All authors
Claude Skills by curiositech
github.com/curiositech1,260 skills8 installs1,712 views
- Macos Host SecurityDesign or review macOS host safety for agents and downloaded executables. Use for Endpoint Security and eslogger, Network Extension and pf egress, codesign/quarantine checks, TCC and Full Disk Access, secret scanning with structured formats and entropy, Santa binary lockdown, or Port Daddy's `pd safe` design. Covers the read-only versus privileged trust boundary. NOT for generic Rust compiler work (use rust-development-workflow), web security (use agentic-zero-trust-security), or prompt-injec...Votes: 0GitHub stars: 2
- Macos Launchd SupervisionAuthor correct macOS launchd plists for long-lived local daemons and design the EXTERNAL supervision-integrity check that catches what KeepAlive cannot self-heal: the supervising job itself getting unloaded. Use when writing or reviewing a LaunchAgent/LaunchDaemon plist, debugging a daemon that "silently died" after a brew upgrade or logout, choosing LaunchAgent vs LaunchDaemon, or fixing launchd's minimal-PATH "command not found" failures. NOT for systemd/Linux unit files, Windows services, ...Votes: 0GitHub stars: 2
- Make Copy And Media HumanReview and rewrite copy, web UI, slides, READMEs, commits, PRs, marketing pages, educational chapters, class materials, notebooks, and generated media to strip AI-isms — Claudeisms, GPT-isms, Codexisms, Geminisms, engineering-artifact slop, and the v0/Lovable design look — producing a line-item fix plan as static HTML. Use before shipping any outward-facing text or design, when something "reads like AI", or when auditing a property for machine tells. NOT for grammar/spell checking, SEO optimi...Votes: 0GitHub stars: 2
- Manager Driven Team OrchestratorDesigns and audits bounded manager-led synthesis over frozen evidence packets, with independent positions, reciprocal steel-man review, durable dissent, correction tickets, and fresh engineering, product, and design beats. Use for constitutional or architecture conventions. NOT for spawning agents, running teams, selecting runtime topology, managing people, fixed writer-reviewer workflows, or manager self-approval.Votes: 0GitHub stars: 2
- Mastering The Game Of Go With Deep Neural Networkslicense: Apache-2.0 NOT for unrelated tasks outside this domain.Votes: 0GitHub stars: 2
- Mcp Server DesignUse when designing, building, or debugging a Model Context Protocol (MCP) server in Node/TypeScript. Triggers: stdio JSON-RPC handshake, tool descriptions as discovery surface, lazy startup vs eager catalog loading, telemetry placement, schema design for tool inputs (zod), tool naming conventions for discoverability, error handling that does not leak stack traces, MCP client compatibility (Claude Desktop, Claude Code, Cursor), local resource fetching, secrets and env var handling, distributin...Votes: 0GitHub stars: 2
- Mcp Trust BrokerVet a third-party MCP server before it can run: install-card completeness (manifest, provenance, permission label, health check, disable/repair/uninstall, usage trace), signature verification, least-privilege capability mapping, a sandbox smoke test, quarantine-until-reviewed, and team allow/approve/block policy. Use when a new MCP server is discovered or proposed for the fleet's tool palette, when a server requests to exit quarantine and run for real, or when auditing whether an MCP install ...Votes: 0GitHub stars: 2
- Mechanism Design For Agent LaborDesign bond pricing functions, escrow mechanics, and settlement protocols for AI agent labor markets. Use when pricing Float Plan bonds, designing collateralized work contracts, analyzing incentive compatibility, building settlement oracles, or designing marketplace dynamics for agentic task completion. Grounded in mechanism design theory (Hurwicz, Maskin, Myerson — Nobel 2007), Vickrey auctions, game theory for multi-agent systems (Nisan et al. 2007), and the Port Daddy Bonded Commons protoc...Votes: 0GitHub stars: 2
- Media Gen DeploymentServe generative image, video, and audio workloads in production — Modal, Replicate, fal.ai, RunPod, Beam, Baseten, Cloudflare Workers AI/R2/Queues/Containers, plus self-hosted (Vast/Lambda/CoreWeave). Activate on: deploy diffusion model, host ComfyUI API, Modal GPU, Replicate Cog, fal serverless, RunPod handler, Cloudflare Workers AI, R2 storage, GPU cold start, image gen API, video gen serving, ML inference cost optimization, GPU rental pricing, network volumes for weights. NOT for: trainin...Votes: 0GitHub stars: 2
- Mediator Expertise Live Interview Methodlicense: Apache-2.0 NOT for unrelated tasks outside this domain.Votes: 0GitHub stars: 2
- Metal Shader Expert20 years Weta/Pixar experience in real-time graphics, Metal shaders, and visual effects. Expert in MSL shaders, PBR rendering, tile-based deferred rendering (TBDR), and GPU debugging. Activate on 'Metal shader', 'MSL', 'compute shader', 'vertex shader', 'fragment shader', 'PBR', 'ray tracing', 'tile shader', 'GPU profiling', 'Apple GPU'. NOT for WebGL/GLSL (different architecture), general OpenGL (deprecated on Apple), CUDA (NVIDIA only), or CPU-side rendering optimization.Votes: 0GitHub stars: 2
- Metal Text PipelineDecide HOW LOW to go for a bare-metal 2D/text rendering pipeline on Apple GPUs, and pay the right costs. Covers the layered choice — pure objc2-metal + hand-written MSL (own command queue, glyph atlas, frame pacing) vs wgpu (Metal under the hood, cross-platform) vs Vello-on-wgpu (compute vector renderer you don't have to write) — plus CAMetalLayer/CADisplayLink frame pacing, ProMotion 120Hz, the glyph-atlas / signed-distance-field text problem, CPU-GPU sync, and honest cost accounting of "pur...Votes: 0GitHub stars: 2
- Modern Drug Rehab ComputerComprehensive 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 ...Votes: 0GitHub stars: 2
- Multi Agent Authoring Product BarDefine and measure the product-quality bar a multi-agent authoring tool must clear before its own makers reach for it over Claude Code or Codex for real work — table-stakes parity on the single-agent loop, real (non-Potemkin) coordination differentiators, and an honest dogfood-retention signal. Use when auditing whether a swarm/console feature is ready to replace an incumbent, sequencing roadmap between inner-loop parity and coordination-plane work, or reviewing a "we dogfood our own tool" cl...Votes: 0GitHub stars: 2
- Multi Agent CoordinationCoordinate multiple AI agents working on the same codebase or project simultaneously. Covers git worktree isolation, file locking strategies, message passing between agents, shared state management, conflict resolution, task decomposition for parallel agents, and patterns from Claude Code, Cursor, Devin, and similar multi-agent developer tools. Activate on: "multi-agent", "parallel agents", "agent coordination", "worktree isolation", "concurrent agents", "file locking agents", "agent conflict...Votes: 0GitHub stars: 2
- Nano Banana Image GenGenerate 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 Gem...Votes: 0GitHub stars: 2
- National Expungement ExpertDeep expertise in criminal record expungement laws across all 50 US states and DC. Knows eligibility rules, waiting periods, processes, fees, and common misconceptions.Votes: 0GitHub stars: 2
- Native App DesignerCreates breathtaking iOS/Mac and web apps with organic, non-AI aesthetic. Expert in SwiftUI, React animations, physics-based motion, and human-crafted design. Use for iOS/Mac app UI, React/Vue animations, native-feel web apps, physics-based motion design. Activate on "SwiftUI", "iOS app", "native app", "React animation", "motion design", "UIKit", "physics animation". NOT for backend logic or API design (a non-visual backend concern), simple static sites (use web-design-expert), or design-syst...Votes: 0GitHub stars: 2
- Naturalistic Decision MakingField-based research methodology studying expert decision-making in real-world high-stakes environmentsVotes: 0GitHub stars: 2
- Naturalistic InsightResearch on how insights and creative solutions emerge naturally during problem-solving and expertiseVotes: 0GitHub stars: 2
- Nau Au Kuter 2003 Shop2SHOP2 hierarchical task network planner for automated planning through recursive task decompositionVotes: 0GitHub stars: 2
- Ndm Decision ModelsModels of naturalistic decision-making including recognition-primed decisions, sensemaking, and mental simulationVotes: 0GitHub stars: 2
- Ndm Law EnforcementApplication of naturalistic decision-making research to law enforcement expertise and field decisionsVotes: 0GitHub stars: 2
- Neobrutalist Web DesignerModern web applications with authentic neobrutalist aesthetic. Bold typography, hard shadows (no blur), thick black borders, high-contrast primary colors, raw visual tension. Extrapolates neobrutalism to SaaS dashboards, e-commerce, landing pages, startup MVPs. Activate on 'neobrutalism', 'neubrutalism', 'brutalist', 'bold borders', 'hard shadows', 'raw aesthetic', 'anti-minimalism', 'gumroad style', 'figma style'. NOT for glassmorphism (use vaporwave-glassomorphic-ui-designer), Windows retro...Votes: 0GitHub stars: 2
- Next Move Customer PersonaDeep understanding of /next-move customer personas — who needs AI that tells them what to work on next. Developers with ADHD, overwhelmed project leads, consultants juggling codebases, indie hackers who context-switch. Activate on 'next-move customer', 'who needs next-move', 'task prioritization persona', 'developer decision fatigue', 'what should I work on', 'ADHD developer tools', 'context switching pain'. NOT for WinDAGs orchestration personas (use windags-customer-persona), marketing exec...Votes: 0GitHub stars: 2
- Next MovePredicts 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 Jury-rig visualization backed by POST /api/execute and /ws/execution/:id, and fall ba...Votes: 0GitHub stars: 2
- Nisan Et Al 2007 Algorithmic Game TheoryFrame a computational mechanism-design or equilibrium question using the Algorithmic Game Theory literature: private information, allocation, payments, incentive compatibility, efficiency, and computation. Use for a literature-grounded analysis, not for automatic prescription of VCG, proportional allocation, reputation, or an equilibrium algorithm. NOT for advisory file-claim games without payments (game-theoretic-agent-incentives).Votes: 0GitHub stars: 2
- Node Memory Leak HuntingUse when a Node.js process is growing memory unbounded in production, hits OOM, restarts on schedule, or shows monotonic RSS in Grafana. Triggers: heap snapshot diff (Comparison mode in Chrome DevTools), v8.writeHeapSnapshot, --heapsnapshot-signal=SIGUSR2, clinic doctor / clinic heap, Allocation sampling vs Allocation instrumentation timeline, --max-old-space-size, retainers / dominators, EventEmitter listener leak, closures over big objects, Buffer.allocUnsafe, intern caches that never evict...Votes: 0GitHub stars: 2
- Normative Bdi Agent ArchitectureApply normative BDI reasoning to agents that must detect norms, choose which commitments to internalize, and resolve conflicts by comparing consequences. Use when obligations, prohibitions, or policies collide in autonomous systems. NOT for simple fixed-priority rules, pure constraint satisfaction, or domains where no real normative conflict exists.Votes: 0GitHub stars: 2
- Normative Bdi AgentsA framework for building rational agents that can recognize, evaluate, and selectively adopt norms while resolving conflicts through consequence-based reasoning. Enables agents to make principled decisions when rules, obligations, and goals are mutually incompatible.Votes: 0GitHub stars: 2
- Nygard 2018 Release It 2nd EditionProduction stability patterns including circuit breakers, bulkheads, and resilience strategies for real-world systemsVotes: 0GitHub stars: 2
- Oauth2 And Oidc From ScratchUse when implementing or reviewing OAuth 2.0 / OAuth 2.1 / OpenID Connect from scratch in a real codebase, choosing a flow (authorization code + PKCE, client credentials, BFF), validating ID tokens, storing tokens safely in browsers, sizing refresh-token rotation, or migrating off implicit / ROPC. Triggers: "should I use a JWT or session cookie", PKCE code_challenge/code_verifier, exact redirect_uri match, state vs nonce confusion, ID-token replay, refresh-token rotation, BFF (backend-for-fro...Votes: 0GitHub stars: 2
- Observability Absences AuditAudit a service or daemon for observability ABSENCES — what should be logged, audited, or alarmed but isn't — across security trails, coordination integrity, resource self-monitoring, failure visibility, and request/actor/tenant correlation. Use when reviewing a multi-tenant coordination service before dogfooding or GA, when tenant_id or a requestId is missing from logs, or when a defined event enum never fires (a silent event). Keywords: observability gap, missing audit log, no tenant_id, si...Votes: 0GitHub stars: 2
- Olog ConstructionBuild ontology logs (ologs) from problem descriptions using categorical foundations. Use when designing problem taxonomies, classifying tasks for routing, building knowledge libraries, establishing formal analogies between domains via functor search, or translating between natural language and database schemas. Grounded in Spivak (MIT 2012, 2014). NOT for general ontology engineering (OWL/RDF), knowledge graphs without categorical structure, or database administration.Votes: 0GitHub stars: 2
- Ongaro Ousterhout 2014 RaftApply Raft's design principles for building understandable, reliable distributed and multi-agent systemsVotes: 0GitHub stars: 2
- Openai DocsUse for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat/Work/Codex comparisons. Do not use for generic app/software tasks that merely mention Codex.Votes: 0GitHub stars: 2
- Opentelemetry InstrumentationUse when adding distributed tracing, debugging missing spans, fixing W3C traceparent propagation, configuring OTLP exporters (gRPC vs HTTP), choosing sampling strategies, setting resource attributes, or wiring auto-instrumentation libraries. Triggers: spans missing in Datadog/Honeycomb/Jaeger, "service.name = unknown_service", trace assembly broken across services, async work losing context, OTLP collector unreachable, sampling rate decisions, ESM vs CJS auto-instrumentation loader bugs. NOT ...Votes: 0GitHub stars: 2
- Operad Task DecompositionModel hierarchical task composition with typed interfaces and colored operads. Use when designing multi-agent decompositions, checking subworkflow boundaries, or distinguishing formal substitution from scheduling and execution semantics. Covers wiring diagrams, explicit artifact bindings, and an acyclic task-workflow model. NOT for runtime orchestration, proving agent correctness, or general category theory education.Votes: 0GitHub stars: 2
- Operator Surface Authority DesignerDecide which single operator surface — Scout, FleetBar, or pd-console — owns each capability by its distance-from-work (intake/ambient/deep), and audit that placement for authority spread, unenforceable controls, evidence overflow into FleetBar, and hot/cool bus-subscription mismatches. Use when placing a new capability on one of Agent Harbor's three operator surfaces, reconciling a mockup that duplicates a capability across two surfaces, or auditing an existing operator-surface spec before i...Votes: 0GitHub stars: 2
- Ostrom Commons GovernanceApply Elinor Ostrom's 8 design principles for governing commons to software architecture and AI agent coordination systems. Use when auditing shared-resource systems for governance gaps, designing agent commons (shared ports, files, channels), evaluating whether a coordination daemon satisfies self-governance properties, or building graduated-sanction regimes for misbehaving agents. NOT for environmental policy, fisheries management, general political science, or organizational management con...Votes: 0GitHub stars: 2
- Outbox Pattern ImplementationUse when you need to publish a message to Kafka / RabbitMQ / SNS atomically with a database commit, when fixing the dual-write hazard between DB and broker, deciding between polling-publisher and CDC (Debezium) relay, designing the outbox schema, handling at-least-once / idempotency on the consumer, or pruning a high-volume outbox table. Triggers: dual write, "we updated the DB but the event never published", outbox/inbox pattern, Debezium connector, EventRouter SMT, aggregate_type / aggregat...Votes: 0GitHub stars: 2
- Panic Room FinderExpert in residential hollow space detection, hidden room discovery, and safe room planning. Helps map house dimensions, identify anomalies suggesting hidden spaces, and safely explore potential voids. Knowledge of architectural history, construction methods, and non-destructive investigation techniques. Activate on "panic room", "hidden room", "secret room", "hollow space", "house mapping", "find hidden space", "room dimensions", "hidden door", "false wall", "priest hole", "prohibition era",...Votes: 0GitHub stars: 2
- Park 2023 Generative AgentsAnalyze Park et al. (2023) simulation agents with memory, retrieval, reflection, and planning. Use for source-bound agent-simulation design and diagnostic traces. NOT for claims about real human cognition, factual truth, safe autonomy, or general social-coordination guarantees.Votes: 0GitHub stars: 2
- Partner Text CoachReal-time communication coach for navigating partner/relationship texts. Analyzes incoming messages for emotional subtext, suggests thoughtful responses, helps de-escalate conflict, and provides follow-up conversation strategies. Expert in attachment theory, nonviolent communication (NVC), Gottman research, and healthy relationship dynamics. Activate on "what should I say", "how to respond", "partner text", "relationship message", "what does this mean", "text my partner", "conversation with p...Votes: 0GitHub stars: 2
- Pd Relay Zero TrustArchitects 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 cha...Votes: 0GitHub stars: 2
- Personal Finance CoachExpert personal finance coach with deep knowledge of tax optimization, investment theory (MPT, factor investing), retirement mathematics (Trinity Study, SWR research), and wealth-building strategies grounded in academic research. Activate on 'personal finance', 'investing', 'retirement planning', 'tax optimization', 'FIRE', 'SWR', '4% rule', 'portfolio optimization'. NOT for tax preparation services, specific securities recommendations, guaranteed return promises, or replacing licensed financ...Votes: 0GitHub stars: 2
- Pet Memorial CreatorCompassionate support for pet loss, memorial creation, and honoring the bond between humans and their animal companions. Specializes in tribute writing, keepsake ideas, and navigating the unique grief of losing a pet.Votes: 0GitHub stars: 2
- Photo Composition CriticExpert photography composition critic grounded in graduate-level visual aesthetics education, computational aesthetics research (AVA, NIMA, LAION-Aesthetics, VisualQuality-R1), and professional image analysis with custom tooling. Use for image quality assessment, composition analysis, aesthetic scoring, photo critique. Activate on "photo critique", "composition analysis", "image aesthetics", "NIMA", "AVA dataset", "visual quality". NOT for photo editing/retouching (use native-app-designer), g...Votes: 0GitHub stars: 2
- Photo Content Recognition Curation ExpertExpert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition, perceptual hashing for de-duplication, screenshot/meme detection, burst photo selection, and quick indexing strategies. Activate on 'face recognition', 'face clustering', 'perceptual hash', 'near-duplicate', 'burst photo', 'screenshot detection', 'photo curation', 'photo indexing', 'NSFW detection', 'pet recognition', 'DINOHash', 'HDBSCAN faces'. NOT for GPS-based lo...Votes: 0GitHub stars: 2
- Physics Rendering ExpertReal-time rope/cable physics using Position-Based Dynamics (PBD), Verlet integration, and constraint solvers. Expert in quaternion math, Gauss-Seidel/Jacobi solvers, and tangling detection. Activate on 'rope simulation', 'PBD', 'Position-Based Dynamics', 'Verlet', 'constraint solver', 'quaternion', 'cable dynamics', 'cloth simulation', 'leash physics'. NOT for fluid dynamics (SPH/MPM), fracture simulation (FEM), offline cinematic physics, molecular dynamics, or general game physics engines (u...Votes: 0GitHub stars: 2