venture-health-check
Skill4 starsChanged 8 months agoMITView on GitHub
Check the health of one or all ventures and score them across dimensions
In this repository14 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- brand-setupSkill
- daily-digestSkill
- deploySkill
- ecosystem-scoutSkill
- process-approvalsSkill
- publish-contentSkill
- qa-checkSkill
- send-outreachSkill
- submit-for-approvalSkill
- venture-bootstrapSkill
- venture-intakeSkill
- venture-staffingSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Distinctive: line 20
If provided: check only that venture
- Distinctive: line 21
If empty: check all active ventures
- Very specific: line 25
If slug provided, use it. Otherwise read portfolio/registry.md and get all ventures where stage is NOT KILLED, PAUSED, or MATURE.
- Distinctive: line 41
Read these files (skip if they don't exist):
- Very specific: line 93
Update portfolio/registry.md with new health scores and last check date.
- Distinctive: line 97
If any venture scores below 50:
- Distinctive: line 98
Write a brief health alert explaining what's wrong
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Venture Health Check
Score venture health across multiple dimensions. Used by scheduled health checks and on-demand.
Input
Optional venture slug: $ARGUMENTS
- If provided: check only that venture
- If empty: check all active ventures
Step 1: Get Ventures
If slug provided, use it. Otherwise read portfolio/registry.md and get all ventures where stage is NOT KILLED, PAUSED, or MATURE.
Step 2: For Each Venture
2a: Pull Latest
cd $PROJECTS_DIR/{slug} && git pull --quiet 2>/dev/nullIf not cloned:
gh repo clone {user}/{slug} $PROJECTS_DIR/{slug} -- --quiet 2>/dev/null2b: Read State Files
Read these files (skip if they don't exist):
CLAUDE.md— venture context and focusplans/current.md— active plan, how many tasks completed vs pendingdocs/changelog.md— last entry date (recency of progress)metrics/— any metric filesdecisions/— recent decisionslearnings/— any learnings captured
2c: Check Git Activity
cd $PROJECTS_DIR/{slug} && git log --oneline -10 --format="%h %ad %s" --date=shortThis shows recent commit activity — a proxy for work being done.
2d: Score Health
Score 0-100 across these dimensions:
Progress Velocity (0-25)
- 25: Multiple commits this week, tasks being completed, changelog updated recently
- 15: Some activity this week but slow
- 5: No activity in the past week
- 0: No activity in 2+ weeks
Plan Clarity (0-25)
- 25:
plans/current.mdexists, has clear objectives and tasks, tasks are being checked off - 15: Plan exists but is stale or vague
- 5: No clear plan
- 0: No
plans/current.mdat all
Documentation Health (0-25)
- 25: Key docs exist and are populated (not just templates), changelog is up to date
- 15: Docs exist but some are still templates/placeholders
- 5: Minimal documentation
- 0: No docs beyond initial scaffold
Stage Appropriateness (0-25)
- 25: Venture is doing work appropriate to its stage and making progress toward exit criteria
- 15: Work is appropriate but slow
- 5: Work seems misaligned with stage (e.g., building features during validation)
- 0: No evidence of stage-appropriate work
Overall Score = sum of all dimensions
Health Levels:
- 80-100: Healthy — operating well
- 60-79: Attention — some areas need improvement
- 40-59: Warning — significant issues, flag for founder
- 0-39: Critical — needs immediate founder attention
Step 3: Update Registry
Update portfolio/registry.md with new health scores and last check date.
Step 4: Flag Issues
If any venture scores below 50:
- Write a brief health alert explaining what's wrong
- Include in the output for the founder
Step 5: Output
Display a health summary:
## Venture Health Check — {date}
| Venture | Stage | Health | Velocity | Plan | Docs | Stage Fit |
|---------|-------|--------|----------|------|------|-----------|
| {slug} | {stage} | {total}/100 | {v}/25 | {p}/25 | {d}/25 | {s}/25 |
{If any alerts:}
### Alerts
- **{slug}** ({score}/100): {brief description of issue}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
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.

