/feedback -- Record stakeholder input

SkillDev tools

Record stakeholder input — new constraints, corrections, or direction changes.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the /feedback -- Record stakeholder input skill

What this skill tells your AI

The instructions your AI receives, as published by grainulation/grainulator in skills/feedback/SKILL.md and read by ahel’s review.

The user is relaying feedback from stakeholders that should be incorporated into the sprint.

Arguments

$ARGUMENTS

Instructions

  1. Parse the feedback: Identify what the stakeholder said. This could be:

    • A new constraint ("CTO says prioritize speed over cost")
    • A correction ("compliance says we need SOC2 Type II, not Type I")
    • A direction change ("skip the custom build, focus on Auth0 vs Clerk")
    • A new question ("what about latency in EU regions?")
  2. Create feedback claims as f### claims:

    • Type: constraint for hard requirements, feedback for opinions/preferences
    • Evidence tier: stated (stakeholder said it, not independently verified)
    • Tag with the stakeholder's name or role
  3. Check for conflicts: Does this feedback contradict existing claims? If a stakeholder says "budget is $10K max" but research shows a solution at $15K, that's a conflict. Set conflicts_with on both claims.

  4. Run wheat_compile to surface any new conflicts.

  5. Print result:

    Feedback recorded:
    - <f001>: <summary>
    - <f002>: <summary>
    
    Conflicts introduced: <N>
    
    Next steps:
      /resolve            -- resolve any new conflicts
      /research <topic>   -- investigate new questions from feedback
      /challenge <id>     -- test if feedback contradicts existing evidence
    

Signals

GitHub stars
86
Forks
6
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
feedback
Source
github.com/grainulation/grainulator