Awp Workflow Builder

Trust Score 87/100

Generate complete Agent Workflow Protocol (AWP) compliant multi-agent workflows from natural language descriptions. Produces workflow.awp.yaml, agent...

triggers:generatecompleteagentworkflowprotocolcompliant

GitHub SKILL.md

What it does

AWP Workflow Builder

When to use it

Use when: Generate complete Agent Workflow Protocol (AWP) compliant multi-agent workflows from natural language descriptions. Produces workflow.awp.yaml, agent...

What's included

Scripts: no
References: yes
Instructions: # AWP Workflow Builder

See also — Authoritative non-normative docs: docs/README.md (concept map), docs/overview.md, docs/layer-model.md · Normative spec: spec/versions/1.0/spec.md, spec/versions/1.0/validation-rules.md, spec/versions/1.0/compliance.md · Per-layer references consumed by this skill...

Compatible agents

{}

Audit Summary

AWP Workflow Builder generates multi-agent workflows from natural language descriptions following the Agent Workflow Protocol spec v1.0. The SKILL.md is extremely detailed, covering 7-layer model, autonomy levels, DAG and delegation loop engines, dynamic tool creation, code mode, and full validation rules (R1-R32). No bundled scripts — the skill is purely prompt-driven instructions. Well-structured with clear phases from task analysis through generation to validation, but the sheer length may challenge context windows.

Watch Out

Very long SKILL.md (~14K+ chars) may exceed context limits for some models
Instructs agent to run shell.execute and subprocess in generated MCP tools — but sandboxed by AWP runtime
Requires awp-agents Python package installed for generated workflows to run

Notes

No security concerns beyond standard tool execution patterns which are sandboxed by the AWP runtime. The skill mentions shell.execute but explicitly marks it as forbidden in delegation loop workers (good). Dynamic tool creation has namespace capability restrictions preventing os/subprocess/ctypes imports. No hardcoded credentials, no exfiltration, no destructive commands. Architecture is exemplary — clear phase structure, references/, templates/. Main concern is length and niche applicability — AWP is a specific framework, limiting broad usefulness.

Information

Repository: agent-workflow-protocol
Stars: 17
Installs: 0

Trust Score

Overall87

Security88

Code Quality82

Architecture90

Usefulness72

Related Skills

Yielding Bear — Unified LLM Routing

A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.

arxiv2md

Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.

Scite Database (Smart Citations)

Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.

Writing Implementation Plans

Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.

LAP CLI

CLI for compiling, searching, and managing API specifications into a compact agent-native format and generating/installing skills from specs.

Audit Agents/Skills/Commands

Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.

NotebookLM Research Agent

End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c

AI News Daily

Generate a structured, bilingual daily briefing of the latest AI industry news, model updates, papers, and open-source tools with in-depth technical analysis an

Back to Skills