Claude Skills by manusco

Design Director with a craftsman's eye. Designs interfaces that feel inevitable, human, and timeless through first-principles craft: optical precision, typographic hierarchy, perceptual color, motion with physics, and the subconscious detail layer that separates outstanding from average. Use when starting a design system, specifying UI, auditing a design that feels generic or AI-made, modeling the objects, names, and states users perceive, refining an interface toward high polish, designing a...

Visual Asset Generator. Produces production-ready images to a brief (hero imagery, illustration, textures, marketing visuals, character sheets) using disciplined, model-agnostic prompt craft. Use when generating visual assets where composition, style consistency, and reproducibility matter. Defers all interface and UI taste to resonance-design-designer.

AI / LLM Product Engineer. Owns AI subsystem design and implementation: model routing, prompts, retrieval, RAG internals, agents, evals, grounding, guardrails, cost, and latency. Use when building or diagnosing those systems. Whole-system topology, service boundaries, trust zones, and cross-system data ownership belong to Architect.

Tooling Engineer Specialist. Builds CLI tools, automation scripts, and MCP servers that extend agent capabilities. Use when a manual or repetitive task needs a permanent automated solution, when building a new MCP server to give agents access to a resource, or when optimizing a slow/error-prone internal workflow.

Backend Engineer Specialist. Implements business logic, API endpoints, and data flows with strict type safety, layered architecture, and explicit error handling. Use when building or modifying API endpoints, writing business logic services, integrating third-party APIs, designing data flows, or performing a shadow path audit on an existing service.

The execution orchestrator. Converts architecture into atomic, verifiable steps via the Implementation Plan. Use when an implementation plan is approved and ready to be built. Drives the frontend and backend engineers.

Database Architect Specialist. Designs schemas, optimizes queries, and writes zero-downtime migrations. Use when designing a new entity schema, diagnosing a slow query, writing a migration, selecting a database engine, or auditing data integrity constraints.

Debugger Specialist. Finds root causes through the Scientific Method. No fixes without reproduction. Use when investigating a bug report, diagnosing a production incident, diagnosing an agent trajectory failure, or when a flaky test needs to be pinned to a deterministic reproduction case.

DevOps Engineer Specialist. Implements and verifies CI/CD, Infrastructure as Code, environment parity, rollback mechanisms, and secret rotation. Use for infrastructure changes or diagnostics. During a live incident it contributes bounded infrastructure actions under Incident command; it does not own severity, communications, or incident disposition.

Frontend Engineer Specialist ("The Glassmith"). Implements pixel-perfect, performant, and accessible UI with strict component architecture, shadow state coverage, and Core Web Vitals compliance. Use when building React/Vue/web components, implementing a page from a design spec, polishing UX interactions, or auditing a frontend for performance or accessibility issues.

Game Architect Specialist. Designs core game loops, injects "Juice" (feedback systems), and selects the right engine for the game's soul. Use when designing a core loop from scratch, making a prototype feel flat and lifeless more engaging, selecting a game engine, or adding particle/audio/haptic feedback to an existing mechanic.

Mobile Architect Specialist. Builds offline-first, touch-physics-driven mobile apps in React Native and Flutter with store compliance and Thumb Zone optimization. Use when architecting a new mobile app, designing an offline sync strategy, replacing stiff animations with spring-based physics, or preparing a store submission checklist.

Performance diagnostician. Measures and profiles latency, throughput, resource use, Core Web Vitals, query behavior, and AI cost to identify the proven bottleneck and an optimization budget. Use when the cause or limiting resource is unknown. Hand implementation to Frontend, Backend, Database, AI Engineering, DevOps, or SEO according to the proven owner.

Finance operating-cycle conductor. Use when a user wants actuals, runway, forecast, scenarios, budget decisions, investor updates, or operating metrics governed from source data to decision record.

Leadership operating-cycle conductor. Use when a founder, manager, or executive needs goals, decisions, delegation, hiring, feedback, conflict, cadence, or operating review turned into a clear management cycle.

Marketing Analytics Engineer. Owns measurement definitions, event taxonomies, instrumentation, attribution, sample design, statistical validity, and causal experiment verdicts. Use when evidence must be made trustworthy or interpreted. Conversion owns the customer-facing intervention and variant hypothesis, not the measurement verdict.

Organic Content Distribution Specialist. Plans unpaid feed and community distribution across LinkedIn, X, Instagram, TikTok, YouTube, newsletters used as editorial products, and community channels. Use when building organic content calendars, adapting one idea to platform-native posts, planning repurposing, packaging short or long-form video for discovery, defining community engagement, or deciding how unpaid content should reach an audience. Do not use for paid media, SEO, owned lifecycle em...

Conversion Rate Engineer. Diagnoses decision friction and designs page, journey, offer, and experiment interventions that improve a named action. Use for CRO audits, friction simulation, variant hypotheses, or offer structure. Analytics owns instrumentation, sample design, statistical validity, attribution, and the causal verdict.

Conversion Copywriter Specialist. Writes and rewrites persuasive, idiomatic copy for landing pages, sales pages, lifecycle messages, social posts, subject lines, hooks, and CTAs. Use to create the words, sharpen the argument, apply an existing voice profile, humanize a draft, or check proof and readability. Voice owns extracting a reusable voice profile from a corpus.

Lifecycle and Retention Strategist. Owns scalable product moments and triggered messaging from signup through activation, habit, dunning, save, and win-back. Use when the system must improve cohort behavior before or between human account interactions. Growth chooses the cross-funnel constraint and portfolio. Customer Success owns named post-sale accounts, renewals, QBRs, health, expansion, and escalations.

Paid Acquisition Specialist and media buyer. Plans and scales paid programs across search, paid social, and demand gen, engineers account and campaign structure, runs creative and angle tests, matches ads to landing pages, and holds spend to unit economics. Use when running ads, setting up SEM or Google Ads, launching paid social, buying media, writing ad creative, scaling ad spend, allocating budget, or judging campaigns by CAC, ROAS, or payback.

Marketing campaign conductor. Use when a defined outreach, nurture, newsletter, social, creative, video, or paid campaign must move from intent through specialist assets, approval, launch proposal, and outcome measurement. It may dispatch an unresolved hypothesis to GTM Thinker and an unresolved portfolio choice to Growth. It owns neither strategic decision and never auto-publishes.

Search operating-cycle conductor. Use when recurring or one-off search performance evidence must be collected, checked, interpreted through the SEO specialist, and turned into an owner-ready audit report. It keeps artifacts private by default, requires joint query-page evidence for cannibalization claims, and uses the canonical P0-P3 audit taxonomy. It prepares a run but does not schedule one.

SEO Specialist and Answer Engine Optimizer. Handles technical audits, on-page optimization, content quality (E-E-A-T), schema markup, GEO (Generative Engine Optimization), local SEO, topic clustering, programmatic SEO, and Core Web Vitals. Use when auditing a site for search visibility, optimizing a page for AI citation, building a topic cluster, diagnosing a ranking drop, or implementing schema markup.

Audit conductor for a branch, change set, or codebase. Owns audit scope, earned specialist dispatch, severity normalization, reconciliation, and final disposition. Use for a multi-domain audit before merge or release. Security, Reviewer, QA, Architect, Backend, Performance, and Product own their domain findings. Use a specialist directly for a single-domain question.

Resonance project kernel. Initializes the public project scaffold, loads project context, and maintains project-owned state and memory inside an adopter's repository. Use for `/init`, orientation, or explicit project-state persistence. It is not the general request router, delivery conductor, audit coordinator, or owner of domain work.

Teaches the operator, not the repo. Produces a dense, concrete explainer of a concept, a diff, an idea, or a window of recent work, written for the specific developer so they keep building a mental model when the agent does the writing. Use when the user says explain this, teach me, help me understand this change, or what did we just build, or proactively when a change introduces a concept new to the codebase. Offers an optional predict-then-reveal check-in for active recall.

The company operating system for a founder running a business with a fleet of agents. Owns company OKRs, scorecards, weekly reviews, L10/EOS and IDS, decisions, cadence, delegation, and authority budgets. Use when running the company operating rhythm or defining what an agent may spend, send, change, or commit. Product discovery, PRDs, PMF, and product roadmap choices belong to Product.

The autonomous goal loop. Takes a goal and drives it to a verified finish by first confirming a goal contract, then decomposing it into slices, building, and verifying against grounded checks (real tests, validators, audit), bounded and never auto-shipping. Use when the user gives an outcome to reach rather than a single step, mixes goals with requested tactics, says take this to done, run with it, or make this happen end to end. Manual-only (drives builds, tests, and real side effects).

Writes a handover document for a colleague after a coding session or sprint. Use at the end of a session to capture what was done, decisions made, open TODOs, and backlog. Produces docs/handovers/YYMMDD_handover.md. If a handover file already exists for today, appends to it. Run before closing the conversation. Session context is the richest input.

The self-improving loop. Reads the eval scorecard, finds the skills that show no measured lift, sharpens the skill body or its rubric, and keeps a change only when it raises the measured lift. Use when improving skill quality, working the eval work-list, or making the framework better with evidence instead of opinion. Manual-only (it edits skills and rebuilds).

Incident Commander for an active production event. Owns severity, command roles, mitigation priority, communication cadence, approval gates, and verified recovery. Use when production is currently degraded or a live SEV is declared. DevOps contributes infrastructure actions under Incident command. Retro analyzes the event only after recovery. Manual-only because mitigation and communication have real side effects.

Legal and compliance specialist with a GDPR and DACH (Germany, Austria, Switzerland) lens. Use when writing a privacy policy or terms of service, reviewing a contract or a specific risky clause, handling GDPR or data processing questions (lawful basis, DSAR, controller vs processor, DPA), preparing for a compliance audit such as SOC2, or navigating IP and licensing. Drafts and reviews documents and explains the rules in plain language. It is NOT a substitute for a qualified lawyer; escalate h...

Knowledge Keeper and canonical project-documentation owner. Turns finalized evidence or solved work into durable Diataxis documentation, chooses placement, updates indexes, supersedes contradictions, and archives deprecated docs. Do not use for open-ended research or unsettled claims; hand the evidence question to Researcher first.

Observability Engineer. Makes a running system explainable from the outside: structured logs, metrics, distributed traces, SLOs, and actionable alerts. Use when adding logging or metrics, instrumenting with OpenTelemetry, defining the Four Golden Signals, designing SLIs/SLOs and error budgets, building dashboards, or fixing noisy or missing alerts for a system already in production.

The Experience Auditor Swarm. Audits a live page or a whole site from first principles: the job each page exists to do, whether its value promise is real and delivered fast, clarity, the path to action, craft, function, and trust. Use when auditing a website or landing page you run, doing a first-principles UX and conversion review, asking where a site can be improved, or producing a forward-looking improvement backlog. Runs the experience lenses (conversion, design, copywriter, seo, code aud...

Product Manager Specialist. Defines what to build and why through discovery, Working Backwards PRDs, RICE prioritization, and PMF diagnostics. Use when a feature needs scoping, a roadmap needs product prioritization, or product-market fit needs testing. Company OKRs, scorecards, weekly reviews, L10/EOS, IDS, delegation, and authority budgets belong to Founder OS.

Chief of Staff and Operations Engineer. Eliminates bottlenecks, enforces high-signal async communication, and projects team velocity using data. Use when analyzing team workload, grooming a backlog, auditing communication health, or projecting sprint landing dates via velocity-based burndown.

Quality Assurance Specialist. Proves that the system works, or breaks it trying. Use when writing a test plan, auditing test coverage against the 8-Path Matrix, writing destructive test cases, building an LLM eval suite, or performing a verification audit before a release.

Essentialist Refactor Specialist. Reduces complexity without changing behavior using the Mikado Method and Safe Sequence. Use when simplifying a God class, deduplicating a business rule, centralizing scattered permission checks, migrating legacy patterns to modern standards, or performing an atomic cleanup pass on a specific file.

Engineering retrospective analyst. Uses completed-cycle evidence and git history to explain what happened, what changed, and what should improve. Use when a sprint, release, or recovered incident needs retrospective analysis. It does not command a live incident or implement infrastructure changes.

General code-review gatekeeper. Reviews a concrete diff or PR for correctness, maintainability, regressions, and integration risk, then classifies findings P0 to P3. Use for the whole change. Security owns threat modeling, exploitability, authorization, secret, injection, and security-control conclusions; route suspected vulnerabilities there.

Independent second-model review for concrete diffs and decision artifacts. Dispatches a diff or confirmed plan/ADR/goal contract to a configured independent reviewer, then reconciles the result so disagreement surfaces the bug or assumption one model rationalizes away. Use before merging a risky change, as the final gate in a goal loop, before a high-risk one-way decision, or when the user asks for a second opinion, cross-model review, independent check, or decision review.

Security Auditor Specialist. Owns threat models and security findings for authorization, secrets, injection, trust boundaries, infrastructure controls, and AI abuse paths. Use when the question is whether a system or change is exploitable or adequately defended. Reviewer owns the general correctness and maintainability gate for the full diff.

The Logistics Officer. Safely transports code to the user using the ShipIt protocol. Use when preparing a release, tagging a version, generating a changelog, or deploying to production.

Authors, audits, and hardens Resonance skills with the Forge compiler. Use when building a new skill, converting a workflow into a procedure skill, writing or fixing a skill description or frontmatter, shrinking a bloated SKILL.md, adding evals, or running the skill validator. Covers all three archetypes (knowledge, procedure, orchestration) and emits per-tool, per-model output.

System health assessor. Produces a repeatable whole-system health baseline and trend score across stability, test health, security posture, maintainability, and operational readiness. Use for periodic health checks or release readiness trends. Use Audit for finding-level review of a branch, change set, or concrete codebase scope.

The Maintainer. Upgrades the Resonance framework kernel with a preflight plan, backup, scoped replacement, rollback path, and verification. Use when migrating a project to a new version of Resonance.

The Synchronizer. Realigns the project map (state.md) with the territory (git history). Use when the roadmap is out of sync, after a long session of unlogged work, or when onboarding onto a stale project.

Tone of Voice Architect. Extracts evidence from a writing corpus and compiles a portable behavioral voice profile with examples and boundaries. Use when the reusable voice itself must be discovered or documented. Copywriter applies an existing voice profile and writes or rewrites the actual copy.