north-star
Skill1 starsChanged 10 months agoMITView on GitHub
Evaluate whether current work serves the project's ultimate goal. Scores branches, goals, and commits against declared pillars/objectives. Flags drift and misalignment.
Files
North Star — Ultimate Goal Alignment Check
Evaluate whether the current work serves the project's declared ultimate goal. Scores current branch, active goals, and recent changes against the project's core objectives. Flags drift, gaps, and misaligned work.
Quick Start
# Full alignment audit of current session
/north-star
# Quick 2-3 sentence check
/north-star session
# Score only the current branch
/north-star branch
# Score only active um-goals
/north-star goals
# Retrospective: classify last 20 commits by objective
/north-star retroHow It Works
- Load the project's north star — reads
ULTIMATE_GOALS.md(or equivalent) from the repo root. Extracts core objectives, pillars, stage progress, anti-goals, and remaining gaps. - Gather current work context — branch diff vs main/dev, active um-goals, recent commits, changed files.
- Classify every change — each file, commit, and goal maps to a pillar/objective (or is flagged as drift).
- Score alignment — overall verdict: ALIGNED, ENABLING, DRIFTING, or OFF-MISSION.
- Gap analysis — which objectives this work advances, which are untouched, which are most urgent.
- Actionable recommendations — concrete next steps based on alignment state.
Setup
The skill requires a goal definition file in your repo root. Create one of:
ULTIMATE_GOALS.md(preferred)GOALS.mdNORTH_STAR.md- A
## Goalsor## Objectivessection in yourCLAUDE.md
Minimal ULTIMATE_GOALS.md template
# Ultimate Goals
## Prime Directive
> One sentence describing what success looks like for this project.
## Pillars
1. **Pillar Name** — what this pillar delivers
- Stage 0: ... (status: shipped / in-progress / planned)
- Stage 1: ...
2. **Pillar Name** — ...
## "Are We Getting Closer?" Checklist
1. Question about pillar 1 progress (YES/NO test)
2. Question about pillar 2 progress (YES/NO test)
## Anti-Goals
- Things we explicitly do NOT do
- Bright lines we don't cross
## Remaining Gaps
- What's still missing before the system is "done"Output Format
## North Star Alignment — {date}
### Current Work
Branch: {branch}
Active Goals: {count}
Files Changed: {count}
### Pillar Scorecard
| Pillar | Stage | Advancing? | Detail |
|--------|-------|------------|--------|
| ... | ... | ... | ... |
### Overall: {ALIGNED / ENABLING / DRIFTING / OFF-MISSION}
{one-line summary}
### "Are We Getting Closer?"
1. {checklist question}: {YES/NO} — {evidence}
2. ...
### Gaps & Priorities
- Closest to closing: {gap}
- Most urgent unaddressed: {gap}
- This work's contribution: {what it closes}
### Recommendations
{actionable next steps}Scoring Rules
| Score | Meaning | Action |
| ALIGNED | Work directly advances at least one pillar | Confirm and continue |
| ENABLING | Infrastructure that unblocks a specific pillar (must name which) | Valid, but tie it to a pillar |
| DRIFTING | Doesn't clearly map to any pillar | Ask for justification |
| OFF-MISSION | Contradicts an anti-goal or delays pillar progress | Flag and suggest alternatives |
Design Principles
- Read-only — never modifies files, goals, or branches
- Honest — if work is drifting, say so. No rationalizing.
- Actionable — every finding comes with a concrete next step
- Fast in session mode — 2-3 sentences, under 30 seconds
- Anti-goals are bright lines — if anything approaches one, name it explicitly
- Infrastructure is valid — but it must be tied to a pillar to score ENABLING
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- andreaskelm/pm-brain★ 234same name
- fusebase-dev/fusebase-flow★ 9same name
- ai-analyst-lab/north-star★ 8same name
- BhaskarManam/pstack★ 4same name
- raphaelDkhn/worldbuilder★ 3same name
- uzysjung/uzys-agent-harness★ 3same name
- ele-yufo/unstuck★ 2same name
- Naoray/skills★ 2same name
- poponline63/north-star★ 2same name
- agentmart/pm-os★ 1same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use strategy.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
EpistatesSkillstrategy
Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.
Also in 3 projects that use this
In this repository2 other files it gives its agents.
- manus-workflowSkill
- um-goalsSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

