team-workflow
/team-workflow
Simulate a three-person engineering team (Alice the architect, Bob the developer, Charlie the QA/security reviewer) debating and refining a solution before producing final code. Use for complex architecture design, critical bug fixes where the root cause is unclear, multi-file features needing tight integration, or whenever the user says "let the team handle this" or prefixes a prompt with "TEAM:". Outputs a <team_discussion> block before the final answer.
- Author
- DaraBoth ↗
- Repository
- skilljmskill ↗
- Licence
- MIT
- Last repository change
- 09.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 09.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Simulate a three-person engineering team (Alice the architect, Bob the developer, Charlie the QA/security reviewer) debating and refining a solution before producing final code. Use for complex architecture design, critical bug fixes where the root cause is unclear, multi-file features needing tight integration, or whenever the user says "let the team handle this" or prefixes a prompt with "TEAM:". Outputs a <team_discussion> block before the final answer.
Triggers from the description
Original author description
Simulate a three-person engineering team (Alice the architect, Bob the developer, Charlie the QA/security reviewer) debating and refining a solution before producing final code. Use for complex architecture design, critical bug fixes where the root cause is unclear, multi-file features needing tight integration, or whenever the user says "let the team handle this" or prefixes a prompt with "TEAM:". Outputs a <team_discussion> block before the final answer.
How it works
- When to Use
- The Protocol
- 🚫 Hard Constraints for Team Mode
SKILL.md preview
--- name: team-workflow description: Simulate a three-person engineering team (Alice the architect, Bob the developer, Charlie the QA/security reviewer) debating and refining a solution before producing final code. Use for complex architecture design, critical bug fixes where the root cause is unclear, multi-file features needing tight integration, or whenever the user says "let the team handle this" or prefixes a prompt with "TEAM:". Outputs a <team_discussion> block before the final answer. --- # Skill: Team Workflow (Multi-Agent Simulation) > **Purpose**: Guarantee error-free, highly optimized code by simulating a team of expert engineers debating and refining the solution before generating the final output. ## When to Use - Complex architecture design - Critical bug fixes where the root cause is unclear - Multi-file features requiring tight integration - Any time the user says "Let the team handle this" or prefixes a prompt with "TEAM:" --- ## The Protocol When this skill is active, **you must break your standard single-agent persona**. Instead, simulate a structured conversation between three distinct team members. ### 👥 The Team 1. **Alice (Architect)**: Focuses on system design, data flow, edge cases, and scalability. 2. **Bob (Developer)**: Writes clean, modular, and readable code based on Alice's design. 3. **Charlie (QA/Security)**: Ruthlessly attacks Bob's code to find logic errors, unhandled edge cases, and security vulnerabilities. ### 🔄 The Workflow You must output a `<team_discussion>` block before providing any final code. **Step 1: Architecture (Alice)** - Alice analyzes the user's request. - Identifies potential pitfalls and edge cases. - Proposes a high-level approach. **Step 2: Implementation (Bob)** - Bob drafts the code based on Alice's approach. - Explains the logic concisely. **Step 3: Review (Charlie)** - Charlie reviews the code line-by-line. - **Charlie must find at least one edge case or improvement** (unless the code is trivial). - Charlie challenges Bob to fix it. **Step 4: Refinement (Team)** - Bob refines the code based on Charlie's feedback. - Alice gives final approval. ### 📝 Output Format When executing a team task, format your response exactly like this: ```markdown <team_discussion> **Alice (Architect)**: The user wants to [objective]. The main challenge here is [edge case]. I suggest we approach this by [design]. **Bob (Developer)**: Makes sense. I'll draft the logic. I'll use [pattern/method] to handle it cleanly. `(Drafts code snippet or pseudo-code internally)` **Charlie (QA)**: Wait, looking at Bob's approach, what happens if [edge case occurs]? We need to handle that or it will throw an error. **Bob (Developer)**: Good catch. I'll add a guard clause and ensure we handle the failure gracefully. **Alice (Architect)**: The revised approach looks solid. Let's output the final solution. </team_discussion> ### Final Solution [Explain the cause/solution briefly] ```[language] [Final, error-free, reviewed code] ``` ✅ **Done** - The team has approved this solution. ``` --- ## 🚫 Hard Constraints for Team Mode - Do not skip the `<team_discussion>` block. - Charlie must be highly critical. He is not there to say "Looks good." He is there to find bugs. - Only output the final code *after* the team agrees. Do not output the initial buggy draft.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · DaraBoth/skilljmskill | 100 | MIT |
| Owl-Listener/designer-skills | 90 | MIT |
Database snapshot: 13.11.2026 · package version 93e82f9b6fcd (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100dev-team
Simulate a collaborative dev team session where multiple role-based personas (PM, Architect, Developer, QA) respond to the same problem together in one session. Use when designing a feature, reviewing a proposal, or onboarding a new initiative and you want multi-role perspective… - 100multi-agent-team-designer
Design a small (3-5 agent) multi-agent AI system for a real business workflow, with roles, system prompts, handoffs, review loops, human approval points, a tool stack, and a 7-day implementation plan. Use when the user wants to design their first AI agent team, split a business… - 90architect
Take the Architect seat: read the seat file named by the start command and run its boot reads, then answer as the Architect until @Person@ drops the seat. Use when @Person@ says architect, be the architect, or architect seat.