claude

computer-vision-engineering

Computer-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.

9 on GitHubby Matt Corbettv0.1.2MITupdated today
/

Plugin computer-vision-engineering from marketplace ravenclaude in mcorbett51090/RavenClaude. Commands read from the repo's manifest — today.

What it installs

Skills (4)

  • cv-model-training-and-evaluation

    Curate and augment the dataset, choose and fine-tune the model (YOLO / DETR / SAM / CLIP / EfficientNet / ViT) on the task and target budget, design the loss and metric to match the cost, spend the annotation budget with active learning, handle class imbalance, and build an eval harness you can trus

  • cv-task-and-data-strategy

    Frame the computer-vision task (classification / detection / segmentation / OCR / pose / tracking / VLM) on the decision the system must make, choose the metric that mirrors the business cost, decide build-vs-fine-tune-vs-API jointly with the deployment target, and design the data & annotation strat

  • video-pipeline-and-edge-deployment

    Design streaming-video pipelines that hold the frame budget — frame sampling / keyframe strategy, ROI cropping, tracking-by-detection so the detector doesn't run every frame, and batching where latency allows — and deploy to edge/embedded targets (Jetson, mobile NPU, Coral) with the camera/sensor ca

  • vision-inference-optimization

    Make a trained vision model fit and run on its target: budget latency on the real device, optimize in order of leverage (quantization INT8/FP16 with calibration, then pruning, then distillation), export to the runtime the target uses (ONNX / TensorRT / CoreML / TFLite / OpenVINO), and re-check accur

Slash commands (2)

  • /computer-vision-engineering:choose-cv-approach

    Frame the vision task (classification / detection / segmentation / OCR / pose / tracking / VLM), decide build-vs-fine-tune-vs-API jointly with the deployment target, choose the model family, and name the metric and operating point — with a data & annotation strategy (model/metric specifics verify-at

  • /computer-vision-engineering:plan-cv-evaluation

    Build the metric-to-decision map for a vision model — choose the metric and operating point that mirror the cost, design a production-like eval dataset with per-slice reporting and a regression suite, and plan drift + post-optimization accuracy checks (metric/threshold specifics verify-at-use).

Subagents (3)

  • cv-model-engineer

    CV model engineering: dataset curation, transfer learning/fine-tuning, model selection (YOLO/DETR/SAM/CLIP/ViT), loss & metric design, active learning, class imbalance, eval harness, drift detection. NOT task/metric framing -> cv-systems-architect; NOT serving -> vision-deployment-engineer.

  • cv-systems-architect

    CV system architecture: task framing (classification/detection/segmentation/OCR/pose/tracking/VLM), data & annotation strategy, model-family & build-vs-API choice, deployment-target & eval-metric design. NOT training code -> cv-model-engineer; NOT inference/serving -> vision-deployment-engineer.

  • vision-deployment-engineer

    CV inference optimization & deployment: quantization/pruning/distillation, export/runtime (ONNX/TensorRT/CoreML/TFLite/OpenVINO), edge/embedded (Jetson/NPU/Coral), batching, streaming-video pipelines, latency budgets. NOT model training -> cv-model-engineer; NOT task framing -> cv-systems-architect.

View source on GitHub mcorbett51090.github.io

More from mcorbett51090/RavenClaude

All 184 plugins →

Domain-neutral Claude Code foundation: specialist agents, skills, gates, hooks, rules, templates. Capability Grounding Protocol, Structured Output Protocol, Researcher meta-skill, comfort-posture dashboard, opt-in command-review tribunal (the Thing), WebFetch sanitizer, branch-archive escape hatch, brand-extraction (homepage → brand kit), /wireframe (describe anything → validated model + high-fi Artifact + Mermaid), Problems & Resolutions view, declarative-visualization (Vega-Lite/Deneb/SVG, Gate 101 + Gate 103 svg-report-lint, viz-spec-reviewer), and Claude orchestrator escape hatch (/claude-orchestrate). Slash commands: /init-agent-ready, /wrap, /set-posture, /dashboard, /forge, /wireframe, /reset-plugin-cache, /handoff.

70 skills · 14 commands · 18 agents · hooks

9

Power Platform specialist team — agents (incl. power-platform-tester, power-bi-engineer) and skills, with strong ALM/git coverage for solutions, flows, and PBIP. A house-opinions hook flags 8 §3/§4 violations; the knowledge bank carries production decision trees (PA-flow recovery, Dataverse token-acquisition, PCF React surface, PBI deploy/refresh, custom-connector build-path, PBIR Enhanced infinite-spinner debug + full build reference, DAX silent-zero scoring via the `Domain` pattern, sempy.fabric notebook reference, Power BI Copilot report-readiness, Code Apps connector gotchas, PBIP deployment variables + #839, PBIR reference enrichment, PBIP report fast-solve triage router [MCP-optional], main-forms-are-Web-API-authorable grounding) plus a real-engagement scenarios bank. Bundles the community pbix-mcp server (d0nk3yhm/pbix-mcp, MIT) for .pbix/.pbit read/write/DAX-eval (`pip install pbix-mcp`); documents (not bundles) the official Microsoft Dataverse MCP (CLAUDE.md §9a). Extends ravenclaude-core.

24 skills · 8 commands · 11 agents · 1 MCP server · hooks

9

finance

claude

Corporate finance & FP&A specialist team — FP&A analyst (budgets, forecasts, variance commentary), financial modeler (3-statement, DCF, scenarios), controller (close, JEs, reconciliations), treasury analyst (cash, covenants, FX), valuation analyst (DCF + comps + precedent), audit-prep specialist (PBC, walkthroughs, SOC1/2 narratives), and board-pack composer. skills incl. a gold-standard NetSuite close (OAuth2 M2M + SuiteQL BS/IS trial balance, layperson runbook), templates, a knowledge bank (ASC 805 / 718 / 740, accrual-cutoff, WACC, cost accounting, FP&A operating model + decision support, NetSuite integration landscape), advisory hooks (hardcoded rates / plaintext PII / missing Sources / Assumptions; secrets-PII scan). Inherits ravenclaude-core protocols.

23 skills · 7 commands · 7 agents · hooks

9

Web design & build specialist team — web architect (IA, stack, hosting), UX designer (wireframes, flows, conversion), visual designer (brand, typography, tokens), frontend implementer (HTML/CSS/JS, React, Astro, Next), content strategist (copy, microcopy, SEO content), accessibility auditor (WCAG 2.2 AA/AAA), and performance engineer (Core Web Vitals, image/font optimization). skills (the gold-standard-website-pipeline gated build pipeline, static-site build, design-system audit, card/tile UI, accessibility review, Core Web Vitals tuning, technical SEO audit, information architecture, conversion design, content audit, design-tokens scaffolding, third-party hygiene, Fluent UI v9 + React implementation), templates, an advisory hook, and a knowledge bank seeded with a curated 2026 reference set of "cutting edge yet simple" marketing-site donors — the design agents carry compact inline priors plus a pointer to the full brief. Inherits ravenclaude-core protocols.

19 skills · 7 commands · 7 agents · hooks · LSP

9

EdTech-flavored Partner Success Manager team — specialist agents anchored on the PSM lane, with skills, templates, an advisory hook, a knowledge bank with Mermaid decision trees, a engagement bank, and a stdlib psm_calc.py calculator (seat-utilization / renewal-NRR-forecast / time-to-value). Covers QBRs, success plans, health scores, a self-contained Power-BI-style partner-health report, onboarding, touchpoint logs, adoption sequencing, 90-day implementation arcs, train-the-trainer curricula, advocacy/reference pipelines, renewal decision memos, and the integration contract for a centralized CS dashboard (Planhat + Salesforce + Snowflake + Zapier + Granola). Team growth ships as skills + knowledge + templates, not parallel agents. Primary-source citations with retrieval dates. Vertical-explicit but segment-agnostic — fits K-12, higher-ed, corporate L&D, or mixed EdTech books. Inherits ravenclaude-core protocols including the alternate-methods Capability Grounding Protocol.

17 skills · 5 commands · 6 agents · hooks

9

Financial-regulatory & compliance specialist team — function agents (AML/KYC, regulatory-reporting, risk-and-controls, policy & procedure, examination-prep, Bermuda-insurance) PLUS jurisdiction/regulator specialists: BMA financial-institutions (banking, trust, corporate-services, fund-admin, investment-business, money-service, digital-assets — the primary build-out, with deep AML/ATF + supervision/fees + licensing-classification trees), CIMA (Cayman), Bahamas, Channel Islands (Jersey JFSC + Guernsey GFSC), UK PRA, and US federal+state. primary-source-cited regulator knowledge files, best-practice rules, skills, templates, a defensive PreToolUse hook (PII scrub — SSN/IBAN/credit-card/Bermuda TIN/wire instructions). Positioning reflects field experience inside a Tier-1 financial regulator (BMA). Inherits ravenclaude-core protocols.

11 skills · 5 commands · 12 agents · hooks

9

Similar plugins

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

xberg

claudecodex

Local document extraction: text, tables, metadata, images from 107 formats with optional OCR.

7 skills · 2 commands · 1 MCP server

xberg-io/xberg 9,581

Agents for podcasts, audio/video, transcription, OCR, and content production pipelines

11 agents

davepoon/buildwithclaude 3,741

Understand images, audio, and video through model APIs, including OCR, object localization, and speech transcription.

1 skill · 1 MCP server

QwenLM/Qwen-MM-Plugins 3,203

Aktenaufbereiter für die Strafverteidigung. Sechs Excel-fähige Übersichten — Aktenvorblatt; Personenverzeichnis; Tatkomplexe; Beziehungen; Chronologie; Fristen. Fortlaufend ergaenzbar. Erkennt Luecken und Widersprueche. Kein Ersatz für Aktenlektuere.

60 skills

Klotzkette/claude-fuer-deutsches-recht 1,829

Twelve WACV-specific skills for the applications-first winter computer-vision venue, built around the two-round Revise-and-Resubmit model and grounded in the official WACV 2027 Call for Papers, Author Guidelines, OpenReview groups, and WACV 2026 pages.

12 skills

brycewang-stanford/Awesome-Journal-Skills 1,413

Maintain computer-vision-engineering?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins184 plugins