agentleFS
Sign inStart free
SpiderIQSpiderIQ/skills/skills/SpiderCompanyData/company-intel/SKILL.md

company-intel

Skill1 starsChanged 3 months agoMITView on GitHub

Company intelligence research — full pipeline: Perplexity discovery, website crawl, company registry lookup, email verification, and people/LinkedIn extraction. Single or batch (up to 50).

7 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use positioning-workshop, proto-persona and 6 more.

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.
  • nandanosqlSkill

    positioning-workshop

    Facilitate a guided positioning session that walks through target customer, problem, category, benefit, and differentiation using April Dunford's methodology with adaptive questions.

    Also in 4 projects that use this

  • nandanosqlSkill

    proto-persona

    Create hypothesis-driven user personas before doing full research. Uses behavioral attributes, goals, and frustrations to model target users quickly for early-stage alignment.

    Also in 3 projects that use this

  • Dragoon0xSkill

    roadmap-planning

    Build and communicate a product roadmap that balances customer needs, business goals, and team capacity. Covers outcome-driven planning, stakeholder communication, and roadmap hygiene. Use when planning quarters, aligning stakeholders on direction, or when the roadmap feels like a feature wishlist.

    Also in 3 projects that use this

  • huntsyeaSkill

    jobs-to-be-done

    Applies Bob Moesta's demand-side thinking and Jobs-to-be-Done framework to help product teams understand why customers switch, hire, and fire products. Use when conducting switch interviews, drawing forces diagrams, writing job statements, mapping demand timelines, understanding the struggling moment, analyzing why customers hire or fire your product, exploring passive or active looking behavior, researching JTBD, or when user mentions Bob Moesta, demand-side thinking, big hire, little hire, push/pull/anxiety/habit, or the four forces of progress.

    Also in 3 projects that use this

  • +4 more from nandanosql

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Distinctive:

    If you know the domain, pass it — skips Perplexity discovery step (faster)

    line 38
  2. Distinctive:

    If you know the LinkedIn URL, pass it — skips LinkedIn search step

    line 39

“Common” is measured: kept by at least 6 in 10 of the 7 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-intel #data_collection

deep company research — full pipeline: Perplexity discovery, website crawl, registry lookup, email verify, LinkedIn extraction

/#lookup-company-data → basic company registration/VAT data only /#scrape-google-maps → local business discovery by geography /#scrape-website-extract-leads → website scraping without company context

Chain

researchCompany → getJobStatus (poll 10s) → getJobResults researchBatch (up to 50) → getJobStatus → getJobResults

Limits

$batch:max 50 companies per batch job

Pitfalls

  • If you know the domain, pass it — skips Perplexity discovery step (faster)
  • If you know the LinkedIn URL, pass it — skips LinkedIn search step
  • Single company research is faster for urgent requests — use researchBatch for bulk

Case $t:2026-04

UK fintech companies: Batch(15 companies)→Discovery→Site crawl→Companies House→Verify→LinkedIn→12 complete profiles. 12min.

Methods

  • researchCompany(company_name, city?, country_code?, domain?, linkedin_url?, profile_mode?, max_employees?, config?, test?) — Research a single company through the full intelligence pipeline. Returns job_id to poll for results via GET /jobs/{job_id}/results. → getJobStatus (poll every 10s)
  • researchBatch(companies, profile_mode?, max_employees?, config?, test?) — Research multiple companies in batch (max 50). Same pipeline, processes all companies. Returns job_id to poll. → getJobStatus (poll every 10s) [WARN: max 50 companies per batch]
  • getJobStatus(job_id) — Check status of a company intel job.
  • getJobResults(job_id) — Get results of a completed company intel job.

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.

Check your setup, free