Works with
Packaged from the source skill for Claude, Codex and 4 more.
About this skill
Passive Deal Screener helps a prospective limited partner organize the first review of a private investment offering. Alireza Rezvani's skill examines the deal from the investor's position: what is disclosed, what could reduce distributions, how the sponsor is paid, and what needs independent verification before deeper diligence.
It supports equity syndications, development equity, preferred equity, bridge lending, and private credit. A full screen produces a ten-section report; a focused request can return a fee analysis, benchmark comparison, or questions for the sponsor. It can also contrast two offerings or provide structured JSON.
Use this skill when
- You have an offering summary, sponsor memo, or brief solicitation and need a disciplined list of issues to investigate.
- You want to separate a marketed return from the fees, promote, financing assumptions, and distribution timing behind it.
- You are preparing sponsor questions or comparing the structures of two private deals.
Useful inputs include the asset and deal type, holding period, claimed gross and net returns, fee schedule, waterfall, financing terms, distribution schedule, sponsor commitment, and realized track record. Sparse input can still yield a disclosure-gap report. Unstated terms should remain gaps rather than silently becoming facts.
What it can do
- Route the offering to deal-specific disclosure, fee, and structural checks.
- Separate operating cash flow, exit proceeds, and leverage in the proposed return story, then name assumptions that change the result.
- Inventory fee layers and estimate gross-to-net drag using the supplied calculator, while identifying assumed or unavailable inputs.
- Compare net returns with dated public-comparator snapshots and explain differences in liquidity, duration, and leverage.
- Connect identified concerns to sponsor questions, including the answers or evasions that would require follow-up.
- Assemble a diligence checklist covering documents and third-party verification still needed.
This is preliminary screening, not underwriting, verification of a sponsor, or financial, legal, or tax advice. The fee calculator uses an additive approximation and a single exit distribution for promote calculations; it does not model a complete distribution schedule. Benchmark figures are bundled historical snapshots, not a live market feed or a forecast, and require refresh or an explicit current override when used.
Typical workflows
Provide the offering, classify its structure, and review the return mechanics, fee stack, financing, and missing disclosures. The report distinguishes disclosed facts, inferences, and unsupported assumptions, then turns unresolved points into concrete sponsor questions and verification tasks.
For a narrower review, supply the fee and waterfall terms and request the drag estimate with its limitations. For two offerings, screen each on the same basis and compare lock-up, cash-distribution timing, conditions, and remaining evidence needs. The result supports deciding what to investigate next; it does not instruct the reader to deploy capital.
What is inside the skill
Section headings from the original SKILL.md (about 1,417 words of instructions). Read the full text in the source repository before installing.
- Modes
- Workflow
- Routing — which reference, which slice
- Skepticism contract
- Anti-Patterns
- Proactive triggers (surface unprompted)
- Output Artifacts
- Communication
- Cross-References
Bundled files
evals/evals.jsonexamples/README.mdexamples/equity-syndication/input.mdexamples/equity-syndication/output.mdexamples/hard-money-fund/input.mdexamples/hard-money-fund/output.mdexamples/private-credit-fund/input.mdexamples/private-credit-fund/output.mdreferences/01-asset-class-norms.mdreferences/02-fee-stack-library.mdreferences/03-red-flag-library.mdreferences/04-question-bank.mdreferences/05-benchmark-returns.mdreferences/data/README.mdreferences/data/etf-comparators-snapshot.mdreferences/data/fred-10yr-snapshot.mdreferences/data/ncreif-npi-snapshot.mdreferences/data/preqin-vintage-note.mdscripts/benchmark_comparator.pyscripts/fee_drag_calculator.pyLICENSE
Example prompts
- Screen the attached preferred-equity offering from an LP perspective. Separate disclosed facts from assumptions, identify missing protections, and return prioritized sponsor questions with the evidence needed to resolve them.
- Review this syndication fee schedule and waterfall. Estimate fee drag only from the supplied terms, label the calculator assumptions, and explain which distribution-timing details are still needed for full underwriting.
- Compare these two bridge-fund summaries on lock-up, distribution timing, financing, fee layers, and disclosure quality. Produce a side-by-side diligence checklist without making a capital-allocation recommendation.
How to install Passive Deal Screener
Claude Packaged
- Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
- For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
- For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
- Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
Codex Packaged
- Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
- Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
- Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
- AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
GPT Packaged
- Download the GPT package from the skill page.
- Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
- Upload the bundled reference files as knowledge so the GPT can consult them.
- Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
Gemini Packaged
- Download the Gemini package from the skill page.
- For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
- Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
- Test a matching task and verify the referenced tools and files are available.
Cursor Packaged
- Download the Cursor package from the skill page.
- Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
- Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
- Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
OpenCode Packaged
- Download the OpenCode package from the skill page.
- Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
- Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
- Start OpenCode in the project and test a matching task with the model and permissions you use.
Permissions & security
Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method
Passive Deal Screener FAQ
What does the Passive Deal Screener skill do?
Screen private offerings from the LP perspective: return mechanics, fee drag, missing disclosures, sponsor questions, and next diligence steps.
Which AI agents can use Passive Deal Screener?
Packages for Claude, Codex and 4 more are built from the same source instructions.
How do I install Passive Deal Screener in Claude?
Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
Who made Passive Deal Screener and what is the license?
Passive Deal Screener is published by Alireza Rezvani under the MIT license. The source is https://github.com/alirezarezvani/claude-skills/tree/main/finance/skills/passive-deal-screener. The catalog keeps the original attribution.
What permissions does Passive Deal Screener need?
Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.