SkillAgentSearch skills...

company-dossier

Build a complete, sourced intelligence dossier on any company from public records — people, money, hiring, tech stack, news and risk — as a web app, CLI and MCP server. Live at companydossier.lol.

Install / Use

claude mcp add ever-just -- npx -y github:ever-just/company-dossier

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

81/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of company-dossier

company-dossier scores 81/100 on our quality scale, 40th of 46 Human Resources skills we index.

Its MCP Server is 6.2 KB long, well organised into 9 sections with 5 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
29/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated yesterday, so company-dossier is actively maintained.
  • Our last check on 2026-09-23 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 92/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-10-03. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

company-dossier compared with similar skills

All 4 of these similar skills score higher than company-dossier; compare them before choosing.

SkillScoreStarsUpdatedFormat
company-dossier (this skill)by ever-just8131d agoMCP Server
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
CowAgentby zhayujie10048.0ktodayCLAUDE.md

Frequently asked questions

How do I install company-dossier?
Run claude mcp add ever-just -- npx -y github:ever-just/company-dossier. The install tabs above show the steps for each supported agent.
Which AI agents does company-dossier work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is company-dossier safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 92/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is company-dossier still maintained?
The repository was last updated yesterday, so company-dossier is actively maintained.

Company Dossier

Build a complete, sourced intelligence dossier on any company from public records — for humans and agents.

Status: Production · npm company-dossier v0.3.4 · public · MIT

npm license

Live site · In-browser generator · Hosted MCP server · VS Code extension · Methodology

| | | |---|---| | What it is | A company-research engine that compiles a nine-section, source-attributed dossier | | Who it's for | Analysts, founders, sales and diligence teams — and the AI agents working for them | | Live at | companydossier.lol · hosted MCP server | | Stack | Node 18+ · TypeScript · zero-dependency static site · GitHub Pages + AWS CloudFront | | Status | Production · npm v0.3.4 · six public-source collectors · no API key required |

The problem it solves

Researching a company properly costs a day and forty open tabs: the website, the archived version of the website, the job board, the funding announcements, the DNS records, the news. Almost all of it is public. None of it is assembled. The tools that do assemble it hand back a raw data dump, put it behind a seat licence, or print a number with no source beside it.

Company Dossier assembles it instead. Give it a company name or a domain and it returns a readable file organised into nine fixed sections, where every derived claim carries the source it came from and every section without public data is marked as a gap rather than filled with a guess. Public sources only. No account, no API key, free.

What it does

  • Nine sections, always the same nine — overview and identity, people, hiring, money, locations, tech fingerprint, news and timeline, relationship web, risk flags.
  • Collects from six public sources — live website crawl, the Internet Archive's Wayback CDX API, DNS and email records, RDAP domain registration, web-technology fingerprinting, and public search and social discovery.
  • Attributes every claim — each section records which source produced it, and the run metadata records which sources answered, degraded, or failed.
  • Runs four ways — in the browser, from the terminal, as an MCP tool for an AI agent, or inside VS Code.
  • Emits machine-readable output — dossier.json alongside the markdown, so a script or an agent reads the same dossier a person does.
  • Publishes a dossier as a site — --format site scaffolds a themed static site and --deploy gh-pages publishes it, noindex by default.

Quickstart

npx company-dossier acme.com                    # writes "Acme DOSSIER/" + dossier.json
npx company-dossier "Acme Corporation"          # research by name, no domain needed
npx company-dossier acme.com --sections overview,tech,risk --json > acme.json

As a library, or as an MCP server for an agent:

import { buildDossier } from 'company-dossier';
const { json, files } = await buildDossier('acme.com');
company-dossier-mcp          # stdio MCP server, tool: build_dossier({ target, sections? })
company-dossier-mcp-http     # same tool over MCP Streamable HTTP on :8787

How it works

One orchestrator in packages/company-dossier/src/core.ts fans out to the collectors in parallel where that is safe, normalises what comes back into a single DossierData object, then renders one markdown file per requested section plus a README.md index and dossier.json. Collectors are independent and failure-tolerant: a source that times out is recorded as failed in the run metadata and the dossier is still produced without it.

Repository layout

packages/company-dossier/   The npm package — CLI, library, MCP (stdio + HTTP), web server
  src/collectors/           dns · rdap · website · wayback · techstack · search
  src/core.ts               Pipeline orchestrator and the nine-section renderer
site/                       Zero-dependency static generator for companydossier.lol
methodology/                The reproducible playbook: pipeline, architecture, tools, case study
integrations/               Claude Agent Skill + ChatGPT GPT / Apps-SDK (MCP) configuration
knowledge/                  Open Knowledge Format base, written for agent consumption
infrastructure/             S3 + CloudFront + ACM router for per-dossier subdomains
reports/                    Dated audit artifacts — security, mobile/accessibility, copy
growth/                     Discoverability and off-site distribution playbooks

Configuration

Nothing is required to build a dossier. These apply only to the hosted surfaces.

| Variable | Required | Default | Purpose | |---|---|---|---| | COMPANY_DOSSIER_MCP_TOKEN | No | unset | Bearer token for the HTTP MCP server; unset means no auth | | COMPANY_DOSSIER_MCP_ALLOWED_ORIGINS | No | unset | CORS allow-list for the HTTP MCP server | | PORT / HOST | No | 8787 / 0.0.0.0 | Listen address for the HTTP MCP and web servers | | COMPANY_DOSSIER_WEB_RATE | No | see src/web.ts | Rate limit for the hosted web generator | | COMPANY_DOSSIER_S3_BUCKET / AWS_REGION | No | companydossier-dossier-sites / us-east-1 | Target for infrastructure/deploy-dossier.mjs |

Development

cd packages/company-dossier && npm install && npm run build   # tsup → dist/
node site/build.mjs                                            # builds the site into docs/

The site deploys to GitHub Pages on any push touching site/ (.github/workflows/pages.yml); the built docs/ output is generated, not committed. Per-dossier subdomains are noindex by policy — see infrastructure/README.md for why. Contributor conventions and a deeper repo map are in AGENTS.md.

License

MIT · by EVERJUST. Built from public information only — a dossier is a starting map, not a verdict. Verify before you act on it.

Related Skills

View on GitHub
GitHub Stars3
CategoryHuman
Updated1d ago
Forks0

Languages

JavaScript

Trust signals

92/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low