Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build a candidate's research brief on a company before an application or interview. Use when asked to research a company for a job, prep a company brief before an interview, or understand a prospective employer fast. Produces a one-page brief — what they do & how they make money, recent news & trajectory, product & competitors, likely challenges, culture signals, and smart questions to ask.
.claude/skills/mohitagw15856-company-brief/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -1% | 0% |
Walking into an interview without understanding the business is the fastest way to look like you're just collecting offers. This skill assembles a candidate's research brief — what the company does, how it makes money, where it's heading, and the challenges you'd be hired to help with — so you can speak to their reality and ask questions that signal you've done the work.
Ask for these only if they aren't already provided:
> Note: ground this in real, provided information. Where current facts aren't supplied, say so and mark inferences as assumptions — don't fabricate funding rounds, metrics, or news.
1. What they do & how they make money — the business in plain terms: product, customers, and the revenue model. If you can't tell how they make money, that's itself worth noting.
2. Trajectory & recent news — stage, growth signals, funding/earnings, launches, leadership changes (from the info provided). Where it's clearly heading.
3. Product & competitors — the core product, who they compete with, and their differentiation (or lack of it).
4. Likely challenges — the 2–3 problems this company is probably grappling with that this role would touch. This is the gold: it's what you'll speak to in the interview.
5. Culture signals — what their site, JD, reviews, and public voice suggest about how they work (and whether you'd want to).
6. Smart questions to ask — 4–6 questions that show you understand their business and surface what you need to know (avoid generic "what's the culture like?").
7. Your angle — how to connect your background to their specific situation, in one or two lines.
Interview research / company due-diligence practice for candidates (business model · trajectory · role-relevant challenges).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,612 | 20,698 | -8% | 1 | 1 | 0% | 3,815 | 4,090 | +7% | 0 | 0 | — |
case-02 | fail→fail | 30,073 | 17,751 | -41% | 1 | 1 | 0% | 5,278 | 3,787 | -28% | 0 | 0 | — |
case-03 | fail→fail | 31,042 | 16,082 | -48% | 1 | 1 | 0% | 5,359 | 3,603 | -33% | 0 | 0 | — |
case-04 | pass→pass | 12,608 | 15,182 | +20% | 1 | 1 | 0% | 2,223 | 3,158 | +42% | 0 | 0 | — |
case-05 | pass→fail | 7,687 | 16,757 | +118% | 1 | 1 | 0% | 1,382 | 3,549 | +157% | 0 | 0 | — |
case-06 | pass→fail | 8,076 | 14,156 | +75% | 1 | 1 | 0% | 1,434 | 3,039 | +112% | 0 | 0 | — |
case-07 | fail→pass | 11,911 | 3,078 | -74% | 1 | 1 | 0% | 1,873 | 1,257 | -33% | 0 | 0 | — |
case-08 | fail→fail | 23,501 | 15,991 | -32% | 1 | 1 | 0% | 3,929 | 3,472 | -12% | 0 | 0 | — |
case-09 | fail→pass | 14,298 | 17,895 | +25% | 1 | 1 | 0% | 2,330 | 3,707 | +59% | 0 | 0 | — |
case-10 | fail→pass | 17,224 | 13,216 | -23% | 1 | 1 | 0% | 2,910 | 2,816 | -3% | 0 | 0 | — |
case-11 | pass→pass | 15,359 | 13,513 | -12% | 1 | 1 | 0% | 2,353 | 3,082 | +31% | 0 | 0 | — |
case-12 | pass→pass | 17,586 | 12,913 | -27% | 1 | 1 | 0% | 2,856 | 2,826 | -1% | 0 | 0 | — |
case-13 | fail→pass | 16,688 | 11,931 | -29% | 1 | 1 | 0% | 2,730 | 2,701 | -1% | 0 | 0 | — |
case-14 | fail→fail | 22,983 | 16,324 | -29% | 1 | 1 | 0% | 3,803 | 3,583 | -6% | 0 | 0 | — |
case-15 | pass→pass | 18,559 | 15,344 | -17% | 1 | 1 | 0% | 2,887 | 3,168 | +10% | 0 | 0 | — |
case-16 | fail→pass | 20,697 | 13,542 | -35% | 1 | 1 | 0% | 3,519 | 3,044 | -13% | 0 | 0 | — |
case-17 | fail→pass | 23,038 | 18,275 | -21% | 1 | 1 | 0% | 3,550 | 3,412 | -4% | 0 | 0 | — |
case-18 | pass→fail | 19,819 | 14,691 | -26% | 1 | 1 | 0% | 3,221 | 2,952 | -8% | 0 | 0 | — |
case-19 | fail→pass | 21,115 | 14,481 | -31% | 1 | 1 | 0% | 3,168 | 2,803 | -12% | 0 | 0 | — |
case-20 | pass→pass | 14,715 | 16,277 | +11% | 1 | 1 | 0% | 2,352 | 3,214 | +37% | 0 | 0 | — |
case-21 | fail→pass | 21,032 | 15,217 | -28% | 1 | 1 | 0% | 3,031 | 3,065 | +1% | 0 | 0 | — |
case-22 | fail→pass | 27,915 | 14,897 | -47% | 1 | 1 | 0% | 4,315 | 3,133 | -27% | 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. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
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.