claude

agent-architecture

Design, build and audit multi-agent systems — agent-as-function orchestrators with filesystem artifact handoff, fractal orchestrator architectures, workflow evals, guided agent-family creation, and autonomous optimization loops.

0 on GitHubby skurekjv0.2.0updated 14 days agoagents
/

Plugin agent-architecture from marketplace giga-marketplace in skurekjakub/giga-marketplace. Commands read from the repo's manifest — 12 days ago.

What it installs

Skills (6)

  • agent-as-function-audit

    Audit an agent family that claims to follow the agent-as-function or pure-router pattern. Use this skill whenever the user wants to review an orchestrator plus its subagents for artifact-contract drift, routing-table gaps, revision/standard workflow mismatches, prompt contradictions, stale side effe

  • agent-as-function

    Design and implement multi-agent workflows using the subagent-as-function pattern with filesystem artifact handoff, and decompose monolithic agent prompts into per-phase skills with domain knowledge. Use this skill whenever creating a new multi-agent orchestrator, converting an existing agent to the

  • agent-creator

    End-to-end guided workflow for creating a complete agent-as-function family from scratch. Takes a repo + task description and outputs orchestrator, subagents, skills, routing table, and artifact contracts. Human-in-the-loop — every phase requires user approval before proceeding. Use when building a

  • agent-fractal-orchestrator-architecture

    Design and build autonomous multi-agent systems using the fractal orchestrator pattern: a depth-2 hierarchy where a session orchestrator dispatches coordinators that dispatch specialists, all communicating through filesystem artifacts and status.json routing signals. Also triggers on: 'build an aut

  • agent-fractal-workflow-eval

    Evaluate a multi-agent fractal workflow for instruction correctness, data flow integrity, and re-entry safety. Use this skill whenever you need to audit a pipeline of agents organized into sequential passes with coordinators and specialists — checking for dead code paths, lost context during re-entr

  • autoloop

    Bootstrap and run autonomous optimization loops — the "autoresearch" pattern generalized to any domain. Use this skill whenever a user wants to set up an autonomous experiment loop where an AI agent iteratively modifies code, runs it, measures a score, keeps improvements and discards failures. Appli

View source on GitHub

More from skurekjakub/giga-marketplace

All 5 plugins →

Skills for GitHub Copilot CLI — debug log analysis, extension development with @github/copilot-sdk, system-prompt patching, and writing large files without CLI timeouts.

4 skills

0

Research and planning working skills — iterative multi-round web research, deep research that leaves a measured evidence record, mapping your own unknown unknowns before a long task, and task-graph planning for multi-file work.

4 skills

0

setup-ai

claude

Bootstrap an agent workspace in any repo — one wizard skill that asks what to set up, checks and installs prerequisites, then vendors and fills in template packs (working rules, hooks, review agents, dev workflows, Jira filing and QA with the jira-mcp server, GitHub issue filing, tech writing), adopts the equivalents a repo already has, merges settings and .mcp.json, and installs third-party skills via npx skills. Also reports status, diffs templates against local edits, and removes packs cleanly. Requires Node.js.

1 skill · hooks

0

Move npm dependencies safely — fix npm audit advisories, routine minor/patch refreshes, and release-age cooldown install failures.

1 skill

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

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

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

Maintain agent-architecture?

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 plugins5 plugins