, or agent-side intent classification — those are different research practices entirely. Do NOT use for Analyze last quarter's NPS results and produce a dashboard. Do NOT use for Classify whether this agent request from the user is high-risk before executing. Do NOT use for Set up an A/B test of two onboarding flows.

Use when allocating context-window budget across system, skill-injection, working, and output zones; monitoring context health; deciding when to compact; preserving state before compaction; recovering after compaction; or choosing strategies for 1M, 200K, or 128K context windows. Covers zone budgets, practical model-budget tables, the 80% compaction rule, pre/post-compact protocols, persistence hierarchy, operation token costs, and token-reduction techniques. Do NOT use for deciding what information belongs in the working set (use `context-management`), prompt design (use `prompt-craft`), graph architecture (use `context-graph`), or memory curation. Do NOT use for decide what context to load or drop in the working set. Do NOT use for design the multi-graph architecture for skills + docs + memory. Do NOT use for improve the prompt template the agent uses. Do NOT use for curate the durable memory index across sessions. Do NOT use for which skill should activate for this query.

Use when designing or reviewing React error boundaries: what an error boundary catches (rendering errors, lifecycle errors, constructor errors) and what it does not (event handler errors, async errors, SSR errors, errors in the boundary itself), why React still requires class components for error boundaries, how to place boundaries by granularity (page / feature / leaf), how error boundaries pair with Suspense, the reset-and-recover pattern (resetKeys, error.reset), the Next.js error.tsx route-segment convention, and how to integrate boundaries with error reporting (Sentry, observability). Covers React 18+ and Next.js App Router. Do NOT use for Suspense boundary placement (use suspense-patterns), for general error-handling discipline (try/catch in async code, validation errors), for backend error contracts (use api-design), or for observability infrastructure (use error-tracking). Do NOT use for handle a Promise rejection in an event handler (use code-review for the local try/catch pattern).

Use when designing or extending an application exception-reporting pipeline: error boundary placement, tracker SDK wrappers, sanitized reporting calls, environment gating, user context without PII leaks, breadcrumbs, and verification that each layer reports correctly. Covers component, route, global, and manual capture surfaces plus central `reportError`/`reportMessage` patterns. Do NOT use for the visual error UX shown to users (use `a11y` and interaction skills), chasing one captured error (use `debugging`), or broad privacy and retention policy (use `owasp-security`). Do NOT use for design accessible error-message copy and recovery UI for the 404 page. Do NOT use for the boundary fired but the tracker shows no event — root-cause it. Do NOT use for explain our error-tracking architecture in the contributor docs. Do NOT use for review this AI-generated error handler for correctness. Do NOT use for decide if the new error path needs an integration regression test.

Use when discovering a domain through events, commands, actors, policies, aggregates, read models, external systems, and temporal workflows before implementation. Do NOT use for event schema/topic contracts (use `event-contract-design`), webhook handler implementation (use `webhook-integration`), generic state transition modeling (use `state-machine-modeling`), or persistence schema design (use `entity-relationship-modeling`). Do NOT use for implement Shopify webhook signature verification and idempotent retries. Do NOT use for draw the state machine for this one status field. Do NOT use for create a normalized data model and indexes. Do NOT use for write event-bus infrastructure code. Do NOT use for define the schema, topic, compatibility, and fixtures for a selected event.