curiositech

Predicts the highest-impact next action for your project by running a 5-agent meta-DAG pipeline. Gathers project signals automatically (git, recent files, port-daddy, CLAUDE.md), then runs sensemaker → decomposer → skill-selector + premortem → synthesizer. When execution is approved, convert each predicted node into a skillful node prompt using skillful-node-prompt + skillful-subagent-creator, prefer live WinDAGs visualization backed by POST /api/execute and /ws/execution/:id, and fall back to ASCII only when live visualization is unavailable. Activate on: "what should I do", "what's next", "next move", "/next-move", "where should I focus", "what's the highest impact thing right now". NOT for: creating skills, debugging one specific bug, or promising topology-specific runtime behavior the current server cannot execute.

Comprehensive knowledge system for addiction recovery environments, supporting both residential and outpatient (IOP/PHP) patients. Expert in evidence-based treatment modalities (CBT, DBT, MI, EMDR, MAT), recovery resources, coping strategies, crisis intervention, family systems, and holistic wellness. Activate on "rehab", "addiction recovery", "substance abuse", "treatment center", "IOP", "PHP", "detox", "sobriety support", "MAT", "Suboxone", "methadone", "12 step", "SMART Recovery". NOT for prescribing medications (consult medical professionals), emergency overdose situations (call 911), or replacing licensed counselors/therapists.

Daily protection and relapse prevention companion for people in recovery. Expert in identifying high-risk situations, managing triggers, maintaining accountability, encouraging therapy/couples counseling investment, and building sustainable recovery habits. Activate on "relapse prevention", "staying sober", "trigger management", "recovery daily", "sobriety check-in", "high risk situation", "couples therapy recovery", "protect sobriety". NOT for active crisis (call 988 or your sponsor), prescribing medications (consult doctors), or replacing counselors/therapists.

license: Apache-2.0 NOT for unrelated tasks outside this domain.

Generate images with Google's Nano Banana family (Gemini 2.5 Flash Image, Nano Banana 2, Nano Banana Pro) using character and style references. Use when the user mentions "nano banana", "gemini image", any "gemini-*-image*" model id, character consistency for image generation, style transfer with Gemini, or multi-reference image composition. NOT for Ideogram (use existing Ideogram scripts), Qwen on Apple Silicon (see ~/.claude/QWEN_IMAGE_GUIDE.md), generic prompt engineering, or non-image Gemini calls.

Design Kafka consumer groups that survive rebalances, hit the right delivery guarantee (at-most/at-least/exactly-once), and handle poison messages without stalling the topic. Use when picking a partition assignment strategy (Range vs Sticky vs Cooperative-Sticky vs the new KIP-848 protocol), tuning heartbeat / session / max.poll.interval timeouts, choosing manual vs auto offset commits, designing dead-letter or retry topics, or migrating from Classic to the next-gen Consumer protocol. NOT for Kafka cluster ops (broker tuning, partition reassignment), schema design (Avro/Protobuf/Schema Registry), or stream processing topology (use a kafka-streams skill).

Diagnose and eliminate the GraphQL N+1 resolver explosion using Facebook DataLoader's per-request batching, plus the second-order defenses (persisted queries, depth limits, cost analysis). Use when a GraphQL query that returns N items in a list triggers N+1 database round trips, when designing nested resolvers that load associations, when a list query times out under load, or when you need to budget query cost before resolvers run. NOT for REST-style endpoint design (use api-versioning-strategy), generic database query optimization (use database-query-optimizer), or schema design (use graphql-server-architect).

Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new skills, reviewing existing skills, debugging activation failures, encoding domain expertise, designing skills for subagent consumption, or understanding platform constraints and distribution surfaces. NOT for general Claude Code features, runtime debugging, non-skill coding, or MCP server implementation.

Multi-agent coordination daemon for coding agents. Use for deterministic port claims, session tracking, salvage, file claims, notes, pub/sub, tuple-space coordination, background fleets, and debugging multi-agent failures across Claude Code, Codex, Gemini CLI, Cursor, or Windsurf. NOT for production deploy orchestration, Docker or Kubernetes networking, or cloud service discovery.

Use this skill when running SEO audits, optimizing for AI search engines (AI Overviews, ChatGPT, Perplexity), generating schema markup, diagnosing traffic drops, fixing Core Web Vitals, managing site migrations, or building keyword strategies. Runs scored full-site audits (0-100 Health Score) across 21 modules including technical SEO, E-E-A-T, hreflang, and programmatic SEO. Three modes: Audit, Plan, Execute. NOT for PPC/Ads, social media management, or generic marketing strategy unrelated to organic search.

Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new skills, reviewing existing skills, debugging activation failures, encoding domain expertise, designing skills for subagent consumption, or understanding platform constraints and distribution surfaces. NOT for general Claude Code features, runtime debugging, non-skill coding, or MCP server implementation.

Use this skill when creating a new Claude skill from scratch, editing or improving an existing skill, or measuring skill performance with evals and benchmarks. Invoke whenever the user says things like "make a skill for X", "turn this workflow into a skill", "test my skill", "improve my skill", "run evals", "benchmark this", or "optimize my skill description". Also use proactively when the conversation has produced a repeatable workflow that would benefit from being captured as a skill. Covers the full lifecycle: capture intent → draft SKILL.md → run evals → review with user → iterate → optimize description → package. NOT for general coding help, debugging runtime errors, building MCP servers, writing Claude hooks, or creating plugins — use domain-specific skills for those.

Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new skills, reviewing existing skills, debugging activation failures, encoding domain expertise, designing skills for subagent consumption, or understanding platform constraints and distribution surfaces. NOT for general Claude Code features, runtime debugging, non-skill coding, or MCP server implementation.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new skills, reviewing existing skills, debugging activation failures, encoding domain expertise, designing skills for subagent consumption, or understanding platform constraints and distribution surfaces. NOT for general Claude Code features, runtime debugging, non-skill coding, or MCP server implementation.

Guide for creating, improving, benchmarking, and packaging Claude Agent Skills (SKILL.md files). Invoke when users want to create a skill from scratch, improve or test an existing skill, benchmark skill performance with variance analysis, or optimize a skill description for triggering accuracy. Also invoke when users say "turn this into a skill", "make a skill for X", "help me write a SKILL.md", "my skill isn't firing correctly", or want to convert a workflow/conversation into a reusable skill. Invoke proactively when a conversation has produced a repeatable workflow worth capturing. If the user mentions SKILL.md, skill files, skill descriptions, or skill triggering, this skill applies.

Instruction manual for agents driving Port Daddy multi-agent coordination. Use when an agent will edit a repo, recover work, coordinate with other sessions, inspect FleetBar/Fleet Control Center truth, package skill/docs surfaces, or leave a durable handoff. NOT for generic coding that does not need Port Daddy state.

Contributor manual for agents working ON the Port Daddy codebase itself — the daemon, MCP server, FleetBar / Fleet Control Center, website, CLI surface, distribution mirrors, internal recovery ledger, and the named internal actors (Coxswain / Navigator / Cartographer / Lookout / Quartermaster + Shipwright). Use when editing the port-daddy repo. NOT for agents using Port Daddy on other projects (use port-daddy-agent-skill for that), and NOT distributed to public skill catalogs — this skill is private to the port-daddy repo.

Voice and copy guide for portdaddy.dev and Port Daddy marketing surfaces. Use when writing or editing any user-facing copy on website-v2: landing, docs, hero, CTAs, sidebar labels, page intros, ADR summaries, blog posts, email, social. NOT for internal docs (ADR bodies, code comments, CHANGELOG).

Instruction manual for agents driving Port Daddy multi-agent coordination. Use when an agent will edit a repo, recover work, coordinate with other sessions, inspect FleetBar/Fleet Control Center truth, package skill/docs surfaces, or leave a durable handoff. NOT for generic coding that does not need Port Daddy state.

Architects Port Daddy's outbound-only event relay and the zero-trust crypto stack that governs it — PKI choice (ACME vs OIDC vs Web-of-Trust), per-publisher Merkle event chains, harbor cards on the wire, Phase 3 capability attenuation, E2E payload encryption, ProVerif extension, and the V4 remote-harbor redefinition. Use when designing the relay, writing the PKI/relay/V4 ADRs, deciding PKI strategy with proponent/pragmatic/antagonist deliberation, scaffolding ACME or OIDC, building Merkle chain primitives, or extending the symbolic protocol model. NOT for implementing the local daemon, generic harbor-card refactors, Float Plan economic settlement (deferred), or generic zero-trust theory (use agentic-zero-trust-security).

Defensive security and mechanization fleet for the Port Daddy whitepapers (Bonded Commons, Anchor Protocol). Use when responding to red-team findings in a versioned round, when closing a cited-but-unmodeled proof, or when proposing the next paper version bump. NOT for ad-hoc code review — see code-reviewer skill.

Adversarial security review fleet for the Port Daddy whitepapers (Bonded Commons, Anchor Protocol). Use when a paper version is being prepared, when a coordination/cryptographic claim is being added, or when paired with the whitehat-defense skill in a versioned red-vs-white iteration round. NOT for production threat response — see SECURITY.md for incident handling.

Builds, rehabilitates, audits, and hardens premium production web apps from a durable design-system contract. Use for React, Next.js, or Vite apps, including dirty existing website repos, where token discipline, Radix or Headless UI primitives, visual user review, accessibility, Storybook, performance, SEO, observability, security, privacy, reliability, release engineering, sustainability, i18n, content depth, and adversarial verification matter. NOT for small static snippets, one-off CSS tweaks, native mobile apps, backend-only APIs, or quick mockups where production rigor is out of scope.