pitch-review
Skill1 starsChanged 4 months agoMITView on GitHub
Stress-test a proposal, business plan, or pitch deck against the seven proposal lenses and the CSAC view. Make the user find the weak spots themselves through questions, then give a synthesized verdict at the end.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- solanabr/startup-builder-skilltheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- solanabr/startup-builder-skill★ 2same name
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.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Ask for the material: a file, a paste, or a spoken summary.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
/pitch-review — proposal review by interview
Review a proposal, business plan, or pitch deck against the seven lenses in concepts/06-proposal-anatomy.md. Don't red-pen it for them — ask the questions that make them see the weak spot. Give the synthesized verdict only at the end.
Start
- Ask for the material: a file, a paste, or a spoken summary. If it's long, ask what the single ask of the proposal is first.
- Say which seven lenses you'll run, one line each, so they know the yardstick.
The seven lenses (as questions)
Walk them one or two at a time — not as a checklist dump. For each, ask before you judge.
- Conclusion first? "Where does a reader first learn your core point — page 1, or page 12? Is the proof up front or in an appendix?"
- Battlefield choice. "Are you fighting the incumbent where it's strong? What axis did you redraw the problem onto — and can you actually win there?"
- Logic-tree → strategy axis. "What's the split that organizes your strategies? Does the set close the funnel, or only open it (acquisition with no retention)?"
- Target × strategy alignment. "Are the targets you name early the same ones your later strategies serve? Where do they drift apart?"
- Slide grammar. "Does each key page carry a one-line conclusion up top and a one-line implication at the bottom, or does the reader have to infer the point?"
- A concept that bookends. "Is there a single line that opens and closes the deck? What is it?"
- Feasibility signals. "What in here says 'this will actually ship' — a real benchmark, real usage, a lifecycle-based roadmap? Or is it all intention?"
The CSAC cross-check
Alongside the seven lenses, probe the underlying logic:
- Clarification: "Is the problem it solves the real problem, or a symptom?"
- Structuring: "Is the core claim conclusion-shaped and falsifiable, or a vague aspiration?"
- Analysis: "For the biggest claim — what evidence backs it, and what shape is that evidence?"
- Watch for the quantitative caution: if the ask needs numbers and the deck is all qualitative structure, name that gap.
Verdict
At the end, and only then, synthesize:
- Strongest 1–2 lenses (what's working — be specific about why).
- Weakest 1–2 lenses (the load-bearing weaknesses, ranked).
- The one change that would move the proposal most, and why.
Offer to save the review to cases/YYYY-MM-DD-topic-review.md if it went deep.
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.

