Company context
Extract firmographics, traction signals, funding, team composition, tech stack, hiring activity, and decision-makers for a target company. Produces a markdown artifact with qualification score (0-25), ICP fit assessment, red flag analysis, and optional Apollo account brief. Output drops into any client or prospect folder and feeds discovery prep, competitor research, positioning, and proposal scoping.
When to run
Invoke for "company research", "company background", "qualify this prospect", "discovery call prep", "account brief", or whenever the user provides a company URL for research.
Do NOT invoke for competitor analysis, product messaging, buyer personas, or casual website checks.
Skill chain: this is a root/gateway skill. Common downstream chains in the premium reference.
Inputs
Required: Company identifier — website URL, LinkedIn URL, or company name. If name is ambiguous (e.g., "Atlas", "Beam"), confirm with user before proceeding.
Optional (improve quality):
- LinkedIn company URL — sharper team size + org structure
- Specific questions — focus research on areas of interest
- Discovery call date — adds urgency context
Steps
- Validate input. Confirm company is identifiable. If name ambiguous, ask user for URL or clarification.
- Fetch website. Pull homepage (positioning, customer signals), about page (story, team), careers page (hiring signals).
- Search funding. Crunchbase, Tracxn, PitchBook, CB Insights, TechCrunch, Forbes, company press. Query patterns in the premium reference.
- Search revenue / team. GetLatka, Growjo, LeadIQ, Owler, LinkedIn company page. Use revenue-from-team-size heuristics in the premium reference when sources are sparse.
- Extract customer signals. Logo walls, case studies, "trusted by X" claims, G2/Capterra review counts.
- Assign confidence levels. High = official source; Medium = reputable third-party; Low = aggregator/estimate. Map to
[VERIFIED] / [INFERRED] / [ESTIMATED] per ontology. Detail in the premium reference.
- Identify conflicting data + document gaps. Flag sources that disagree. Mark missing data as
[UNAVAILABLE: searched X, Y, Z]. Suggest discovery questions to fill gaps.
- Calculate qualification score (0-25). Five criteria × 0-5: stage fit, revenue fit, industry fit, marketing leader present, ICP signals. Rubric in the premium reference.
- Assess ICP fit signals. Team signals, marketing gaps (opportunities), positioning complexity, intent signals — checklist in the premium reference.
- Check red flags. Layoffs, funding drought, exec departures, pivots, hidden pricing, missing logos, high burn — checklist in the premium reference.
- Generate 3-5 key observations. Discovery-call-ready insights and talking points.
- Optional — account brief mode. If user requests, gate on Apollo credits, then run
apollo_get_organization_job_postings (1 credit) + apollo_search_people (free, filtered to director+). Output hiring activity, key people, outreach angles. Spec in the premium reference.
- Self-evaluate. Run completeness, evidence, and guardrail checks per the premium reference. Flag low-confidence areas before review gate.
- Render output. Use the standard template in the premium reference (traction signals, funding details, team breakdown, qualification score, ICP fit, red flags, key observations, data gaps + optional account brief).
- Review gate (Level 1, quick review). Present qualification score + traction signals. Then surface chain suggestions: competitors? discovery questions? client-discovery? Apollo sequence? Save as reference example if positive feedback.
What good looks like
Evaluations
- All 4 target questions answered (revenue, customers, funding, team) or marked
[UNAVAILABLE: searched X]
- Every data point carries source + confidence level
- Qualification score calculated 0-25 with notes per criterion
- ICP fit + red flags checklists completed
- Data gaps section with discovery questions
- No invented funding/revenue/team numbers —
[UNAVAILABLE] notation when missing
- Confidence levels match the ontology mapping (High → verified, Medium → inferred, Low → estimated)
1---2name: company-context3description: "Researches a company from its URL: firmographics, traction, funding, team, tech stack, hiring and decision-makers, with a 0-25 qualification score, ICP fit read and red flags. Use when asked for company research, a company profile, an account brief or a prospect qualification."4metadata:5 source: https://skillmd.com/skills/matteotitta/company-context6---78# Company context910Extract firmographics, traction signals, funding, team composition, tech stack, hiring activity, and decision-makers for a target company. Produces a markdown artifact with qualification score (0-25), ICP fit assessment, red flag analysis, and optional Apollo account brief. Output drops into any client or prospect folder and feeds discovery prep, competitor research, positioning, and proposal scoping.1112## When to run1314Invoke for "company research", "company background", "qualify this prospect", "discovery call prep", "account brief", or whenever the user provides a company URL for research.1516Do NOT invoke for competitor analysis, product messaging, buyer personas, or casual website checks.1718Skill chain: this is a root/gateway skill. Common downstream chains in the premium reference.1920## Inputs2122**Required:** Company identifier — website URL, LinkedIn URL, or company name. If name is ambiguous (e.g., "Atlas", "Beam"), confirm with user before proceeding.2324**Optional (improve quality):**25- LinkedIn company URL — sharper team size + org structure26- Specific questions — focus research on areas of interest27- Discovery call date — adds urgency context2829## Steps30311. **Validate input.** Confirm company is identifiable. If name ambiguous, ask user for URL or clarification.322. **Fetch website.** Pull homepage (positioning, customer signals), about page (story, team), careers page (hiring signals).333. **Search funding.** Crunchbase, Tracxn, PitchBook, CB Insights, TechCrunch, Forbes, company press. Query patterns in the premium reference.344. **Search revenue / team.** GetLatka, Growjo, LeadIQ, Owler, LinkedIn company page. Use revenue-from-team-size heuristics in the premium reference when sources are sparse.355. **Extract customer signals.** Logo walls, case studies, "trusted by X" claims, G2/Capterra review counts.366. **Assign confidence levels.** High = official source; Medium = reputable third-party; Low = aggregator/estimate. Map to `[VERIFIED] / [INFERRED] / [ESTIMATED]` per ontology. Detail in the premium reference.377. **Identify conflicting data + document gaps.** Flag sources that disagree. Mark missing data as `[UNAVAILABLE: searched X, Y, Z]`. Suggest discovery questions to fill gaps.388. **Calculate qualification score (0-25).** Five criteria × 0-5: stage fit, revenue fit, industry fit, marketing leader present, ICP signals. Rubric in the premium reference.399. **Assess ICP fit signals.** Team signals, marketing gaps (opportunities), positioning complexity, intent signals — checklist in the premium reference.4010. **Check red flags.** Layoffs, funding drought, exec departures, pivots, hidden pricing, missing logos, high burn — checklist in the premium reference.4111. **Generate 3-5 key observations.** Discovery-call-ready insights and talking points.4212. **Optional — account brief mode.** If user requests, gate on Apollo credits, then run `apollo_get_organization_job_postings` (1 credit) + `apollo_search_people` (free, filtered to director+). Output hiring activity, key people, outreach angles. Spec in the premium reference.4313. **Self-evaluate.** Run completeness, evidence, and guardrail checks per the premium reference. Flag low-confidence areas before review gate.4414. **Render output.** Use the standard template in the premium reference (traction signals, funding details, team breakdown, qualification score, ICP fit, red flags, key observations, data gaps + optional account brief).4515. **Review gate (Level 1, quick review).** Present qualification score + traction signals. Then surface chain suggestions: competitors? discovery questions? client-discovery? Apollo sequence? Save as reference example if positive feedback.4647## What good looks like4849### Evaluations5051- All 4 target questions answered (revenue, customers, funding, team) or marked `[UNAVAILABLE: searched X]`52- Every data point carries source + confidence level53- Qualification score calculated 0-25 with notes per criterion54- ICP fit + red flags checklists completed55- Data gaps section with discovery questions56- No invented funding/revenue/team numbers — `[UNAVAILABLE]` notation when missing57- Confidence levels match the ontology mapping (High → verified, Medium → inferred, Low → estimated)