agentleFS
NagiliantNagiliant/Genesis-Legacy-V2/skills/genesis-northstar/SKILL.md

North Star

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Write the perfect-world vision for the feature — no-compromise narrative, weighted quality dimensions, and the Compass. The qualitative reference every audit measures against.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the North Star: a first-person, no-compromise vision of the feature in a perfect world, plus weighted Quality Dimensions and The …

    line 9
  2. Very specific:

    Write northstar.md from north-star-template.md, in first person, four sections:

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

North Star — The Perfect World

Write the North Star: a first-person, no-compromise vision of the feature in a perfect world, plus weighted Quality Dimensions and The Compass (decision filters for subjective choices). It is the qualitative reference every later audit — especially A4 and the F-pass — measures against.

Gate: the specify phase must be accepted. Requires the spec and design docs.

Inputs

  • .genesis/project-state.md (mode)
  • .genesis/features/<feature>/spec.md (required), design.md (required), brainstorm-log.md
  • The constitution
  • approvals/master.json (verify specify accepted)

Process

  1. Resolve the feature name; handle an existing North Star (revise in place, or archive to northstar-v{N}.md and write fresh) and partial-file resumption.
  2. Deep-read the entire master spec — every FR, AC, user story, NFR.
  3. Write northstar.md from north-star-template.md, in first person, four sections:
    • The Perfect World — narrative of the feature when every requirement is perfectly met; experience, not mechanism; mode-aware.
    • Quality Dimensions — feature-specific dimensions, each weighted Critical / Important / Nice, each with what it means, a concrete and testable "what perfect looks like," and one test question. Always include Zero-Tolerance Quality (Critical).
    • The Emotional Quality — "for the user" and "for the builder," mode-aware.
    • The Compass — decision filters phrased as questions, mode-aware.
  4. No-compromise validator (up to 3 iterations): strip implementation detail, timeline language ("in v1", "for now", "later"), compromise language ("MVP", "good enough", "adequate"), and vague quality terms; fill missing perspectives; rewrite product-brochure voice into a grounded one. Concrete is allowed ("sub-100ms"); naming implementation is not ("Redis cache").
  5. Constitution-compliance check; present; commit.

Mode differences

  • Greenfield: the perfect technical system.
  • Brownfield: perfect integration (no regression, clean boundaries); add the compass question "Does this respect what exists?"
  • Lowfield: perfect content pipeline (every stage and artifact earns its place); add "Does this serve the domain or just the process?"

Output

  • .genesis/features/<feature>/northstar.md — the perfect-world vision + weighted quality dimensions + compass.

Next step

Brainstorm the first group at the micro boundary (/genesis-brainstorm --boundary micro), then /genesis-micro 0.

Natural language triggers

- "write the north star"
- "perfect world vision"
- "quality dimensions for X"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.