All authors
Claude Skills by curiositech
github.com/curiositech1,260 skills8 installs1,712 views
- Go Pprof ProfilingUse when CPU usage is high, memory grows unboundedly, goroutines leak, mutex contention shows in traces, or escape analysis suggests excess heap allocation. Triggers: net/http/pprof endpoint exposure, go tool pprof analysis, flamegraph generation, allocs vs inuse_space heap profiles, runtime/trace event timeline, mutex profiling, block profiling, goroutine dumps, GC pressure measurement. NOT for non-Go languages, distributed tracing (use OpenTelemetry skill), or production telemetry pipelines.Votes: 0GitHub stars: 2
- Gpu Hosted Asset HardeningHardening playbook for any long-lived GPU box running ML daemons (ComfyUI, Ollama, vLLM, Triton, Ray, JupyterHub, Hugging Face TGI). Covers threat model, network hardening, auth + quotas, capability sandboxing, secrets and storage, observability, patching cadence. NOT for one-shot serverless inference (use media-gen-deployment), NOT for incident response on a suspected-compromised box (use comfyui-incident-response), NOT for ecosystem-side supply-chain hygiene (use supply-chain-defense-for-ml...Votes: 0GitHub stars: 2
- Gpui Rust ConsoleBuild and extend pd-console — Port Daddy's GPU-native macOS operator console (GPUI 0.2.x, Zed's Rust UI). Covers the render-agnostic Block/Pane(Surface) contract, the two-thread reqwest↔smol refresh pipeline, Taffy flexbox layout, uniform_list virtual scroll, focus + keyboard nav, the OKLCH theme and ICS maritime flag badges, GPUI's missing text-input, and the real feature-gated cargo/CI gate. Use when adding panes, visual polish, or debugging GPUI rendering/layout/focus in core/pd-console. N...Votes: 0GitHub stars: 2
- Gpui ShadersImplement per-pixel WGSL/wgpu shader effects for a native GPUI surface, including render-to-texture or a separate GPU window. Use when an effect truly needs fragment work such as noise, SDFs, water, full-resolution dithering, or scanlines. NOT for GPUI pane/layout contracts (gpui-rust-console), element-tree animation and transitions (rust-gpui-motion), cooperative-editor architecture (build-coop-ide-gpui), or web shaders.Votes: 0GitHub stars: 2
- Grafana Dashboard BuilderUse when building Grafana dashboards backed by Prometheus, Loki, or Tempo, designing PromQL/LogQL queries, wiring template variables, setting alert rules, building SLO dashboards, or maintaining dashboards as code. Triggers: rate() vs increase() confusion, irate vs rate, label_replace, recording rules, alerting rule expressions, multi-dimensional template variables, ad-hoc filters, dashboard JSON model, provisioning via Terraform/grafonnet, p99 / histogram_quantile usage. NOT for Datadog/New ...Votes: 0GitHub stars: 2
- Graphql N Plus One DataloaderDiagnose 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-strate...Votes: 0GitHub stars: 2
- Harbor ChartworkChartwork for the Harbor library: choosing the diagram kind that fits an idea and drawing it in TikZ to the house style, with mechanical figure QA. Use when drafting, redesigning, auditing or QA-ing any figure in the chapters or research papers. NOT for matplotlib/raster plots, web SVG components, slide decks, or prose exposition.Votes: 0GitHub stars: 2
- Harbor ExpositionHouse style for writing up research results: the seven-moves-plus-two-rails template (scene, one-breath sentence, structural analogy, boxed theorem, hand-checkable numbers, application, honest boundary — with an expert express lane and mandated relation-map/regime figures). Use when drafting, reviewing, or converting any Harbor-program result, execution report, paper section, README, or technical explainer for a smart-but-uninitiated reader. NOT for API reference docs, marketing copy, code co...Votes: 0GitHub stars: 2
- Harbor ResultsCompendium of the Harbor coordination program's executed results R1–R17 — information floor, split-digest theorem, derived regret head, digest-zoom frontier, hypervisor-as-supervisory-control, sheaf equivocation verdict (with the consistency-radius theorem), inspection tower, work-unit machine, sealed-room noninterference, ε-ledger conservation, canary/SPRT detection power, no-mint reputation inheritance, engine substitution and resurrection soundness, costly-escalation tuning band, Erlang-C ...Votes: 0GitHub stars: 2
- Hierarchical Skill ReprRepresentations for hierarchical skill structures including knowledge graphs and ontological decompositionVotes: 0GitHub stars: 2
- Hierarchical Skills RepresentationUse for affordances, hierarchical control, nullspace composition, and information-seeking action selection in embodied agents. NOT for pure symbolic planning, generic RL tuning, or domains without sensorimotor grounding.Votes: 0GitHub stars: 2
- Hoare 1978 CspFoundational theory for process-oriented concurrency through synchronous message-passing, applicable to multi-agent coordination and parallel decompositionVotes: 0GitHub stars: 2
- Hong Et Al 2024 MetagptDesign explicit software-work artifacts and dependency-gated handoffs, using MetaGPT paper and v0.8.1 boundaries. NOT for claiming the paper or v0.8.1 artifacts guarantee safe autonomous software delivery.Votes: 0GitHub stars: 2
- Hono PatternsUse when building APIs on Hono (Cloudflare Workers, Bun, Deno, Node), debugging route ordering, wiring middleware, validating with @hono/zod-validator, returning streaming responses, configuring CORS with credentials, handling errors via app.onError, or composing typed RPC clients. Triggers: c.env binding types, c.header + c.redirect interaction, missing await next() bugs, Set-Cookie not attaching to redirect, route-precedence surprises, JWT middleware setup, hono/client typed RPC end-to-end....Votes: 0GitHub stars: 2
- How To Solve It PolyaUse when stuck on a hard problem, decomposition is unclear, a related problem is needed, or explicit looking-back review will improve transfer. NOT for routine execution with a known procedure, rote checklist work, or domain questions that need specialized subject matter expertise instead of heuristic search.Votes: 0GitHub stars: 2
- Hsts Planning SchedulingUse when planning, scheduling, state variables, temporal constraints, bottlenecks, or commitment-level decisions are entangled in one constrained system. NOT for lightweight to-do planning, generic project-management advice, or domains that lack explicit causal and resource constraints.Votes: 0GitHub stars: 2
- Htmx Progressive EnhancementUse when building server-driven UIs with htmx, designing hx-* attribute compositions, choosing swap strategies (innerHTML/outerHTML/morph), wiring out-of-band updates, integrating with form validation, or migrating from a SPA back to server-rendered HTML. Triggers: hx-get/hx-post setup, hx-target + hx-swap interplay, hx-trigger debouncing, OOB swaps for parts of the page outside the request target, response headers like HX-Trigger and HX-Push-Url, integration with Hyperscript or Alpine.js, ac...Votes: 0GitHub stars: 2
- Huang Et Al 2026 Six Sigma AgentApplication of Six Sigma quality methodology to AI agent process improvement and reliabilityVotes: 0GitHub stars: 2
- Hypertree PlanningBuild and evaluate a rule-guided HTP planning outline before separate leaf-content work. Use when a planning problem has reusable decomposition rules and needs an explicit outline, pruning record, and integration checks. NOT for scheduling, multi-agent coordination protocols, or database hypertree decomposition.Votes: 0GitHub stars: 2
- Ideal Web App BuilderBuilds, 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 twe...Votes: 0GitHub stars: 2
- Idempotency Key PatternsImplementing the `Idempotency-Key` HTTP header pattern (Stripe-pioneered, IETF-standardizing) so retries don't double-charge or duplicate side effects — full Postgres schema with recovery-point state machine, fingerprint check, in-progress lock with 409 response, and 24h retention. Grounded in Stripe blog/docs, the IETF httpapi WG draft, and Brandur Leach's canonical implementation. NOT for distributed sagas/transactions, event-stream exactly-once delivery, webhook dedup, or general retry/bac...Votes: 0GitHub stars: 2
- Impact Of Rapport On Intelligence YieldUse for rapport, elicitation, transcript audit, interview design, and disclosure-yield analysis by auditing attention, coordination, and typed yield instead of vague warmth or self-report. NOT for coercive extraction, generic tone polishing, or persuasion tasks that do not depend on genuine disclosure.Votes: 0GitHub stars: 2
- Incident Command Decision IntelligenceApply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.Votes: 0GitHub stars: 2
- Intercultural DiscourseCross-cultural communication frameworks for understanding discourse patterns across culturesVotes: 0GitHub stars: 2
- Interior Design ExpertExpert interior designer with deep knowledge of space planning, color theory (Munsell, NCS), lighting design (IES standards), furniture proportions, and AI-assisted visualization. Use for room layout optimization, lighting calculations, color palette selection for interiors, furniture placement, style consultation. Activate on "interior design", "room layout", "lighting design", "furniture placement", "space planning", "Munsell color". NOT for exterior/landscape design, architectural structur...Votes: 0GitHub stars: 2
- International Code Of SignalsExpert on the International Code of Signals (ICOS, Pub. 102, 1969/2003) — encode, decode, and explain maritime signals by any method (flag hoists, flashing light, sound, radiotelephony): single-letter urgent signals, the two-letter General Signal Code, the three-letter Medical Signal Code, procedure signals, Morse, phonetic alphabets, distress and lifesaving signals, MAYDAY/PAN PAN/SECURITE — plus adapting ICOS mechanisms (complete-meaning registries, complements tables, two-phase acks, prior...Votes: 0GitHub stars: 2
- Investigations Of Naturalistic Decision Makinglicense: Apache-2.0 NOT for unrelated tasks outside this domain.Votes: 0GitHub stars: 2
- Investigations Of Naturalistic Decisionlicense: Apache-2.0 NOT for unrelated tasks outside this domain.Votes: 0GitHub stars: 2
- Ipc Communication PatternsComprehensive reference for inter-process communication mechanisms -- every way processes can talk on a computer. Covers sockets (TCP, UDP, Unix domain), WebSockets, SSE, pipes (named/anonymous), shared memory (mmap, shm_open), message queues, signals, D-Bus, XPC (macOS), gRPC, REST, stdin/stdout, file-based coordination, and clipboard. Performance benchmarks, platform availability, and code examples for each. Special focus on which IPC works best for AI agent coordination. Activate on: "IPC"...Votes: 0GitHub stars: 2
- Jury Rig Bootstrap LifecycleInspect, plan, verify, or roll back Port Daddy's native Jury-rig machine bootstrap. Use for replacing retired skill-runtime instructions, preserving handwritten configuration and catalog provenance, checking an exact bootstrap receipt, or diagnosing an interrupted cutover. Not for ordinary skill search, broad text replacement, installing arbitrary plugins, or granting new machine authority.Votes: 0GitHub stars: 2
- Kafka Consumer Group DesignDesign 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...Votes: 0GitHub stars: 2
- Kieras Goms For Task AnalysisGOMS cognitive modeling methodology for analyzing human-computer interaction task performanceVotes: 0GitHub stars: 2
- Knowledge Elicitation Of Recognition Primed Decisionslicense: Apache-2.0 NOT for unrelated tasks outside this domain.Votes: 0GitHub stars: 2
- Kubernetes Debugging RunbookUse when triaging CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending pods, networking failures, ingress 502/504, PVC stuck, HPA not scaling, init-container loops, sidecar startup ordering, or "kubectl describe says nothing useful". Triggers: pod restart counts climbing, "no nodes available to schedule", "back-off restarting failed container", DNS resolution failures inside the cluster, NetworkPolicy denials, livenessProbe killing healthy pods. NOT for cluster setup (kubeadm, kops), cloud-...Votes: 0GitHub stars: 2
- Kubernetes Graceful ShutdownShutting down HTTP services in Kubernetes without dropping traffic — the SIGTERM/preStop dance, the EndpointSlice removal race, the `preStop sleep` pattern, terminationGracePeriodSeconds budgeting, and the Node.js + Go server skeletons. Grounded in kubernetes.io and language runtime docs. NOT for rollout strategies, PodDisruptionBudgets/node draining, or service-mesh sidecar lifecycle.Votes: 0GitHub stars: 2
- Lakatos Degeneracy DetectorDetects degenerating research programmes in AI skill libraries by tracking whether version changes narrow a skill's declared scope to exclude anomalies (monster-barring) rather than accommodating them through improved theory. Operationalizes Lakatos's MSRP distinction between progressive problemshifts (novel predictive content) and degenerating ones (content-decreasing post-hoc exclusions), using four instrumented signals — Scope Contraction Rate, Novel-case Coverage Ratio, Failure-Exclusion ...Votes: 0GitHub stars: 2
- Latex AuthoringWrite or revise LaTeX source for articles and technical documents: document class, math, tables, citations, semantic macros, and package selection. Use when the requested change is in .tex content or preamble. NOT for compiling or diagnosing build failures (latex-build-diagnostics), Beamer slides (latex-beamer-presentations), TikZ figures (tikz-figure-engineering), or repository PDF publication (latex-whitepaper-engineering).Votes: 0GitHub stars: 2
- Latex Whitepaper EngineeringAuthor, revise, and ship LaTeX whitepapers in repos that publish committed PDFs behind a metadata registry. Covers the full loop: editing .tex with thebibliography discipline, two-pass pdflatex builds, catching undefined citations/references from the log, source→published PDF naming, version/date title blocks bumped in lockstep with the site registry, and Math.round(bytes/1024) size sync against metadata drift checks in CI. Use when editing website-v2/public/whitepaper/*.tex in port-daddy or ...Votes: 0GitHub stars: 2
- Launch Readiness AuditorAssess software launch readiness through evidence-backed checks of product flow, reliability, security, operations, and release risk.Votes: 0GitHub stars: 2
- Law Enforcement Decision Making During Crisislicense: Apache-2.0 NOT for unrelated tasks outside this domain.Votes: 0GitHub stars: 2
- Layout Overflow GuardMechanically detect text overlap, overflow, truncation, and horizontal page scroll in any HTML page or web artifact — before shipping it. Purely geometric: renders headlessly and measures tight glyph-level bounding boxes from Range.getClientRects(), then flags text-vs-text collisions, clipped/ ellipsis-truncated elements, text escaping its container, and body horizontal scroll. No LLM, no vision. Use whenever you produce or edit a UI, Artifact, HTML page, dashboard, chart, or component, and A...Votes: 0GitHub stars: 2
- Legibility For Agentic SystemsMake a swarm of autonomous coding agents LEGIBLE to one human operator without high-modernist over-flattening. Applies James C. Scott's *Seeing Like a State* (legibility, mētis, high-modernism) and Hobbes' *Leviathan* (state of nature -> consented authority) to multi-agent software systems. Core discipline: DIGEST-WITH-ZOOM — every summary is a lens onto the real artifact (diff, reasoning trace, claim row), never a replacement for it. Use when designing read-surfaces, dashboards, attention qu...Votes: 0GitHub stars: 2
- Legible Roadmap With SidequestsSteward one canonical product roadmap while honoring an ADHD operator's energy-driven sidequests, using a link-or-opt-out discipline so every unit of work — planned or impromptu — stays traceable to real commits, PRs, or receipts. Use when designing how a roadmap coexists with burst-energy work, building a reconciliation cadence that folds sidequests back into the plan, or diagnosing a roadmap that has become either a rigid planning cage or an ignored wishlist. NOT for per-item issue-tracker ...Votes: 0GitHub stars: 2
- Liu 2023 AgentbenchComprehensive benchmark suite for evaluating LLM agents across diverse interactive environmentsVotes: 0GitHub stars: 2
- Llm Evaluation HarnessBuild automated LLM evaluation pipelines with benchmarks, regression tests, RAGAS, and human eval workflows. Activate on: LLM evaluation, benchmark testing, eval pipeline, RAGAS, model regression tests. NOT for: traditional software testing (testing-expert), model training (ai-engineer).Votes: 0GitHub stars: 2
- Local First Tenancy BoundaryAudits a product's local-first account/tenancy model: whether every identity-gated feature keeps a real local-only path, whether every scope-tier crossing (private -> repo -> team -> public) shows an explicit data-boundary consent screen, whether the "local-only mode uploads nothing" claim is runtime-testable rather than asserted, whether export/delete controls exist per tier, and whether the scope ladder is declared as one ordered source of truth. Use when designing or reviewing account crea...Votes: 0GitHub stars: 2
- Logging ObservabilityStructured logging, distributed tracing, and metrics for production applications. [What: OpenTelemetry setup, log level strategy, correlation IDs, SLI/SLO alerting thresholds, Grafana dashboard design, PagerDuty integration] [When: setting up production logging, adding observability to a service, debugging distributed systems, designing alerting, implementing traces/metrics/logs] [Keywords: logging, observability, OpenTelemetry, OTel, structured logs, distributed tracing, correlation ID, metr...Votes: 0GitHub stars: 2
- Logical Fallacy DetectorIdentify, label, and explain logical fallacies in arguments and discourse. Use when the user wants to analyze arguments, check reasoning, evaluate debate claims, spot weak arguments, do debate prep, policy writing, or conflict analysis. Triggers on 'fallacy', 'logical error', 'faulty reasoning', 'argument flaw', 'is this valid', 'check this logic'. Works on both formal deductive errors and informal reasoning mistakes.Votes: 0GitHub stars: 2
- Lora Training 2026End-to-end LoRA/QLoRA fine-tuning for open-weight models in 2026 — picks a base model from its strengths/weaknesses, assesses whether to train locally or in the cloud and sets up either, runs the training, and visualizes both the dataset and base-vs-tuned outputs. Use when fine-tuning, training a LoRA/QLoRA/DoRA adapter, choosing a base model, deciding local-vs-cloud GPU, or previewing training data and results. NOT for full-parameter pretraining, closed-model API fine-tuning (OpenAI/Gemini),...Votes: 0GitHub stars: 2
- Macaroon Capability CredentialsImplement macaroons (Birgisson et al. 2014) as unforgeable, attenuate-only bearer capability credentials, with cross-language byte-parity. Use for capability tokens, bearer-credential attenuation, third-party caveats + discharge gates, delegation chains, "rent-paid"/compulsion caveats, or keeping a Rust and a TypeScript macaroon impl byte-identical via shared test vectors. Covers HMAC-chained first-party caveats, the two vid (verification-id) constructions (HMAC commitment vs AES-GCM sealing)...Votes: 0GitHub stars: 2