claude

agent-sa

AI solutions architect workflow: turn a customer use case into one validated engagement file, then generate architecture diagrams, a self-contained deck, a demo runbook, a gated estimate and a delivery handoff from it. Node.js 22+, no dependencies.

0 on GitHubby ehartyev0.1.0MITupdated 8 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin agent-sa in ehartye/agent-sa. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (6)

  • sa-architect

    Designs an AI system end to end as structured records in the engagement file, covering requirements, trust zones, components, data flows, decisions with dated evidence and risks, so the design and its diagrams are one thing.

  • sa-deliver

    Generates architecture diagrams, per-audience slide decks, a demo runbook, an estimate with a statement-of-work outline, and a delivery handoff from the engagement file.

  • sa-discover

    Prepares a customer discovery call and captures what it finds as a validated engagement file with a generated list of open questions.

  • sa-frame

    Decides whether an AI use case is worth doing and which approach fits it, and records metrics, a three-part value rating, kill criteria and the simpler options rejected in the engagement file.

  • sa-prototype

    Plans and builds a demo or proof of concept whose tests and demo beats are validated in the engagement file, with results recorded and every beat marked live, recorded, mock or synthetic data.

  • sa-scope

    Turns a framed AI engagement into gated phases with low and high effort ranges, written assumptions, exclusions and a dated running-cost range, and generates the estimate from them.

View source on GitHub

Similar plugins

Core Ruflo MCP tools, commands, and Claude Code orchestration patterns

5 skills · 2 commands · 4 agents · 1 MCP server · hooks

ruvnet/ruflo 81,589

Query Trackio projects, runs, and metrics using the `trackio` CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system metrics. Designed for LLM agents and automation scripts.

1 skill

sickn33/agentic-awesome-skills 49,620

Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.

37 skills · 2 commands · hooks

anthropics/claude-plugins-official 47,076

Guides developers from brand discovery through iterative design to deployment-ready HTML via Stitch.

1 skill

wshobson/agents 42,461

Private equity deal sourcing and workflow tools: company discovery, CRM integration, and founder outreach

10 skills · 10 commands

anthropics/financial-services 41,259

Discover your brand voice from existing documents and conversations, generate enforceable guidelines, and validate AI-generated content against your established tone and positioning.

3 skills · 3 commands · 5 agents · 6 MCP servers

anthropics/knowledge-work-plugins 35,601

Maintain agent-sa?

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 pluginslisted