agentleFS
VeeiyVeeiy/vantage-os/skills/venture-triage/SKILL.md

venture-triage

Skill0 starsChanged 5 months agoMITView on GitHub

Weekly venture scoring and triage. Use when the operator says "venture triage", "weekly review", "score the ventures", "what should I kill", "where's my time going", or on a weekly cadence. Scores each active venture on momentum, ROI per hour, and strategic fit. Forces kill/keep/scale decisions.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    9-11: Keep at current level.

    line 42
  2. Very specific:

    Ask the operator to score each venture (you can propose scores based on ventures.md + your knowledge, then have the operator correct).

    line 49
  3. Very specific:

    Update ventures.md with new scores, today's date, and any status changes.

    line 56
  4. Distinctive:

    the day job is non-negotiable for now: Do not propose cutting hours from the job.

    line 110

≈ “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

Venture Triage

Forcing function. the operator runs too many ventures. This skill scores them and forces ruthless choices.

Read first

~/Vault/Vantage-OS/ventures.md - the full registry.

Scoring rubric

For each active venture, score 1-5 on three axes:

Momentum (last 14 days)

  • 5: Shipped material progress, revenue or users moving
  • 4: Active work, on track
  • 3: Some progress, behind plan
  • 2: Stalled, no shipping
  • 1: Dormant, no thought given

ROI per hour (rough estimate)

  • 5: >$100/hr expected value or strategic
  • 4: $50-100/hr
  • 3: $20-50/hr
  • 2: $10-20/hr
  • 1: <$10/hr or speculative

Strategic fit

  • 5: Core to 12-month income replacement plan
  • 4: Important but not critical
  • 3: Optional but the operator cares
  • 2: Legacy obligation
  • 1: Distraction

Total score interpretation

  • 12-15: Double down. Increase hours.
  • 9-11: Keep at current level.
  • 6-8: Cut hours in half. Set a kill deadline if score doesn't improve.
  • 3-5: Kill, pause, or hand off.

Process

  1. Render the current ventures.md registry as a table with last scores and last-updated date.
  2. Ask the operator to score each venture (you can propose scores based on ventures.md + your knowledge, then have the operator correct).
  3. Compute totals.
  4. Surface anything scoring 6 or below. Force a decision:
  • Kill (remove from registry)
  • Pause (move to parked section)
  • Hand off (assign to someone, e.g., a partner for the wellness venture, or a contractor for fleet cleaning)
  • Reset (define a 30-day plan to revive)
  1. Update ventures.md with new scores, today's date, and any status changes.
  2. Compare with last week's scores. Flag any venture that dropped 3+ points.

the operator's likely starting ventures (from CLAUDE.md)

  • rental-fleet (5 vehicles)
  • a mobile detailing service
  • Stock trading (the operating LLC)
  • Hair product (NEW - top focus)
  • a wellness venture (a partner's, supporting role)
  • a dev project dev project
  • a dev project dev project
  • Vantage Brain (Obsidian knowledge system)
  • Section 8 / real estate research
  • a partner salon (a partner's, supporting / partnering for hair product)

That's 10. He cannot actually push on 10. Triage is non-optional.

Output

# Venture Triage - [DATE]

## Scores

| Venture | Momentum | ROI/hr | Fit | Total | Δ from last | Verdict |
|---|---|---|---|---|---|---|
| ... | ... | ... | ... | ... | ... | ... |

## Forced decisions

### Hair product (total: 13) - DOUBLE DOWN
- Increase hours from X to Y
- Specific next action: ...

### [Venture below 9] - CUT or KILL
- Recommendation: ...
- the operator's call: [logged here]

## Hours allocation proposed for next 7 days

- Hair product: X hrs
- rental-fleet: Y hrs
- Trading: Z hrs
- School: W hrs
- ...
Total: not to exceed 40 hrs of venture time (the operator has a full-time job + sleep + a partner + gym + transit)

Rules

  1. No venture survives below total 6 for two weeks running. Force kill or hand off.
  2. No more than 4 ventures can be in "double down" or "keep" at once. If more, force ranking and demotion.
  3. Sundays do not count for hours allocation. protected personal time.
  4. the day job is non-negotiable for now. Do not propose cutting hours from the job.

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.