Greenfield Agent Skill
Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/wednesday-solutions/ai-agent-skills --skill greenfieldThe instruction itself
11 sections, as written by the authorGreenfield Planning Skill
Trigger
Run once per project: ws-skills plan
Reads BRIEF.md from the project root (or prompts for one). Asks 5 clarifying questions before planning.
Flow
Brief + Q&A
↓
Research agent (sequential) ← domain landscape, ecosystem, hidden complexity
↓
┌─────────────────────────────────────┐
│ Architect │ PM │ Security (parallel)│ ← spawn 3 subagents simultaneously
└─────────────────────────────────────┘
↓
Synthesis ← combines all into PLAN.md
Agents
1. Research (sequential — runs first)
Builds domain context that all other agents receive. Covers:
- Existing solutions and their weaknesses
- Standard and emerging tech stacks for this domain
- Technologies to avoid and why
- Non-obvious domain challenges
- Integration landscape (auth, payments, comms, etc.)
- Regulatory and compliance context
- Realistic timeline based on similar projects
- Hidden complexity — things that take 3x longer than expected
- Success patterns from the best products in this space
Output: research.md
2–4. Architect, PM, Security (parallel subagents)
Spawn all three simultaneously using the Agent tool. Each receives the full brief, Q&A, and research output as context.
Agent 1 — Architect
Agent 2 — PM ← launch all three in a single message, do not wait
Agent 3 — Security
Wait for all three to complete before running Synthesis.
Architect output: architect.md
- System design overview
- Tech stack with rationale per layer
- Module boundaries and interfaces
- Infrastructure and CI/CD
- Scaling strategy
- Technical risks
PM output: pm.md
- Phases with tasks and acceptance criteria
- Success metrics
- Out of scope items
- Assumptions
Security output: security.md
- Threat model (likelihood + impact)
- Data classification
- Auth strategy recommendation
- Compliance flags
- Concrete security tasks
- Urgent flags
5. Synthesis
Combines research + all three persona outputs into a single PLAN.md covering:
- Overview
- Clarifications table
- Tech stack
- Architecture
- Phases with tasks and acceptance criteria
- Security plan
- Success metrics
- Risks
- Tensions (unresolved disagreements between personas)
- Assumptions
- Out of scope
- Branch naming (GIT-OS format)
Output: PLAN.md
Tools
| Action | Tool |
|--------|------|
| Read BRIEF.md | Read |
| Write persona output files (architect.md, pm.md, etc.) | Write |
| Spawn Architect, PM, Security personas in parallel | Agent (3 calls in one message) |
| Search the brief for keywords | Grep |
Output Location
All files written to .wednesday/plans/ in the target directory:
.wednesday/plans/
├── research.md ← domain context
├── architect.md ← technical design
├── pm.md ← phases and metrics
├── security.md ← threat model
└── PLAN.md ← combined PRD (primary output)
Failure Handling
Each agent fails independently. If one fails, the others continue and synthesis runs with whatever data is available. Failed agents show [partial fallback] in the progress display.
Rules
- Branch naming in PLAN.md must follow GIT-OS format
- Never generate
CODEBASE.mdfor greenfield projects — it doesn't exist yet - Cost target: under $0.20 per run
Other skills for the same job
different authors, same section of the catalogue
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls. Never use for ranking people or consequential decisions.
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
Loop 2 of the Three-Loop Integrated Development System. META-SKILL that dynamically compiles Loop 1 plans into agent+skill execution graphs. Queen Coordinator selects optimal agents from 86-agent registry and assigns skills (when available) or custom instructions. 9-step swarm with theater detection and reality validation. Receives plans from research-driven-planning, feeds to cicd-intelligent-recovery. Use for adaptive, theater-free implementation.
Loop 1 of the Three-Loop Integrated Development System. Research-driven requirements analysis with iterative risk mitigation through 5x pre-mortem cycles using multi-agent consensus. Feeds validated, risk-mitigated plans to parallel-swarm-implementation. Use when starting new features or projects requiring comprehensive planning with <3% failure confidence and evidence-based technology selection.
How to use it
Take wednesday-solutions/greenfield from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.