claude

claude-app-engineering

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, advisor tool), 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.

9 on GitHubby Matt Corbettv0.9.23MITupdated today
/

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

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (7)

  • agent-sdk-hook-design

    Playbook for designing Claude Agent SDK hooks (PreToolUse, PostToolUse, SessionStart, Stop) — selecting the right event, writing the handler contract, deciding advisory vs blocking behaviour, and avoiding the four common hook anti-patterns. Owned by agent-sdk-engineer.

  • context-budget-planner

    Playbook for allocating a Claude context window across system prompt, retrieved documents, conversation history, and tool results — with token-budget formulas, the retrieve-vs-hold decision, and the compaction triggers that prevent context overflow. Owned by prompt-and-context-engineer.

  • eval-golden-set-builder

    Playbook for constructing a high-signal golden evaluation set: sampling strategy, input diversity, reference-answer authoring, grader pairing, and the minimum-viable size thresholds that make a delta meaningful. Owned by eval-engineer.

  • llm-routing-ladder

    Playbook for designing a cost-optimised model routing ladder: classifying request complexity, wiring the triage→escalate flow, measuring cost-per-resolved-task, and avoiding the common over-provisioning traps. Owned by claude-app-ops-engineer and claude-solution-architect.

  • mcp-server-authoring-checklist

    Gate-by-gate checklist for shipping a production MCP server: transport selection, tool-schema quality, auth wiring, error-response contract, and the security hand-off items that must escalate to core/security-reviewer. Owned by mcp-and-server-tools-engineer.

  • prompt-caching-audit

    Step-by-step playbook for diagnosing a low cache hit rate, finding the breakpoint placement errors that cause it, and correcting them. Covers TTL tradeoffs, pre-warming, tool-definition stability, and the per-model minimum-token floors.

  • tool-schema-design

    Playbook for designing Claude tool definitions (name, description, JSON Schema input_schema) that maximise correct invocation, minimise hallucinated arguments, and produce clean structured output. Covers naming conventions, description prompting, schema constraints, required vs optional fields, and

Slash commands (5)

  • /claude-app-engineering:add-prompt-caching

    Lay out a Claude prompt for a high cache-hit rate — stable content (tools, system, static context) above the cache_control breakpoint, volatile content (timestamps, the incoming message, fresh tool results) below, tool defs never mutated per request.

  • /claude-app-engineering:build-eval-harness

    Build an eval harness that gates prompt/model/tool changes — assemble a golden set and graders before the change, report a delta vs prior so 'looks better' becomes a number, and for RAG eval the retriever (recall@k, MRR) separately from the generator.

  • /claude-app-engineering:design-claude-app-architecture

    Choose the build surface and architecture for a Claude-backed feature — traverse the decision tree (Workbench/Messages/Agent SDK/Managed Agents), right-size the model with a routing ladder, and decide RAG vs long-context, measuring cost-per-resolved-task.

  • /claude-app-engineering:engineer-prompt-and-context

    Engineer a Claude prompt and its context window — climb the leverage ladder (clear+direct+examples first, multi-agent last), curate the right tokens and compact stale history, force structured output via a tool, and keep thinking config stable and dated.

  • /claude-app-engineering:wire-mcp-server-or-tool

    Decide MCP server vs in-process tool and build it right — MCP for genuine cross-client reuse, in-process for a one-off; expose the fewest idempotent tools, authenticate every request, design the tool as a contract, and return actionable errors.

Subagents (6)

  • agent-sdk-engineer

    Use this agent to build agents with the Claude Agent SDK (Python/TypeScript) or Managed Agents — subagents, hooks, skills, slash commands, sessions (resume/fork), permissions/sandboxing, plan mode, MCP wiring, and the prototype-to-Managed-Agents move.

  • claude-app-ops-engineer

    Use for Claude app production ops — token-cost FinOps (cache hit rate, the model routing ladder, Batch API, cost-per-resolved-task), reliability (429/overloaded backoff + jitter, idempotency), and observability. NOT for prompt/caching design (prompt-and-context-engineer); security → core.

  • claude-solution-architect

    Use this agent to decide HOW to build a Claude-backed feature — the build-surface choice (Messages API vs Claude Agent SDK vs Managed Agents vs Workbench), model right-sizing (Opus 4.8 / Sonnet 4.6 / Haiku 4.5, 1M context), the deployment target (Claude API vs Bedrock vs Vertex vs Foundry).

  • eval-engineer

    Use this agent to measure Claude app quality — eval design, golden datasets, programmatic + LLM-as-judge grading, regression suites, and the before/after delta that gates a prompt/model/tool change.

  • mcp-and-server-tools-engineer

    Use to connect Claude to external systems — authoring MCP servers (tools/resources/prompts/sampling over stdio / SSE / Streamable HTTP, with auth) and using Anthropic-hosted server tools (computer use, code execution, web search/fetch, Files API, memory). NOT for in-app tool design or the SDK loop.

  • prompt-and-context-engineer

    Engineer the application's prompt + context + tool layer on the Claude API — prompt-caching strategy (breakpoints, TTL, hit rate), 1M-context management, structured output, adaptive/extended thinking, citations, and in-app tool-use design (schemas, tool_choice, the Messages-API loop).

Hooks (1)

  • PreToolUse

    /usr/bin/env -u BASH_ENV -u ENV -u SHELLOPTS -u BASHOPTS -u LD_PRELOAD -u LD_LIBRARY_PATH -u LD_AUDIT -u DYLD_INSERT_LIBRARIES -u DYLD_LIBRARY_PATH -u PYTHONPATH -u PYTHONSTARTUP PATH=/usr/local/bin:/

Language servers (2)

  • python
  • typescript
View source on GitHub mcorbett51090.github.io

More from mcorbett51090/RavenClaude

All 184 plugins →

RavenClaude Core

claude

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

claude

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

claude

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-partner-success

claude

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

regulatory-compliance

claude

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

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

i-have-adhd

claudecodex

Action-first, ADHD-friendly output shaping for Claude Code.

1 skill · hooks

ayghri/i-have-adhd 61,026

obsidian

claude

Claude Skills for Obsidian

6 skills

kepano/obsidian-skills 51,587

container

claude

Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS

1 skill

apple/container 51,329

Maintain claude-app-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