Skip to content

alirezarezvani/claude-skills / finance/skills/passive-deal-screener

passive-deal-screener

Verified

Use when a passive investor shares a private deal (syndication, preferred equity, bridge fund, private credit) to screen as an LP. Stress-tests it, computes fee drag with fee_drag_calculator.py and compares terms with benchmark_comparator.py.

examples/README.md

View on GitHub
# Examples

Three input/output pairs, one per deal type, showing what the skill produces.
Each `output.md` is a validated run from the eval suite (iteration 5, the run
that cleared the PR gate) with the eval-harness header removed — the analysis
itself is unedited.

| Folder | Deal type | Input | Verdict |
|---|---|---|---|
| `equity-syndication/` | Value-add multifamily syndication | Full offering summary | Pursue with conditions (financing-story cluster) |
| `hard-money-fund/` | Senior-secured bridge loan fund | Platform-style listing | Pursue (well-disclosed; no RED fired) |
| `private-credit-fund/` | Diversified BDC-style credit fund | Fund summary | Pursue with conditions (structure clears every screen) |

All three land on **Pursue** or **Pursue with conditions** — not because the
skill is agreeable, but because these are the *sound* deals in the suite. The eval suite
also exercises the Pass and Pass-as-presented paths (packed red flags, sparse
solicitations, aggressive development pro formas); those live in `evals/`, not
here, because the shipping examples are meant to show a full, clean analysis
end-to-end. The verdicts differ in their **conditions** and **biggest swing
factor**, which is where the LP lens does its work.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 323kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 323kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 323kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall