agentleFS
matteotittamatteotitta/genesys-skills/skills/company-context/SKILL.md

company-context

Skill53 starsChanged 5 days agoMITView on GitHub

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.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brand-kit.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ai-agents-for-agencies-coachesSkill

    brand-kit

    Establish and enforce per-client brand fidelity using the DESIGN.md standard (google-labs-code/design.md). Use whenever starting work for a client, creating any ad/landing-page/creative, or when brand colors/fonts/spacing are needed. Auto-extracts a client's visual identity into a validated DESIGN.md, keeps a central registry, and feeds the tokens into image-studio (statics), fb-ad-video-studio (video), and landing pages. Triggers: "set up brand for <client>", "make a DESIGN.md", "match the client's brand", "what are their brand colors", "new client onboarding", any creative work that must be on-brand.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do NOT invoke for competitor analysis, product messaging, buyer personas, or casual website checks.

    line 14
  2. Very specific:

    Optional — account brief mode: If user requests, gate on Apollo credits, then run apollo_get_organization_job_postings (1 credit) + …

    line 40
  3. Distinctive:

    Self-evaluate: Run completeness, evidence, and guardrail checks per the premium reference.

    line 41
  4. Distinctive:

    Render output: Use the standard template in the premium reference (traction signals, funding details, team breakdown, qualification score, …

    line 42
  5. Very specific:

    All 4 target questions answered (revenue, customers, funding, team) or marked [UNAVAILABLE: searched X]

    line 49
  6. Distinctive:

    Every data point carries source + confidence level

    line 50
  7. Very specific:

    No invented funding/revenue/team numbers — [UNAVAILABLE] notation when missing

    line 54

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. Validate input. Confirm company is identifiable. If name ambiguous, ask user for URL or clarification.
  2. Fetch website. Pull homepage (positioning, customer signals), about page (story, team), careers page (hiring signals).
  3. Search funding. Crunchbase, Tracxn, PitchBook, CB Insights, TechCrunch, Forbes, company press. Query patterns in the premium reference.
  4. Search revenue / team. GetLatka, Growjo, LeadIQ, Owler, LinkedIn company page. Use revenue-from-team-size heuristics in the premium reference when sources are sparse.
  5. Extract customer signals. Logo walls, case studies, "trusted by X" claims, G2/Capterra review counts.
  6. 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.
  7. Identify conflicting data + document gaps. Flag sources that disagree. Mark missing data as [UNAVAILABLE: searched X, Y, Z]. Suggest discovery questions to fill gaps.
  8. 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.
  9. Assess ICP fit signals. Team signals, marketing gaps (opportunities), positioning complexity, intent signals — checklist in the premium reference.
  10. Check red flags. Layoffs, funding drought, exec departures, pivots, hidden pricing, missing logos, high burn — checklist in the premium reference.
  11. Generate 3-5 key observations. Discovery-call-ready insights and talking points.
  12. 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.
  13. Self-evaluate. Run completeness, evidence, and guardrail checks per the premium reference. Flag low-confidence areas before review gate.
  14. 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).
  15. 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)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.