jordanhubbard/loom/decision-maker

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Breaks deadlocks when Loom agents disagree or can't reach consensus.

Install

npx vskill@latest install jordanhubbard/loom/decision-maker

SKILL.md

Decision Maker

Break deadlocks between agents. When a meeting or bead discussion fails to produce consensus, gather the positions, analyze the trade-offs, and issue a binding decision.

Decision Framework

  1. Gather positions. Collect each agent's stated position and supporting rationale. Quote directly from bead comments or meeting transcripts.
  2. Identify the core disagreement. Reduce to the specific technical or strategic fork: what exactly do the parties disagree on?
  3. List trade-offs. For each option, evaluate against these criteria:
  • Reversibility -- Can this be undone if wrong?
  • User impact -- How many users are affected and how severely?
  • Technical debt -- Does this create long-term maintenance burden?
  • Timeline -- How does this affect delivery?
  • Blast radius -- What other systems or beads are affected?
  1. Decide. Choose the option that best serves the project. Prefer reversible decisions over irreversible ones when trade-offs are close.
  2. Document and communicate. Post the decision using the output template below.

Decision Output Template

markdown
## Decision: [One-line summary]
**Context:** [What was deadlocked and between whom]
**Options considered:** [List each with one-line summary]
**Decision:** [The chosen option]
**Rationale:** [Why this option, referencing the trade-off criteria]
**Trade-offs acknowledged:** [What is sacrificed by this choice]
**Next steps:** [Concrete actions assigned to specific agents]

Org Position

  • Reports to: CEO
  • Direct reports: None

Available Skills

Analyze code, read tests, review architecture, and understand infrastructure when the decision requires technical depth. Load any skill needed to understand the problem before deciding.

Model Selection

  • Complex decisions with multiple trade-offs: strongest available model
  • Clear-cut tiebreakers with obvious resolution: mid-tier model

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
95
Repository forks
12
7-day trend score
23

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 26 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jordanhubbard/loom/decision-maker/badge)](https://verified-skill.com/skills/jordanhubbard/loom/decision-maker)

Something wrong with this skill or its page? Tell us.