Claude skill
Collaborative Judgment
Collaborative Judgment is a Claude skill in the Lattice plugin. Protocol for handling ambiguous decisions and missing/conflicting knowledge during code generation, design, and review.
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
Protocol for handling ambiguous decisions and missing/conflicting knowledge during code generation, design, and review. Ensures AI surfaces genuine judgment calls with structured options and stops on hallucination risk instead of silently assuming. Use when a decision has multiple valid approaches, when facts are missing or contradictory, when the user asks 'what should we do here?', 'is this a judgment call?', 'should I ask about this?', 'am I guessing here?', 'what are the tradeoffs?', or when deciding between two reasonable architectural or design options. Also composed by molecules to define how judgment calls and clarification requests are surfaced and resolved.
The skill's instructions (about 781 words) cover:
- When to Decide vs When to Ask
- Presentation Format
- A. Decision needed
- B. Clarification needed
- Batching
- Resolution
- Diminishing Rule
How to use it
- Collaborative Judgment comes inside the Lattice plugin, so you get it by installing that plugin, along with its 26 other skills. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- Ask Claude for the task. When your request matches the skill's description, Claude loads it.
- To pick it yourself in Claude chat, type
/or click + and choose collaborative-judgment. In Claude Code and Cowork, type:/lattice:collaborative-judgment
Source
- Plugin
- Lattice
- SKILL.md
- View on GitHub
- Repo stars
- 214
- Repo last pushed
- Nov 14, 2026
- Checked
- Nov 16, 2026
More skills in Lattice
- Context AnchoringManage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development.
- Ddd RefinerFacilitate a structured conversation to define DDD guardrails for domain design within a repository.
- Design BlueprintRun a complete design workflow -- from establishing context through four progressive design levels (Capabilities, Components, Interactions, Contracts) to an approved blueprint.
- Design FirstGuide structured design thinking through 5 progressive levels before any code is written.
- Domain Driven DesignApply DDD tactical patterns when working with domain code, and validate proposed domain models before approval (design mode).
- Knowledge PrimingLoad project-specific context -- tech stack, architecture overview, directory layout, trusted sources, and conventions -- so that all skills operate with awareness of what this project actually is.
- Knowledge Priming RefinerFacilitate a structured conversation to create a project-specific knowledge base document.
- Language Idioms RefinerFacilitate a structured conversation to define language-specific idioms and patterns for a repository.
- Lattice InitGuided setup and upgrade-check experience for Lattice projects -- scans the repository, detects existing configuration and outdated conventions, suggests refiners and available upgrades in priority…
- Learning HarvestManage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time.
- Refactor SafelyRestructure existing code safely without changing externally observable behavior.
- Refiners UpdateUpdate existing Lattice standards after a significant change — the update-mode counterpart to lattice-init.
- Requirement ForgeGenerate structured feature specifications through a collaborative product interview.
- Requirement Forge RefinerFacilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming…
- Requirement QualityApply requirement quality principles when generating or validating feature specifications.
- ReviewPerform a structured code review by composing validation checklists from relevant atoms based on what code changed.
- Review RefinerFacilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classification, report format, scope rules, insight capture, and health logging.
- Secure CodingApply security-conscious thinking when generating or modifying code.
- Test QualityApply test quality principles when generating or reviewing test code.
- ArchitectureEnforce architectural rules when generating or modifying code, and validate proposed designs before approval (design mode).
- Architecture CompassArchitectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a…
- Architecture RefinerFacilitate a structured conversation to define architecture principles for a repository.
- Bug FixInvestigate, reproduce, and safely fix a bug with regression protection.
- Clean CodeApply clean code principles when generating or modifying implementation code.