Praxikit

All kits / Skill

pitch-panel

Built by PraxikitSkillv0.2.1released 2026-11-15Planning

Put a startup idea in front of six seats (CTO, CMO, COO, PM, CFO, devil's advocate), then get a verdict and one cheap test.

Save

What you'll see

One seat's blockIllustrative output for a made-up idea (a subscription box of left-handed kitchen tools). Every number is tagged.
## CFO   Vote: Back it if   Score: 3/5

Strongest objection: at $39 a box with 40% product cost and about $9 shipping, contribution is roughly $14 a box [assumption]; a $25 acquisition cost pays back in two boxes only if monthly churn stays under 15% [assumption].
Why it matters: most subscription boxes lose half their buyers in three months, which would erase the margin.
What would change my mind: a pre-order cohort where 40% re-order the second box.
Question I would ask in the room: what happens to cash if only half the expected boxes sell?
One number I would want: landed cost per box from two real suppliers.
The devil's advocateSame made-up idea. It speaks last and must name something the other five did not.
## Devil's advocate   Catastrophic risk

Scenario: one large marketplace lists a cheaper left-handed range and takes the search traffic the whole plan depends on.
Trigger: the marketplace sees the category selling.
Likelihood: medium [assumption]
Earliest warning sign: competing listings appearing under the same search terms.
Cheapest hedge: build an email list of buyers from day one, so demand does not depend on one platform's search.
The verdictSame made-up idea. The test and its pass bar are stated before it is run.
## Verdict: Go if   (score 17/25)

Conditions: 1. Buyers pay for a one-off box, not only a subscription (PM). 2. Landed cost leaves 40% margin after shipping (CFO). 3. Ten buyers reached for under $5 each (CMO).
Kill triggers: fewer than 5 of 20 interviewees will pay; second-box re-order under 25%.
This week's test: a one-page priced pre-order for a three-item box, shown to 200 left-handed people. Pass bar: 12 pre-orders.
Not checked: competitors' real prices, supplier minimums.

I am not an investor and this is not a prediction; talk to real buyers before you decide.

Skills 1

  • skillgrill

    Put a startup or product idea in front of a six-seat panel (CTO, CMO, COO, PM, CFO and a devil's advocate) that argues against it across technology, market, operations, product, money and catastrop...

What it does on your machine

Reads

  • The idea you describe, and any files or links you point it at

Writes

  • Nothing, unless you ask it to save the result to docs/pitch-panel.md

Network

None from the kit: it has no scripts and no hooks. If your agent has web search it may use it only when you allow it, and the skill says to name the pages it opened.

Reads, writes and network are declared by the kit's author. Read the source before you rely on them.

Build checks

  • Passed: Manifest has every required field
  • Passed: Changelog has an entry for v0.2.1
  • Passed: Plugin manifest version matches the kit version
  • Passed: No scripts to scan
  • Passed: MIT licence file at the repository root
  • Passed: 1 test file in the kit; CI runs them on every push

Computed from the files at commit 88be77c, CI results for it, built 2026-11-16. These show the kit is consistent. They are not a security audit and do not mean the kit is safe.

Honest limits

  • Not investors and not a forecast: the verdict is a structured argument, not a prediction.
  • Only as good as the facts you give it; anything unsourced is tagged as an assumption.
  • The seats are played by one model, so they share its blind spots. Talk to real buyers before you decide.
  • Deep mode (separate sub-agents for each seat) costs many times more tokens than the default single pass.
  • Not affiliated with any television programme or brand.

Changelog

  1. 0.2.1 — 2026-11-15

    Latest
    • Fix: the score total was "out of 30" but only five seats score (the devil's advocate does not), so it could never reach 30. It is now out of 25, and the example uses 17/25.
    • Fix: the rule for "Go" counted six voting seats. The devil's advocate does not vote, so Go now needs at least four of the five voting seats to say Back it, no stop signal, and a cheap hedge for the devil's advocate's scenario. Found by running the skill on a real idea.
  2. 0.2.0 — 2026-11-15

    • Changed: six seats instead of five. CTO (technology), CMO (market and growth, including competition), COO (operations, regulation, disintermediation), PM (product and validated demand), CFO (financials and business model) and a devil's advocate for catastrophic risk. The devil's advocate speaks last, reads the other five, and must name the one scenario none of them raised, with its trigger, warning sign and cheapest hedge.
    • New: every number is tagged [you], [source: page] or [assumption]; a 1 to 5 score per seat; an assumption ledger; what all six assumed without saying; kill triggers alongside the single test; a coverage check that reports any topic nobody owned.
    • New: market size must be built bottom-up, never as a share of a huge market.
    • Changed: one pass is the default. Deep mode (parallel sub-agents) is used only when asked or when the stakes are high, and the skill says it costs many times more tokens.
  3. 0.1.0 — 2026-11-15

    • First release: /pitch-panel:grill. Five seats (customer, money, build, reach, operations) argue against an idea, each with a vote, one objection, what would change their mind, a question and a number. Then a cross-examination, a verdict (Go, Go if, Stop), three conditions and one cheap real-world test with its pass bar stated in advance.