Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Validate a monthly investor update against a rubric of strong-update sections (transparency, decision-relevance, specific asks). Use before sending a monthly investor update or setting a fundraise communication cadence.
.claude/skills/borghei-investor-update-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 159% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 25% | 0% |
Validate a draft monthly investor update against a rubric of what makes them work — and provide a starting template if you don't have one yet.
investor update, monthly update, founder update, investor communication, fundraise, lead investor, board, KPIs, asks
Before generating the update, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
update.mdpython scripts/investor_update_validator.py update.mdOR start from scratch with assets/investor_update_template.md.
assets/investor_update_template.mdpython scripts/investor_update_validator.py update.mdTime Estimate: 1-2 hours/month.
references/what_makes_good_updates.mdTime Estimate: 1 week to set up; recurring monthly thereafter.
Scans an update markdown file for the structural sections of a strong update and scores it.
bashpython scripts/investor_update_validator.py update.md python scripts/investor_update_validator.py update.md --json
references/what_makes_good_updates.md — What separates good investor updates from badassets/investor_update_template.md — Monthly update template| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,254 | 11,375 | +1% | 1 | 1 | 0% | 1,750 | 2,486 | +42% | 0 | 0 | — |
case-02 | fail→fail | 14,263 | 12,278 | -14% | 1 | 1 | 0% | 2,173 | 2,694 | +24% | 0 | 0 | — |
case-03 | fail→pass | 6,953 | 12,464 | +79% | 1 | 1 | 0% | 1,033 | 2,679 | +159% | 0 | 0 | — |
case-04 | fail→pass | 12,233 | 2,574 | -79% | 1 | 1 | 0% | 2,146 | 1,212 | -44% | 0 | 0 | — |
case-05 | pass→pass | 6,520 | 3,305 | -49% | 1 | 1 | 0% | 976 | 1,255 | +29% | 0 | 0 | — |
case-06 | fail→pass | 9,809 | 5,406 | -45% | 1 | 1 | 0% | 1,589 | 1,475 | -7% | 0 | 0 | — |
case-07 | pass→pass | 11,868 | 7,574 | -36% | 1 | 1 | 0% | 1,635 | 2,068 | +26% | 0 | 0 | — |
case-08 | pass→pass | 10,972 | 8,500 | -23% | 1 | 1 | 0% | 1,628 | 1,943 | +19% | 0 | 0 | — |
case-09 | pass→pass | 13,739 | 8,838 | -36% | 1 | 1 | 0% | 2,011 | 2,045 | +2% | 0 | 0 | — |
case-10 | pass→pass | 12,408 | 10,100 | -19% | 1 | 1 | 0% | 1,846 | 2,213 | +20% | 0 | 0 | — |
case-11 | fail→pass | 13,228 | 13,192 | -0% | 1 | 1 | 0% | 1,921 | 2,408 | +25% | 0 | 0 | — |
case-12 | pass→pass | 13,009 | 11,356 | -13% | 1 | 1 | 0% | 1,747 | 2,478 | +42% | 0 | 0 | — |
case-13 | fail→pass | 11,590 | 4,961 | -57% | 1 | 1 | 0% | 1,723 | 1,538 | -11% | 0 | 0 | — |
case-14 | pass→pass | 10,052 | 10,477 | +4% | 1 | 1 | 0% | 1,589 | 2,374 | +49% | 0 | 0 | — |
case-15 | pass→pass | 13,269 | 11,831 | -11% | 1 | 1 | 0% | 1,881 | 2,356 | +25% | 0 | 0 | — |
case-16 | pass→pass | 10,432 | 9,253 | -11% | 1 | 1 | 0% | 1,504 | 2,056 | +37% | 0 | 0 | — |
case-17 | fail→pass | 12,004 | 9,117 | -24% | 1 | 1 | 0% | 1,819 | 2,184 | +20% | 0 | 0 | — |
case-18 | pass→pass | 9,714 | 6,862 | -29% | 1 | 1 | 0% | 1,583 | 1,761 | +11% | 0 | 0 | — |
case-19 | fail→pass | 5,318 | 1,619 | -70% | 1 | 1 | 0% | 942 | 957 | +2% | 0 | 0 | — |
case-20 | pass→pass | 17,016 | 16,108 | -5% | 1 | 1 | 0% | 2,602 | 3,046 | +17% | 0 | 0 | — |
case-21 | pass→pass | 7,032 | 9,778 | +39% | 1 | 1 | 0% | 1,329 | 2,522 | +90% | 0 | 0 | — |
case-22 | pass→pass | 18,084 | 16,804 | -7% | 1 | 1 | 0% | 2,536 | 3,220 | +27% | 0 | 0 | — |
case-23 | pass→pass | 6,441 | 5,631 | -13% | 1 | 1 | 0% | 1,012 | 1,580 | +56% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.