ever-works/orgs/deal-sourcing-scan
Claude Code and agent skill by ever-works/orgs
- community
Checking that the SKILL.md file is still in the repository.
Use when building or refreshing a sourcing pipeline against an investment thesis — turns a mandate into explicit criteria, a scored candidate pool, and a defensible shortlist, as internal analysis only.
Install
npx vskill@latest install ever-works/orgs/deal-sourcing-scanSKILL.md
Deal Sourcing Scan
The firm's repeatable procedure for turning a thesis into a pipeline. It exists to disqualify cheaply and shortlist defensibly — never to recommend a transaction to anyone.
Steps
- Fix the mandate. Restate the thesis in one sentence, and pin the hard filters: sector, stage, geography, and check-size range. If any filter is missing, get it from the mandate owner before scanning — an unbounded scan wastes the pool.
- Write the criteria. List the positive signals that mark a company worth a closer look (traction shape, team signal, wedge, timing) and the disqualifiers that end a look early. Disqualifiers first — they save the most time.
- Build the pool. Identify candidate companies that pass the hard filters. For each, capture only the few facts that decide a first look; do not diligence at this stage.
- Score. Rate each candidate against the criteria on a fixed rubric. Keep the scale small (e.g. strong / possible / pass) and force a one-line reason per score.
- Label evidence. For every scored fact, mark it observed, inferred, or unverifiable. A candidate carried on inference alone is flagged as such.
- Shortlist. Promote only candidates that clear the bar on the written criteria, not on pitch polish. Each gets a one-pager and an explicit "why this one."
- Log the passes. Every dropped candidate keeps a one-line reason and a date, so the same ground is not re-walked next cycle.
Quality bar
- Every score traces to the written criteria, not to a gut feel.
- Disqualifiers are applied before deep reading, not after.
- Known, inferred, and unverifiable facts are visibly distinguished on every candidate.
- The shortlist is defensible company-by-company; a reader can see why each made it and why the rest did not.
- Nothing in the output reads as advice to invest; it is a pipeline of candidates for internal review.
Output format
A scored pipeline (candidate, filters passed, score, one-line reason, evidence labels, state) plus a ranked shortlist where each company carries a one-pager and a pursue rationale, and a passed-log with dated reasons.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcompanies/summit-ventures/skills/deal-sourcing-scan/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ever-works/orgs/deal-sourcing-scan)