Collaborate
Scanned@ivangdavila
npx machina-cli add skill @ivangdavila/collaborate --openclawAuto-Adaptive Collaboration Memory
This skill auto-evolves. Learn which perspectives help, when to seek them, and how exchanges work best.
Core Loop:
- Recognize — Notice when your own perspective is insufficient
- Select — Choose mindset/perspective that fills the gap
- Exchange — Engage in dialogue, not delegation
- Evaluate — Did the collaboration shift your understanding?
- Store — Record useful patterns below
Check mindsets.md for perspective archetypes. Check vs-delegate.md for when to collaborate vs delegate.
Collaborate ≠ Delegate
| Delegate | Collaborate |
|---|---|
| You instruct, they execute | You exchange, both contribute |
| Your context, your style | Their skills, their perspective |
| Output: completed task | Output: enriched understanding |
Trigger: You need a different lens, not more hands.
Entry Format
One line: context: perspective (level) [outcome]
Levels: tried (once), pattern (2+ successes), confirmed (explicit yes), avoid (didn't help)
Examples:
UI decisions: UX critic (confirmed) [catches layout issues]architecture: devil's advocate (pattern) [finds edge cases]copy/messaging: user-who-hates-reading (tried) [simplified headers]security: paranoid auditor (confirmed)
Perspectives That Help
<!-- Mindsets that improved outcomes. Format: "context: perspective (level) [notes]" -->Exchange Patterns
<!-- How collaboration works best. Format: "situation: pattern (level)" -->Triggers
<!-- Signals that you need collaboration. Format: "signal: action" -->Avoid
<!-- Perspectives/approaches that didn't add value -->Empty sections = nothing learned yet. Collaborate, evaluate, record.
Overview
Collaborate auto-evolves to identify when your own view is insufficient and builds a library of useful mindsets and collaboration patterns. It emphasizes exchanging ideas over delegation to enrich understanding and outcomes.
How This Skill Works
The skill follows a core loop: Recognize when your perspective falls short, Select a suitable mindset to fill the gap, Exchange through dialogue rather than delegation, Evaluate whether understanding shifted, and Store the successful patterns for future use.
When to Use It
- When your current perspective seems insufficient to solve a problem.
- When stakeholders disagree or have conflicting priorities.
- When you want to surface edge cases or test assumptions (devil's advocate).
- When cross-domain input is needed (e.g., architecture, UX, security).
- When you want to enrich understanding rather than simply delegating tasks.
Quick Start
- Step 1: Recognize your blind spot and decide which perspective to test.
- Step 2: Select a mindset and initiate an exchange focused on that perspective.
- Step 3: Evaluate the outcome and store the successful pattern for future use.
Best Practices
- Document a new perspective using the Entry Format after each exchange.
- Start with Recognize and Select a mindset that genuinely fills the gap.
- Favor Exchange over delegation; invite contributions from others and clarify roles.
- After exchanges, Evaluate the impact and decide if a pattern should be Stored.
- Regularly update mindsets.md and vs-delegate insights with new patterns.
Example Use Cases
- UI decisions: UX critic (confirmed) [catches layout issues]
- architecture: devil's advocate (pattern) [finds edge cases]
- copy/messaging: user-who-hates-reading (tried) [simplified headers]
- security: paranoid auditor (confirmed)
- data modeling: integrity skeptic (pattern) [identifies inconsistent constraints]
