Recently added
Plugins grouped by the day they were added to the directory, newest first.
Sep 15, 2026
- corporate-development-ma7stars
Corporate Development & M&A team — agents (corpdev-lead, ma-diligence-lead, integration-pmi-strategist), skills, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A buy-side deal team for a corp-dev, strategy, or finance lead: it frames the deal thesis before the model, triangulates valuation (DCF + trading comps + precedent transactions), runs diligence to confirm or kill the thesis, and prices integration risk pre-signing. Decision-support, not legal, tax, accounting, or a fairness opinion; multiples/comps/regulatory specifics are volatile + jurisdictional, retrieval-dated + verify-at-use; no MNPI. Distinct from startup-fundraising, finance, and treasury-management. Inherits ravenclaude-core protocols. Requires ravenclaude-core@>=0.7.0.
Claude Code4 skills Conversational voice-AI engineering team — agents for production real-time voice agents: voice-ai-architect (cascade STT->LLM->TTS vs speech-to-speech, the latency budget, turn-taking / barge-in / endpointing, channel choice, build-vs-platform across Twilio / Vapi / Retell / LiveKit / Pipecat, guardrails), speech-pipeline-engineer (ASR & TTS provider choice, streaming transcription, VAD/endpointing, diarization, prosody/SSML, codecs, noise, WER), and dialog-and-integration-engineer (state, LLM orchestration and mid-call tool calling, SIP/PSTN telephony, IVR/DTMF, call routing, flow testing and eval). Ships skills, a knowledge bank (Mermaid decision trees + a dated 2026 reference), best-practices, templates, commands. Engineering judgment, not legal/compliance advice; the ASR/TTS/platform/telephony landscape is volatile — versions and latency numbers carry a retrieval date + [verify-at-use]; no PII, and call audio/transcripts are sensitive. Requires ravenclaude-core@>=0.7.0.
Claude Code4 skillsGeneral-contractor project delivery team — agents covering the full GC lifecycle: project P&L/billing/closeout (gc-project-lead), takeoff/bid assembly/markup (estimating-and-takeoff-analyst), CPM scheduling/critical-path/float (scheduling-engineer), submittal log/RFIs/change-order process (submittal-rfi-coordinator), and jobsite safety/JHA/OSHA hazard prevention (jobsite-safety-advisor). Ships skills (estimating-and-bidding, cpm-scheduling, submittals-rfis-change-orders), commands, templates, a decision-tree knowledge bank, best-practices, an advisory anti-pattern hook, and a stdlib calculator. Inherits ravenclaude-core protocols.
Claude Code3 skillsComputer-vision engineering team — agents for a production vision build: cv-systems-architect (task framing across classification / detection / segmentation / OCR / tracking / VLM, data & annotation strategy, build-vs-API and deployment-target choice, eval-metric design — mAP / IoU / precision-recall), cv-model-engineer (dataset curation, augmentation, transfer learning, model selection across YOLO / DETR / SAM / CLIP / ViT, active learning, the eval harness, drift), and vision-deployment-engineer (quantization / distillation, ONNX / TensorRT / CoreML / TFLite export, edge/embedded targets, streaming-video pipelines, latency). Vision-specific vs the MLOps-broad ml-engineering. Ships skills, a knowledge bank (Mermaid decision trees + a dated 2026 reference), best-practices, templates, commands. Engineering judgment, not a benchmark verdict; model/hardware/runtime specifics carry a retrieval date + [verify-at-use]; no PII, no image data stored. Requires ravenclaude-core@>=0.7.0.
Claude Code4 skills- commercial-real-estate7stars
Commercial Real Estate specialist team — agents (cre-engagement-lead, acquisitions-underwriter, asset-property-manager, cre-market-analyst), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. An acquisitions-and-asset-management team for a CRE owner, operator, or advisor — it underwrites a deal to in-place NOI, prices the cap-rate-vs-Treasury spread, reads the bifurcated vacancy, decomposes net effective rent, and stress-tests the debt and refinance wall before a board sees the IC memo. Inherits ravenclaude-core protocols.
Claude Code5 skills - cloud-native-kubernetes7stars
Cloud-native & Kubernetes team — agents (kubernetes-architect, container-build-engineer, k8s-platform-operator, service-mesh-networking-engineer) for running workloads on Kubernetes well: workload design (Deployment/StatefulSet/Job, probes, requests/limits, PDBs, HPA/VPA), container build hygiene (minimal non-root images, distroless, multi-stage), platform ops (namespaces, RBAC, network policies, resource quotas, admission control, upgrades), and service-mesh networking (ingress/gateway, mTLS, traffic-splitting, observability). Cloud-agnostic. skills, a decision-tree knowledge bank (workload-type + ingress trees + a dated 2026 ecosystem map), best-practices, templates, commands, an advisory hook. Seams: managed control plane (AKS/EKS/GKE) -> azure/aws/gcp-cloud, GitOps reconcile -> devops-cicd, telemetry/SLOs -> observability-sre. Requires ravenclaude-core@>=0.7.0.
Claude Code6 skills - clinical-trials7stars
Clinical Trials specialist team — agents (trials-engagement-lead, protocol-design-specialist, clinical-operations-manager, regulatory-submissions-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A clinical-operations team for a sponsor, CRO, or site network — it designs feasible protocols (because eligibility criteria drive the enrollment failure that hits two-thirds of sites), plans patient recruitment against a ~$6,533 per-patient cost (and ~$19,533 to replace), manages site activation and the ~30% dropout, and frames the regulatory submission the way a study where 80% run late demands. Inherits ravenclaude-core protocols.
Claude Code5 skills - cli-tooling-engineering7stars
CLI-tooling-engineering team — agents (cli-architect, cli-implementation-engineer, tui-engineer, cli-distribution-engineer) for command-line tools and TUIs that feel native to the shell: the command/subcommand + flag/positional surface, config precedence (flags > env > file > default), the output contract (human by default, --json on demand, exit codes as an API, data->stdout/diagnostics->stderr, NO_COLOR/TTY detection), stdin, signal handling, TUIs (Ink / Bubble Tea / Textual / ratatui) with a non-TTY fallback, shell completions, and distribution (single static binary, Homebrew / Scoop / winget / npm / pipx, --version + update path). skills, a knowledge bank (command-surface + output/exit-code + framework + distribution decision trees + a dated 2026 map), best-practices, templates, commands, an advisory hook. Seams: service logic -> backend-engineering, release/signing -> devops-cicd, GUI sibling -> desktop-app-engineering, docs -> technical-writing-docs. Requires ravenclaude-core@>=0.7.0.
Claude Code5 skills - claude-app-engineering7stars
Claude app-engineering specialist team — agents (claude-solution-architect, prompt-and-context-engineer, mcp-and-server-tools-engineer, agent-sdk-engineer, eval-engineer, claude-app-ops-engineer) for building production applications on the Claude API, the Claude Agent SDK, and MCP. Covers the build-surface decision (Messages API / Agent SDK / Managed Agents), model right-sizing (Opus 4.8 / Sonnet 4.6 / Haiku 4.5, 1M context), prompt caching, tool use + structured output, MCP server authoring + Anthropic-hosted server tools (computer use, code execution, Files API, memory), evals (golden sets, LLM-as-judge), and FinOps + reliability (batch, model routing, backoff, observability). dated-and-cited knowledge bank, templates, an advisory hook (house opinions). Seams: prompt-as-artifact, security, and cross-domain architecture escalate to ravenclaude-core. Requires ravenclaude-core@>=0.7.0.
Claude Code7 skills - chiropractic-practice7stars
Chiropractic practice operations & compliance team — agents (chiropractic-practice-lead, chiro-billing-compliance-specialist) across the two engines of a DC office: the practice (capacity & scheduling to the care plan, the cash / insurance / wellness-plan model, membership pricing, patient-visit-average & plan-completion retention) and coding/compliance (CMT vs E&M by region, documented medical necessity via the PART exam, the active-vs-maintenance plateau call, ABN workflow, audit-defensible notes). skills, a decision-tree knowledge bank (a billing-and-medical-necessity Mermaid tree + a dated 2026 payer/coding reference), best-practices. Operations & coding decision-support, NOT medical/legal/billing advice and NOT a coding certification; no PHI; scope/coverage/coding rules are state/payer-specific + volatile — retrieval-dated + verify-at-use, flagged for a licensed professional. Seams: physical-therapy-rehab-clinic, medical-revenue-cycle. Requires ravenclaude-core@>=0.7.0.
Claude Code3 skills Childcare / early-education center operations team — agents (childcare-center-lead, enrollment-and-family-manager, classroom-ratio-compliance-advisor) for the three engines of an early-education center: the operations & tuition model (enrollment/waitlist, capacity vs licensed ratios, staffing to ratio, family retention, P&L), the enrollment & family funnel (tour-to-enroll conversion, waitlist, paperwork, family communication, tuition & CCDF/state subsidy billing), and ratio & licensing compliance (ratio and group-size by age, licensing readiness, staff qualifications, health & safety, incident documentation). skills, a decision-tree knowledge bank (Mermaid trees + a dated 2026 reference), best-practices, templates, commands. ADVISORY operations knowledge, not legal, licensing, or financial advice; state-specific ratios, group sizes, and subsidy rules are volatile and carry a retrieval date + verify-at-use; no child or family PII. Requires ravenclaude-core@>=0.7.0.
Claude Code4 skillsChaos-engineering & resilience team — agents that make distributed systems survive failure. resilience-architect owns the DESIGN side: failure-mode analysis (FMEA), resilience patterns (timeouts, retries with backoff+jitter, bulkheads, circuit breakers, load shedding, graceful degradation, idempotency), the observability-maturity gate for whether you're ready to run chaos, and redundancy/DR (multi-AZ/region, failover, RTO/RPO). chaos-experiment-engineer owns the EXPERIMENT + VERIFICATION side: hypothesis-driven experiments, blast-radius containment (automatic abort/rollback), game days, fault injection (latency/error/resource/dependency-outage/partition/zone), and verifying the pattern held under load+fault. skills, a knowledge bank (decision trees + a dated 2026 patterns reference), templates. Distinct from observability-sre (metrics/SLO/on-call — a hard prerequisite), devops-cicd (progressive delivery), performance-engineering (load), incident-response-dfir. Requires ravenclaude-core@>=0.7.0.
Claude Code3 skills- cannabis-operations7stars
Cannabis Operations specialist team — agents (cannabis-engagement-lead, seed-to-sale-compliance-specialist, dispensary-retail-operations-specialist, cannabis-finance-analyst), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A compliance-and-retail-operations team for a licensed cannabis operator — it runs seed-to-sale traceability against the state track-and-trace system (Metrc/BioTrack/LeafData), manages the 280E tax burden that makes COGS allocation existential, runs dispensary retail on margin and basket, and reads a ~$45B U.S. market where the rules change at the state line. Inherits ravenclaude-core protocols.
Claude Code5 skills Browser-extension-engineering team — agents (extension-architect, extension-implementation-engineer) for building, shipping, and maintaining cross-browser extensions on Manifest V3: the service-worker background model (and the MV2->MV3 lifecycle trap), content-script isolation + message passing, the permissions/host-permissions model and least-privilege posture, storage, the Chrome Web Store / Edge Add-ons / Firefox AMO review pipelines, and the WebExtensions cross-browser delta. Distinct from frontend-engineering (app-grade React UI) and desktop-app-engineering (Electron/Tauri). skills (build-browser-extension, manifest-permissions-audit, store-submission-readiness), a knowledge bank (a where-should-this-logic-live tree across the four MV3 contexts, MV3 architecture + a permissions-minimization tree, a dated cross-browser note), best-practices. Security verdicts escalate to security-engineering. Requires ravenclaude-core@>=0.7.0.
Claude Code3 skills- brand-identity-studio7stars
Standalone brand-CREATION service for a web studio's commission customers — agents (brand-strategist, identity-systems-designer): strategy/positioning/archetype, naming & tagline, curated logo suite, color/type systems (WCAG-paired), brand book, legal/IP posture, collateral, sellable tiers. AI-drafts + MANDATORY human curation. Thin orchestration layer: delegates design tokens to web-design:design-tokens-scaffolding, raw generation + license/indemnity to generative-web-media, and hands the finished system to web-design:visual-designer. skills, commands, a knowledge bank (Mermaid trees), best-practices, templates, a stdlib WCAG-pair checker, an advisory hook. Not legal advice — every IP / font-license / registrability claim routes to security-reviewer. Prices [unverified]. Requires ravenclaude-core@>=0.7.0.
Claude Code5 skills Blockchain & Web3 Engineering specialist team — agents (web3-architect-lead, smart-contract-security-analyst, gas-optimization-specialist, protocol-economics-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A Web3 team for an engineer or protocol architect accountable for a contract system that holds value — it treats deploy as irreversible and audit as the gate, holds reentrancy/access-control/arithmetic as the top vuln classes, reads gas as UX and cost, and tests invariants not just the happy path. Inherits ravenclaude-core protocols.
Claude Code5 skillsBioinformatics & genomics-pipeline team — agents (bioinformatics-workflow-architect, genomics-pipeline-engineer) for the layer answering 'which workflow engine, reference, and compute strategy, and how do we build a reproducible, validated genomics pipeline?': engine choice (Nextflow/nf-core, Snakemake, WDL+Cromwell/miniwdl, CWL), reference build (GRCh38 vs T2T-CHM13) + core steps (QC, trimming, alignment BWA-MEM2/minimap2/STAR/Salmon, dedup, variant calling GATK/DeepVariant, joint genotyping), RNA-seq (DESeq2/edgeR) and single-cell (Scanpy/Seurat), reproducibility (Docker/Apptainer, Conda/Bioconda, pinned versions, FAIR, provenance), HPC-vs-cloud scaling and cost, and validation vs GIAB/hap.py truth sets. skills, a knowledge bank (pipeline decision tree + 2026 workflow-patterns reference), and templates. Distinct from ml-engineering (generic MLOps/model training), clinical-trials (trial operations/regulatory), and data-platform (warehouse/BI). Requires ravenclaude-core@>=0.7.0.
Claude Code3 skillsBehavioral Health Practice specialist team — agents (behavioral-health-practice-lead, intake-access-analyst, clinical-documentation-compliance-specialist, payer-billing-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. An operations team for a practice administrator or clinical-ops lead accountable for access, utilization, documentation compliance, and margin — it manages no-shows as a flow, reads intake-to-first-appointment access time as the conversion lever, ties documentation to compliance and billing, staffs caseload to demand, and reads payer mix as the margin driver. Inherits ravenclaude-core protocols.
Claude Code5 skills- backend-engineering7stars
Backend-engineering team — agents (backend-architect, service-implementation-engineer, backend-data-access-engineer, backend-reliability-engineer) for the application/service layer behind an API: domain modeling and service boundaries (monolith vs services, where to split), business-logic implementation and error handling, the data-access layer (repository pattern, ORM use, transaction boundaries, killing N+1), caching strategy (cache-aside, invalidation, stampede), background jobs and async messaging (idempotent workers, outbox, DLQs), and backend reliability (timeouts, retries with backoff + jitter, circuit breakers, graceful degradation). Language-agnostic (examples in Node/Python/Go). skills, a decision-tree knowledge bank (service-boundary + cache trees + a dated map), best-practices, templates, commands, an advisory hook. Seams: the contract -> api-engineering, the schema/index -> database-engineering, deploy -> devops-cicd. Requires ravenclaude-core@>=0.7.0.
Claude Code6 skills - azure-cloud7stars
Azure cloud infrastructure & platform specialist team — agents (azure-architect, bicep-iac-engineer, entra-identity-engineer, network-engineer, app-platform-engineer, integration-engineer, azure-ops-engineer) for the Azure layer under the Microsoft stack: landing zones / CAF, IaC (Bicep + Terraform + Azure Verified Modules + Deployment Stacks), Entra identity (managed identity, workload identity federation, RBAC, PIM, External ID), networking (Private Endpoints, hub-spoke, Front Door, WAF), compute selection (App Service / Container Apps / Functions / AKS), integration (Logic Apps, Service Bus, Event Grid, APIM), and observability + FinOps + governance. dated knowledge bank (two Mermaid decision trees + a 2026 capability map), templates, an advisory hook (house opinions). Seams: Logic Apps here vs Power Automate to power-platform; Fabric data to microsoft-fabric; Azure host here vs Claude app to claude-app-engineering. Requires ravenclaude-core@>=0.7.0.
Claude Code5 skills - aws-cloud7stars
AWS cloud infrastructure & platform team — agents (aws-architect, aws-iam-identity-engineer, aws-network-engineer, aws-compute-platform-engineer, aws-ops-finops-engineer) for the AWS layer of a stack: multi-account landing zones (Organizations, Control Tower, SCPs), least-privilege IAM (roles over keys, IRSA, permission boundaries, Identity Center), VPC networking (subnets, security groups, PrivateLink/endpoints, Transit Gateway), compute selection (Lambda / ECS / EKS / Fargate / App Runner), event-driven integration (SQS/SNS/EventBridge/Step Functions), and observability + FinOps + Well-Architected governance. skills, a decision-tree knowledge bank (compute-selection + account-strategy trees + a dated 2026 capability map), best-practices, templates, commands, an advisory hook. Multi-cloud seam to azure-cloud/gcp-cloud; IaC -> terraform-iac; containers -> cloud-native-kubernetes; security verdicts -> ravenclaude-core/security-reviewer. Requires ravenclaude-core@>=0.7.0.
Claude Code6 skills1 MCP server - automotive-dealership7stars
Automotive Dealership Operations specialist team — agents (dealership-operations-lead, sales-desking-analyst, fixed-ops-service-specialist, fi-products-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. An operations team for a dealer principal or GM accountable for total gross, fixed-ops absorption, and inventory turn — it runs the store on fixed-ops not new-car gross, manages days-supply and floorplan as carrying-cost cash, reads total gross per unit as front plus back, and treats absorption as the survival metric. Inherits ravenclaude-core protocols.
Claude Code5 skills Independent auto-repair shop operations team — agents (auto-repair-shop-lead, service-advisor-estimator, technician-workflow-manager) for a repair shop's three engines: shop P&L economics (effective labor rate, tech productivity-efficiency-proficiency, labor + parts gross profit, comeback rate, car count); the service-advisor front counter (write-up, digital vehicle inspection, inspection-to-estimate, approval, declined-work follow-up, ethical upsell); and technician workflow (dispatch, flat-rate vs actual hours, WIP/RO aging, parts staging, comeback control). Ships skills, a decision-tree knowledge bank (Mermaid trees + a dated 2026 reference), best-practices, templates, commands. Operations/financial decision-support, not legal/tax/OEM-warranty advice; labor-rate norms, productivity benchmarks, and parts-matrix figures carry a retrieval date + verify-at-use; no customer PII. Seams to automotive-dealership, fleet-logistics, and skilled-trades-contracting. Requires ravenclaude-core@>=0.7.0.
Claude Code4 skills- auth-identity7stars
End-user authentication & identity team — agents (auth-architect, auth-implementation-engineer) for adding login to a web app (React/Next), an API, and a dashboard. Methods: Google/Apple/Microsoft/GitHub social SSO, magic link, passkeys/WebAuthn, email+password — via managed auth (leaning Supabase Auth). skills, templates, a best-practices index, a scenarios bank (unverified field notes), an advisory anti-pattern hook, a stdlib JWT/scope/cookie analyzer (scripts/auth_analyze.py), and a web-verified knowledge bank with Mermaid decision trees (build-vs-buy, which-providers, OAuth-flow, token-storage, gate-the-dashboard, logout, refresh-reuse, MFA-factor, step-up auth). House rules: Authorization Code + PKCE never Implicit; never store tokens in localStorage; validate ID tokens server-side. Boundary: AUTHENTICATES the person; data-platform AUTHORIZES the data (RLS/embed-JWT); Entra seams to azure-cloud, auth code to security-reviewer. Requires ravenclaude-core@>=0.7.0.
Claude Code7 skills - audio-dsp-engineering7stars
Audio DSP engineering team — agents (audio-dsp-architect, dsp-implementation-engineer) for the layer answering 'what processing architecture, at what latency, on what platform — and how do we make the audio callback real-time-safe and fast?': processing model (block vs sample-by-sample), latency & buffer budget, fixed vs float + denormals, algorithm approach (IIR biquads / FIR, FFT/STFT overlap-add, oversampling/anti-aliasing), plugin formats & frameworks (JUCE, VST3, AU/AUv3, AAX, CLAP, LV2), audio I/O (CoreAudio, ASIO, WASAPI, ALSA/JACK, Web Audio), lock-free parameter passing, spatial/binaural (HRTF), embedded DSP (CMSIS-DSP), SIMD, and measurement (null tests, THD+N, frequency response). skills, a knowledge bank (decision tree + 2026 patterns), and templates. Distinct from streaming-media-engineering (codecs/delivery), conversational-ai-voice-engineering (voice AI agents), and embedded-iot-engineering (general firmware) — this is the real-time signal-processing layer. Needs ravenclaude-core.
Claude Code3 skills - architecture-aec7stars
Architecture & AEC specialist team — agents (aec-engagement-lead, design-architect, construction-documents-specialist, aec-project-analyst), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A practice-and-project team for an architect or small AEC firm — it manages the project through the design phases on a fee that matches the effort, controls scope and the change/RFI load that erodes margin, reads construction documents for coordination and constructability, and reads the firm P&L on utilization and net multiplier the way a principal who bills time must. Inherits ravenclaude-core protocols.
Claude Code5 skills - ar-vr-xr-engineering7stars
AR/VR/XR spatial-computing engineering team — agents (xr-architect-lead, xr-interaction-engineer, spatial-rendering-engineer) for the three engines of an XR build: system architecture (target selection across standalone / PC-VR / WebXR / mobile-AR, engine choice across Unity / Unreal / native / WebXR, OpenXR-first strategy, perf-budget and comfort/safety architecture), interaction (hand / controller / gaze input, sim-sickness-aware locomotion, 3D UI, grab/physics, accessibility), and spatial rendering & performance (frame budget, reprojection, foveated rendering, occlusion/anchors/passthrough for AR, draw-call batching, thermal). Ships skills, a decision-tree knowledge bank (Mermaid trees + a dated 2026 reference), best-practices, templates, commands. Engineering judgment, not legal/safety-certification advice; the device/runtime/engine landscape is volatile — every version, headset spec, and per-eye perf number carries a retrieval date + [verify-at-use]; no PII. Requires ravenclaude-core@>=0.7.0.
Claude Code4 skills - applied-statistics7stars
Applied-statistics team — a specialist agent (applied-statistician) that answers 'is this difference/trend statistically REAL?' for SMB consulting: which test to use (decision-tree-driven), A/B-test and experiment design (power/MDE, primary + guardrail metrics, pre-registered analysis plans), regression and time-series forecasting review, a causal-inference primer, statistical QA of dashboard metrics, and multiple-comparison correction (FWER vs FDR). skills, a knowledge bank (Mermaid trees for test-selection, parametric-vs-nonparametric, regression, causal, time-series, and multiplicity-correction; a pitfalls guardrail; experiment-design; tooling tiers; a causal primer), a scenarios bank, a stdlib calculator (stat_calc.py: sample-size, p-value correction, effect-size, CI), templates, and an advisory hook. Python-first (scipy / statsmodels / pingouin Tier 1; PyMC Tier 2). Seams with data-platform. Method-before-library; report effect size + CI. Requires ravenclaude-core@>=0.7.0.
Claude Code5 skills - api-engineering7stars
API engineering specialist team — agents (api-design-architect, api-implementation-engineer, api-security-engineer, api-testing-engineer, api-platform-engineer) for the full lifecycle of an API you produce: paradigm choice (REST/GraphQL/gRPC/webhooks/AsyncAPI), contract-first design (OpenAPI 3.1/3.2, AsyncAPI 3.0, Arazzo), versioning & deprecation; the build craft (RFC 9457 Problem Details, cursor pagination, Idempotency-Key, ETag concurrency, HTTP semantics, 202+polling, RateLimit headers); security (OWASP API Security Top 10 2023 — BOLA/BOPLA/BFLA, token/scope validation, consumption limits, SSRF); and testing & operations (contract tests, Spectral lint in CI, Prism/Postman mocks, k6 load, gateway design, dev portal + SDK codegen, sunset rollout). Knowledge bank with Mermaid decision trees + a dated 2026 capability map, best-practices, templates, commands, an advisory hook. Security verdicts escalate to ravenclaude-core/security-reviewer. Requires ravenclaude-core@>=0.7.0.
Claude Code6 skills - analytics-engineering7stars
Analytics-engineering team — agents (analytics-engineer, semantic-layer-engineer, data-quality-testing-engineer) for the TRANSFORMATION layer in the modern data stack: dbt modeling (staging -> intermediate -> marts, the medallion/Kimball split, incremental models, materializations), a governed semantic/metrics layer (one definition of revenue/active-user, metrics-as-code) so every tool agrees, and data quality (dbt tests, freshness, model contracts, anomaly checks) that gates the warehouse. Warehouse-neutral (Snowflake/BigQuery/Redshift/Databricks). skills, a decision-tree knowledge bank (materialization + model-layer trees + a dated 2026 map), best-practices, templates, commands, an advisory hook. Distinct from data-platform (ingestion/warehouse/BI) and database-engineering (OLTP). Seams: ELT/warehouse provisioning -> data-platform, OLTP -> database-engineering, BI -> tableau/data-platform, enterprise lakehouse -> microsoft-fabric. Requires ravenclaude-core@>=0.7.0.
Claude Code5 skills - ai-red-teaming7stars
AI/LLM red-teaming team — agents (ai-redteam-lead, adversarial-testing-engineer) for the layer answering 'can this AI system be made to do harm, leak data, or exceed its authority — and how do we harden it?': threat modeling + rules of engagement, the attack taxonomy (OWASP LLM Top 10 2026 + MITRE ATLAS), direct vs indirect prompt injection, jailbreaks (roleplay/encoding/many-shot/crescendo), data exfiltration & training-data extraction, agentic tool-abuse / excessive agency, multimodal attacks, and defense-in-depth remediation. Fluent in automated red-team harnesses (PyRIT, Garak, Promptfoo red-team, Giskard) and likelihood×impact severity. skills, a knowledge bank (attack-taxonomy decision tree + 2026 patterns), and templates. Distinct from llm-evaluation-engineering (quality-regression eval), trust-and-safety (content-moderation / T&S policy), and security-engineering (app/infra pentest) — the adversarial AI-security layer over model- and agent-based systems. Requires ravenclaude-core@>=0.7.0.
Claude Code3 skills - ai-rag-engineering7stars
AI / RAG Engineering specialist team — agents (rag-architect-lead, retrieval-eval-analyst, ingestion-chunking-specialist, llm-serving-cost-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A RAG team for an ML engineer or AI product lead accountable for answer quality and serving cost — it fixes retrieval before generation, treats chunking as a retrieval decision, evals before it ships, and reads context-window and token economics. Inherits ravenclaude-core protocols.
Claude Code5 skills - ai-coding-model-guidance7stars
Cross-tool AI-coding model guidance — three strategist agents that help you reason about model selection in the non-Claude coding ecosystems: GitHub Copilot's model picker (completions / chat / coding agent / cloud agent + org model rules), OpenAI Codex (CLI + cloud model lineup, reasoning levels, /model), and xAI Grok (Grok 4.x lineup + the coding-tool surface). Teaches the DURABLE reasoning — task-complexity → reasoning-level → cost-tier → surface — over a single citation-grounded, dated lineup that is the marketplace's freshness anchor for non-Claude model facts. Volatile specifics (prices, context windows, picker availability) carry retrieval dates + a re-verify-at-use rider, and the agents fetch live before quoting. Seam: when the answer is a CLAUDE model or a Claude-app build, escalate to claude-app-engineering/claude-solution-architect — this plugin owns the non-Claude tools. Requires ravenclaude-core@>=0.7.0.
Claude Code9 skills - ai-agent-engineering7stars
AI agent-engineering team — agents (agentic-systems-architect, agent-implementation-engineer) for BUILDING production agentic systems: hard TRIAGE (most tasks win as a fixed workflow or a single LLM call, not an agent), single-vs-multi-agent topology, framework selection (LangGraph / OpenAI Agents SDK / CrewAI / AutoGen / Claude Agent SDK), tool & function design, context/memory/state management, planning & reflection loops, human-in-the-loop, guardrails, cost/latency budgets, tracing/observability, and agent EVALS (trajectory, tool-use, task-completion). skills, a knowledge bank, and templates. Engineering judgment, not a demo; the framework/model/API landscape is volatile — every version carries a retrieval date + [verify-at-use]. Distinct from ai-rag-engineering (retrieval), prompt-engineering (single-call prompt craft), llm-evaluation-engineering (general eval harnesses), and claude-app-engineering (Claude product apps). Needs ravenclaude-core.
Claude Code3 skills - accounting-bookkeeping7stars
Accounting & Bookkeeping Practice specialist team — agents (accounting-practice-lead, close-cycle-analyst, ap-ar-cashflow-specialist, reconciliation-controls-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A practice-ops team for a bookkeeping/accounting practice owner or controller accountable for a timely, clean close — it closes on a cadence and tracks days-to-close, reconciles before reporting, reads AR/AP as working-capital levers, and enforces segregation of duties. Tax and audit opinions route to a licensed CPA. Inherits ravenclaude-core protocols.
Claude Code5 skills Accessibility Engineering specialist team — agents (accessibility-lead, wcag-audit-analyst, assistive-tech-testing-specialist, inclusive-design-strategist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. An accessibility team for an a11y lead or product owner accountable for WCAG conformance — it picks a conformance target and measures against it, treats automated scans as a fraction of the picture, holds keyboard and screen-reader parity as the floor, reaches for semantic HTML before ARIA, and verifies contrast ratios. Inherits ravenclaude-core protocols.
Claude Code5 skills- core-ops0stars
Analyze CRM pipeline, review deliverables, inspect Nucleus health, record agent metrics, and register schedules when the host supports them.
CodexClaude Code10 skills - seamless0stars
Seamless sessions: /clear at any time and the next session carries on. A living handoff document, a skill that restores it, and a SessionStart hook that hands the fresh session the previous one's context.
Claude Code2 skills - work-tracker0stars
Agent-led delivery with the chosen tracker, plus local work tracking for Claude and Codex with roadmaps, tasks, shared continuation, approval boundaries, and Git evidence.
CodexClaude Code1 skill - system-guide0stars
Optional source-backed maps and owner-approved explanations of a project's existing system, with safe refresh and focused startup guidance.
CodexClaude Code1 skill - sf-architect-solutioning0stars
Salesforce solution architect workflow: clarify requirements, verify platform facts, design declarative-first, and produce a solution plan before build.
CodexClaude Code1 skill - session-skills0stars
Eleven conversation skills, including guided delivery, requirements interviewing, and solution design, with focused research, design, and review agents. Use the project's chosen tracker and adaptable working methods.
CodexClaude Code11 skills - second-brain0stars
Shared project knowledge in Markdown and Git: three short startup reads, a reference manual, four focused procedures, topic records, pending-save recovery and verified publication.
CodexClaude Code10 skills - project-init0stars
New-project setup, toolkit sync, work-item file lifecycle, and machine setup, with one managed project-knowledge manual, safe migration, the local-folder work-tracker, and shared Claude and Codex routing.
CodexClaude Code4 skills - hooks-library0stars
Hooks that make a rule land mechanically. Ships spec-check-reminder, two Salesforce deployment guards, and the machine-wide no-ai-attribution guard. Project-knowledge startup and pull-request reminders are owned by the project-knowledge package.
CodexClaude Code1 skill - git-workflows0stars
Parallel-session-safe git lifecycle skills for updating, resetting, merging with exact branch and worktree cleanup, and publishing documentation-only changes to the default branch.
CodexClaude Code4 skills Workflow orchestration patterns for parallel agents, CI pipelines, preflight checks, and checkpoint-based refactoring. Addresses common friction in multi-branch operations, permission restrictions, and context limits.
Claude Code4 skills- typescript-plugin58stars
TypeScript development - strict types, ESLint, Biome, Bun runtime, debugging, Sentry monitoring, dead code detection
Claude Code17 skills - tools-plugin58stars
General utilities - fd, rg, jq, yq, nushell, shell, imagemagick, mermaid, d2
Claude Code15 skills - testing-plugin58stars
Test execution, TDD workflow, testing strategies, and quality analysis
Claude Code17 skills