DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to build company research cards from your own data files with DSH Industry Research

Turn Markdown, text, CSV, TSV, or JSON files in the workspace into company cards with explicit gaps.

  • Research
  • Intermediate
  • 30 minutes
  • From the README
  • Any agent

Who it is forA buy-side or corporate strategy analyst with company filings and notes saved locally who needs consistent company cards.

The problemCompany notes are uneven, and metrics often lack a source or a date.

The outcomeA company card per company, with rejected files listed with reasons and every unestablished item shown as a gap.

What you need first

  • DeepSeek Harness installed, with a profile to add plugins to (README tests against dsh-v0.2.1-alpha.1)
  • Node.js and the dsh command available in the terminal
  • A session workspace where the artifact folder (industry-research) can be written
  • Optional: ctx.web mounted and offline left false, needed for industry_track and web-assisted runs

Steps

  1. dsh plugin --profile demo add dsh-industry-research
  2. Place the company data files (.md, .txt, .csv, .tsv, or .json) in the session workspace; PDF is not parsed in v1
  3. Load the method: 加载 company-research-method 技能
  4. Call company_scan with the company name or a batch of companies and the dataFiles list
  5. Check that every metric carries source and asOf, and review the rejected-file reasons

Prompt for your agent

Using the dsh-industry-research plugin in DeepSeek Harness, call company_scan for the companies <company-list> with the listed data files. Expect company cards and a list of rejected files with reasons. Verify that each metric has source and asOf, and that unsupported items appear as gaps.

Caveat. Cards are research support only and do not give investment advice, and tickers must match the built-in formats unless strictTicker is set to false.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page