crystallize-north-star

SkillDev tools

Lets your agent turn a research goal into one clear, ambitious, testable North Star sentence with a traceability map.

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

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the crystallize-north-star skill

About this skill

Compress the goal structure and intentionality into a specific, ambitious, achievable one-sentence research North Star.

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/crystallize-north-star/SKILL.md and read by ahel’s review.

Purpose

Compress a validated goal structure into one specific, ambitious, achievable research North Star.

Input contract

required: [goal_tree, constraints, intended_effect]
optional: [feasibility_annotations, actor_profile, evidence_context]
constraints: [the statement must preserve the declared outcome and limiting constraints]

Procedure

  1. Identify the highest-value outcome and the mechanism or capability it should change.
  2. Remove branch detail that does not distinguish the intended direction.
  3. Draft one sentence with outcome, scope, and constraint boundaries.
  4. Check traceability back to the goal tree and record unresolved tension.

Output contract

produces: [north_star_statement, research_brief, traceability_map, unresolved_tensions]
delta_fields: [findings, hypothesis_updates, decisions, uncertainties, open_questions]

Quality gates

  • The statement is testable and scoped.
  • Every essential term traces to a goal or constraint.

Failure and counterexamples

Do not turn a slogan into a North Star or omit constraints merely to make the sentence aspirational.

Provenance map

  • resolved: north-star-crystallization-crystallize-north-star

Signals

GitHub stars
501
Forks
41
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
crystallize-north-star
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine