Skills de Claude Code · página 99

Use when a PAID MEDIA plan is needed — work backward from revenue to max CPA and required budget, split spend across channels, funnel stages, and campaign types, build a ramp-up timeline, set KPI targets per channel, and prepare a contingency plan. Trigger on 'media plan', 'paid media budget', 'how much should I spend on ads', 'channel mix for the campaign', 'plan the ad budget', 'we have 10k a month and no plan'. Also use when a budget number exists and nobody has decided where it goes. Not for — the pure revenue-to-budget math, see `10-reverse-kpi-global`; the whole marketing budget including non-paid, see `61-budget-planning-global`; the next period plan built from results, see `57-next-ads-plan-global`.

Use when a WINNING ad has to be scaled without breaking it — readiness checks, vertical scaling at plus 20 to 30 percent per step, horizontal scaling into new audiences, creatives, and channels, learning-phase reset risk, how Advantage+ and Performance Max behave when scaled, creative refresh cadence, and the signals that mean stop. Trigger on 'scale ads', 'increase the ad budget', 'scale a winner', 'CPA went up after I scaled', 'how fast can I scale', 'it worked at 50 a day and broke at 200'. Not for — fixing an account that is not working yet, see `03-performance-eval-global`; warm audience plans, see `56-retargeting-plan-global`; proving the winner first, see `19-ab-test-setup-global`.

Use when warm audiences need a plan — retargeting tiers by intent and recency, a different message per tier, frequency caps, attribution windows, lookalike seeds, exclusion rules, and a first-party data base that survives iOS ATT and cookie deprecation. Trigger on 'retargeting', 'remarketing', 'warm audience', 'custom audience setup', 'retarget cart abandoners', 'my retargeting pool is too small'. Also use when the user says people visit once and never come back. Not for — cold prospecting audiences, see `51-audience-research-global`; the pixel and events that feed these audiences, see `53-tracking-setup-global`; email win-back flows, see `14-email-marketing-global`; raising budgets, see `55-scaling-ads-global`.

Use when the next period ADS plan must be built from last period results — read the report and the audit, keep and scale winners, stop or fix losers, set new test hypotheses, split budget, plan three budget scenarios, and schedule the creative pipeline. Trigger on 'next month ads plan', 'plan ads from the report', 'what should we run next month', 'Q4 ads plan', 'next quarter media plan', 'the month ended, now what'. Also use when a report and an audit both exist and no decisions have been made. Not for — the first media plan before any data, see `54-media-plan-global`; scoring the account, see `21-ads-audit-global`; the next period CONTENT plan, see `40-next-content-plan-global`.

Use when positioning needs defining or sharpening — a statement built on Promise, Proof, and Path, a differentiation matrix against competitors, category entry points, a three-level message hierarchy, and tagline directions. Trigger on 'positioning', 'positioning statement', 'what makes us different', 'USP', 'why should customers choose us over them', 'we sound the same as everyone else'. Also use when the user can list features but not a reason to pick them. Not for — competitor teardown research, see `08-competitor-research-global`; how the brand sounds in writing, see `35-brand-voice-global`; the offer and its value stack, see `31-offer-design-global`; the launch built on it, see `59-go-to-market-global`.

Use when a NEW product, offer, or course is going to market — beachhead segment selection, launch messaging, channels by phase across pre-launch, launch, and post-launch, milestones, success metrics, and go or no-go criteria. Trigger on 'go-to-market', 'GTM plan', 'product launch plan', 'we are launching a new product', 'beachhead segment', 'how do we launch this course'. Also use when the user has a finished product and no route to the first customers. Not for — the day-by-day execution checklist, see `60-launch-playbook-global`; the ongoing period plan, see `00-marketing-plan-global`; one campaign inside the launch, see `02-campaign-brief-global`; positioning first, see `58-positioning-global`.

Use when a launch needs a repeatable EXECUTION playbook — a T-30 to D+7 timeline, per-function checklists for content, design, ads, sales, and engineering, a launch-day war room, an escalation matrix, and roll-back criteria. Trigger on 'launch playbook', 'launch checklist', 'launch day plan', 'launch SOP', 'war room', 'we launch in two weeks and nothing is organized'. Also use when a GTM strategy exists and nobody knows who does what on the day. Not for — the strategy and beachhead choice, see `59-go-to-market-global`; the campaign brief, see `02-campaign-brief-global`; the post-launch review, see `63-campaign-retrospective-global`; a live crisis, see `66-crisis-playbook-global`.

Use when a marketing BUDGET has to be planned or managed in USD — allocation by bucket, channel, and month, test versus scale split, scale-up and stop-loss thresholds, reserve, a plan-versus-actual tracker, and a review cadence. Trigger on 'budget planning', 'marketing budget', 'split the budget across channels', 'stop loss threshold', 'quarterly budget', 'we keep overspending and nobody notices'. Also use when a number has been approved and nobody has divided it up. Not for — the revenue-backward math that produces the number, see `10-reverse-kpi-global`; paid media allocation only, see `54-media-plan-global`; paying an external vendor, see `67-agency-vendor-brief-global`.

Use when a leader must review or approve TEXT-based team output before it ships — content briefs checked for angle, pillar, and CTA, ad copy and creative checked for substantiated claims, on-brand tone, a hook inside the first 125 characters, and platform policy, ending in an Approve, Revise, or Redo verdict with point-by-point feedback. Trigger on 'review this brief', 'approve the ad copy', 'check ads before launch', 'review team output', 'is this good enough to publish', 'my team keeps sending me drafts'. Not for — reviewing a visual design, see `47-design-review-global`; evaluating a person over a period, see `65-team-performance-review-global`; writing the copy yourself, see `05-ad-copy-global`.

Use when a campaign has ENDED and the team needs a structured retrospective — a scorecard against target, what worked, what did not, and why with evidence, surprises, process review, lessons written back into the playbook and Brand Hub, and action items with owners. Trigger on 'campaign retrospective', 'campaign retro', 'post-mortem', 'campaign debrief', 'what worked and what did not', 'the campaign is over, what did we learn'. Also use when a campaign underdelivered and the team is arguing about why. Not for — a periodic performance report, see `07-marketing-report-global`; diagnosing live numbers mid-flight, see `03-performance-eval-global`; the next period ads plan, see `57-next-ads-plan-global`.

Use when a leader assigns work to a marketing team member or runs a cross-functional meeting — a task brief with concrete deliverables, a deadline with time and timezone, a definition of done, constraints, and check-in points, plus an async-first meeting agenda and action-item template. Trigger on 'assign a task', 'brief for my team', 'team brief', 'definition of done', 'meeting agenda template', 'my team keeps delivering the wrong thing'. Also use when the user says nobody knows who owns what. Not for — the campaign brief the whole team executes from, see `02-campaign-brief-global`; briefing an external agency or freelancer, see `67-agency-vendor-brief-global`; evaluating performance, see `65-team-performance-review-global`.

Use when a leader evaluates a marketing TEAM MEMBER using data — a KPI scorecard by role, strengths with real examples, areas to improve stated as observable behavior, a 30 and 90 day development plan, and a 1-5 rating rubric. Trigger on 'performance review for my marketer', 'evaluate a team member', 'monthly 1:1 review', 'feedback for my content writer', 'development plan for an employee', 'is this person underperforming'. Also use when the user is unhappy with someone and cannot articulate why. Not for — evaluating a campaign rather than a person, see `63-campaign-retrospective-global`; reviewing one piece of output, see `62-marketing-review-global`; scoring an external vendor, see `67-agency-vendor-brief-global`.

Khi nguoi dung muon tao hoac cap nhat tai lieu goc ve san pham, khach hang, va dinh vi thuong hieu. Cung dung khi nguoi dung nhac 'product context', 'marketing context', 'thiet lap context', 'dinh vi', 'tep khach hang muc tieu', 'mo ta san pham', 'ICP', 'chan dung khach hang ly tuong', hoac muon tranh lap lai thong tin co ban cho moi task. Dung O DAU moi du an marketing truoc khi dung cac skill khac — skill nay tao file `.agents/product-marketing-context.md` ma tat ca skill khac doc truoc.

Foundation skill for the global marketing cluster. Creates `.agents/product-marketing-context-global.md` with region-specific context (currency, primary platforms, regulations, persona research framework). Pick 1 of 4 region variants: US (USD/FTC), EU (EUR/GDPR), SEA (USD or local/PDPA), LATAM (USD or local/LGPD). All other global skills (00-29) read this context file. Trigger: 'global marketing context', 'international product context', 'US marketing context', 'EU marketing setup', 'SEA marketing context', 'LATAM marketing setup', 'multi-region context'.

>-

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof

Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement

5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance

Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating architecture styles.

Comprehensive architecture patterns, methodologies, quality frameworks, and evaluation methods for solution architects. Load when designing system architecture or selecting patterns.

Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.

Domain-specific authoritative source databases, search strategies by topic category, and source freshness rules

BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation

BDD requirements discovery methodology - Example Mapping, Three Amigos, conversational patterns, Given-When-Then translation, and collaborative specification

Structured divergent thinking techniques — HMW framing, SCAMPER, Crazy 8s mechanics, and option diversity guarantees. Enforces strict separation of generation and evaluation phases.

nWave concierge — ask any question about methodology, project state, commands, migration, or troubleshooting. Read-only, contextual answers.

All /nw-* commands — what they do, when to use them, which agent they invoke. For the buddy agent to help users pick the right command.

How the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.

Single Source of Truth detection — where truth lives in an nWave repo and how to avoid contradicting it.

Wave methodology knowledge for the buddy agent — what each wave does, its inputs and outputs, and how to route questions.

Bug fix workflow: root cause analysis → user review → regression test + fix via TDD

Canary skill for auto-injection detection

CI/CD pipeline design methodology, deployment strategies, GitHub Actions patterns, and branch/release strategies. Load when designing pipelines or deployment workflows.

Cross-agent collaboration protocols, workflow handoff patterns, and commit message formats for TDD/Mikado/refactoring workflows

Documentation collapse anti-patterns - detection rules, bad examples, and remediation strategies for type-mixing violations

Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence

Step-by-step workflow for converting bloated command files to lean declarative definitions

Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.

Crafter discipline contract for the ATDD-pure 7-phase workflow — what the slim crafter does in Phase A (GREEN-the-ATs), Phase B (coverage-driven dead-code elimination), and Phase E (batch L1-L6 refactor), plus hard prohibitions and the Phase B common-cuts taxonomy

Data architecture patterns (warehouse, lake, lakehouse, mesh), ETL/ELT pipelines, streaming architectures, scaling strategies, and schema design patterns

Database comparison catalogs, RDBMS vs NoSQL selection criteria, CAP/ACID/BASE theory, OLTP vs OLAP, and technology-specific characteristics

Event Modeling facilitation technique — brainstorm events, identify commands and views, define aggregate boundaries, write Given-When-Then specifications

Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution

Strategic DDD — bounded context discovery, context mapping patterns, subdomain classification, ubiquitous language, and organizational alignment

Tactical DDD — aggregate design rules, entities, value objects, domain events, repositories, domain services, and anti-pattern detection

Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.

DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.

Shared density-resolution contract for wave skills. Canonical detail on the D12 cascade, density resolver call, ad-hoc override workflow, and DocumentationDensityEvent telemetry emission. Referenced from nw-discover / nw-discuss / nw-design / nw-devops / nw-distill / nw-deliver.

Rollback procedures, risk assessment, pre/post-deployment validation, and contingency planning. Load when orchestrating deployment or preparing rollback plans. For deployment strategy details (canary, blue-green, rolling), see `cicd-and-deployment` skill.

Evaluation criteria and scoring for data engineering artifact reviews

Designs system architecture with C4 diagrams and technology selection. Routes to the right architect based on design scope (system, domain, application, or full stack). Two interaction modes: guide (collaborative Q&A) or propose (architect presents options with trade-offs).

Apple LeanUX++ design workflow, journey schema, emotional arc patterns, and CLI UX patterns. Load when transitioning from discovery to visualization or when designing journey artifacts.

7 agentic design patterns with decision tree for choosing the right pattern for each agent type

Designs CI/CD pipelines, infrastructure, observability, and deployment strategy. Use when preparing platform readiness for a feature.

Generates C4 architecture diagrams (context, container, component) in Mermaid or PlantUML. Use when creating or updating architecture visualizations.

Conducts evidence-based product discovery through customer interviews and assumption testing. Use at project start to validate problem-solution fit.

Question-first approach to understanding user journeys. Load when starting a new journey design or when the discovery phase needs deepening.

4-phase discovery workflow with decision gates, phase transitions, success metrics, and state tracking

Conducts Jobs-to-be-Done analysis, UX journey design, and requirements gathering through interactive discovery. Use when starting feature analysis, defining user stories, or creating acceptance criteria.

Acceptance test creation methodology for the DISTILL wave. Domain knowledge for the acceptance designer agent: port-to-port principle, prior wave reading, wave-decision reconciliation, graceful degradation, and document back-propagation.

Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence. Use when the team has a validated problem but hasn't chosen a solution approach.

Review criteria for the nw-diverger-reviewer — validates JTBD rigor, research quality, option diversity, taste application correctness, and recommendation coherence in DIVERGE wave artifacts

DIVIO/Diataxis four-quadrant documentation framework - type definitions, classification decision tree, and signal catalog

Creates evidence-based documentation following DIVIO/Diataxis principles. Use when writing tutorials, how-to guides, reference docs, or explanations.

Strategic and tactical DDD patterns, bounded context discovery, context mapping, aggregate design rules, and decision frameworks for when to apply DDD

Definition of Ready checklist criteria, antipattern detection patterns, UAT quality rules, and domain language enforcement for product owner review

Critique dimensions, severity framework, verdict decision matrix, and review output format for documentation assessment reviews

Use when a DELIVER roadmap already exists and you need to dispatch exactly one identified step through its TDD cycle. Use nw-roadmap to create the plan, nw-deliver for the whole wave, and nw-continue to resume at the next inferred step.

Fast-forwards through remaining waves end-to-end without stopping for review between waves.

Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.

Toyota 5 Whys methodology with multi-causal branching, evidence requirements, and validation techniques

Creates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE). Use when building a new AI agent or validating an existing agent specification.

TLA+ and PlusCal for specifying distributed system invariants. Decision heuristics for when formal verification adds value, key patterns, state explosion management, and alternatives comparison.

Algebra-driven API design with monoids, semigroups, and interpreters via algebraic equations

Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec

Domain modeling with algebraic data types, smart constructors, and type-level error handling

F# language-specific patterns, Railway-Oriented Programming, and Computation Expressions

Haskell language-specific patterns, GADTs, type classes, and effect systems

Hexagonal architecture patterns with pure core and side-effect shell for functional codebases

Kotlin language-specific patterns with Arrow, Raise DSL, and coroutine-based effects

Core functional programming thinking patterns and type system foundations, language-agnostic

Scala 3 language-specific patterns with ZIO, Cats Effect, and opaque types

Naming conventions, API ergonomics, and usability patterns for functional code

5-layer agent output validation, I/O contract specification, vertical slice development, and test doubles policy with per-layer examples

Git change frequency hotspot analysis — find the most-changed files in your codebase

Infrastructure as Code patterns (Terraform, Kubernetes), observability design (SLOs, metrics, alerting, dashboards), and pipeline security stages. Load when designing infrastructure, observability, or security scanning.

Mom Test questioning toolkit, JTBD analysis, interview conduct, assumption testing framework, and hypothesis design

Evidence collection methods, problem categorization, analysis techniques, and solution design patterns

JTBD methodology for extracting real jobs behind feature requests — job statements, abstraction layers, first-principles extraction, ODI outcome statements, and opportunity scoring

Translating JTBD analysis to BDD scenarios - job story to Given-When-Then patterns, forces-based test discovery, job-map-based test discovery, and property-shaped criteria

Core JTBD theory and job story format - job dimensions, job story template, job stories vs user stories, 8-step universal job map, outcome statements, and forces of progress

JTBD discovery techniques adapted for AI product owner context. Four Forces extraction, job dimension probing, question banks, and anti-patterns for interactive feature discovery conversations.

JTBD opportunity scoring and prioritization - outcome statement format, opportunity algorithm, scoring interpretation, feature prioritization, and opportunity matrix template

JTBD workflow classification and routing - ODI two-phase framework, five job types with workflow sequences, baseline type selection, workflow anti-patterns, and common recipes

Basic compiler conformance fixture.

Minimal MDA source demonstrating relationship-graph footnotes and metadata.mda.* MDA-extended fields. Use as a reference fixture when learning the MDA source format.

MDA compatibility demonstration skill for Codex CLI. Compiled from compat/codex-cli/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md is discovered and parsed by Codex CLI with the envelope subset of agentskills.io v1 fields honored.