agentleFS
CodeAlive-AICodeAlive-AI/ceo-ai-os/skills/company-intel/SKILL.md

company-intel

Skill9 starsChanged 6 months agoMITView on GitHub

Full company intelligence report: overview, team, funding, products, news. Use when asked to research a company or understand a potential customer/partner/competitor. For pre-meeting briefings with pipeline context, see meeting-prep. For head-to-head competitor comparison, see competitor-research.

7 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use proto-persona, positioning-statement and 5 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

    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

  • nandanosqlSkill

    positioning-statement

    Define who you serve, what problem you solve, and how you're different using Geoffrey Moore's positioning framework. Creates a clear, defensible market position.

    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

  • +3 more from nandanosql

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before helping, check MEMORY.md for current ICP, competitors, and target accounts.

    line 9
  2. Distinctive:

    Run steps sequentially. Skip a step if not needed or if previous steps gave enough data.

    line 19
  3. Distinctive:

    Only if user needs product/pricing details:

    line 47
  4. Distinctive:

    Start with Step 1 (cheap, fast) — often gives enough for a quick overview

    line 77
  5. Distinctive:

    Add Steps 2-4 only for deep research or meeting prep

    line 78
  6. Distinctive:

    Always use main domain (stripe.com not dashboard.stripe.com)

    line 80

“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

[YOUR_PRODUCT] Context

Before helping, check MEMORY.md for current ICP, competitors, and target accounts. Output in Russian (company names, titles, and product names in original). For chat platforms: structured summary, no raw JSON.

Company Intelligence Report

Generate a full intelligence report on any company using multiple Orthogonal APIs.

Workflow

Run steps sequentially. Skip a step if not needed or if previous steps gave enough data.

Step 1: Company Overview (Brand.dev)

orth run brand-dev /v1/brand/retrieve -q domain=COMPANY_DOMAIN

Returns: name, description, logo, colors, social links, industry.

Step 2: Leadership Team (Fiber)

orth run fiber /v1/people-search -d '{"searchParams": {"company_names": ["COMPANY_NAME"], "job_titles": ["CEO", "CTO", "CFO", "COO", "VP"]}}'

Returns: names, titles, LinkedIn URLs.

Step 3: Company Data & Size (Fiber)

orth run fiber /v1/company-search -d '{"searchParams": {"company_names": ["COMPANY_NAME"]}}'

Returns: employee count, location, industry, funding.

Step 4: Products & Pricing (ScrapeGraph)

Only if user needs product/pricing details:

orth run scrapegraph /v1/smartscraper -d '{"website_url": "https://COMPANY_DOMAIN/pricing", "user_prompt": "Extract all products, pricing tiers, and key features"}'

Output Format

Present as structured report:

**[Company Name]** — [one-line description]

Industry: [industry]
Employees: [count]
HQ: [location]
Funding: [total raised, last round]

Leadership:
- [Name] — [Title]
- [Name] — [Title]

Products: [brief summary]
Pricing: [tiers if available]

Key links: [website], [LinkedIn], [Twitter]

Tips

  • Start with Step 1 (cheap, fast) — often gives enough for a quick overview
  • Add Steps 2-4 only for deep research or meeting prep
  • For competitors specifically, use competitor-research skill instead
  • Always use main domain (stripe.com not dashboard.stripe.com)

Related Skills

  • meeting-prep — pre-meeting briefings combining company + person + pipeline context
  • pipeline-manager — store company research as pipeline prospect data
  • signal-scanner — automated company discovery via buying signals
  • competitor-research — head-to-head comparison with products/strategy analysis
  • lead-enrichment — enrich a specific person at the company
  • person-lookup — deep lookup on a single person
  • exa-company-research — web-based company research via Exa

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.