Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

HypoGeniC Run Planner & Auditor

Plans, audits, and cost-bounds ChicagoHAI HypoGeniC/HypoRefine hypothesis-generation runs entirely locally before any LLM call.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Gives a reproducible install path for hypogenic==0.3.5 with pinned commit and wheel/sdist SHA-256, plus warnings about its heavy dependency set.
  • Separates the official HypoGeniC task YAML from this skill's local run-policy JSON, and validates both with dependency-free scripts.
  • Audits dataset manifests: checksums, schemas, label counts, duplicates, and cross-split leakage; locks train/validation/test/OOD roles.
  • Produces a conservative cost/token upper bound from caps and flags plans as not ready when pricing is missing.
  • Inspects hypothesis banks and result files with aggregate stats only (no raw text), and computes accuracy, coverage, macro-F1, and a confusion matrix without importing any provider SDK.
  • Requires explicit confirmation before any external LLM call, model download, or dataset upload, and includes a provider-retention privacy gate.

Who it's for

  • Researchers running HypoGeniC/HypoRefine on HypoBench or custom labeled text datasets.
  • Teams handling sensitive or unpublished text who must gate data egress to hosted LLMs.
  • Anyone who must document reproducibility: pinned revisions, hashes, preserved splits.

Example uses

  1. "Estimate the worst-case cost of this run config" → bounded token/cost preflight report.
  2. "Audit the pinned deceptive-review dataset" → flags three cross-split duplicate groups before generation.
  3. "Summarize outputs/hypotheses.json" → counts, lengths, hashes, and accuracy summaries with no candidate text printed.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/hypogenic/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/hypogenic folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/hypogenic/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/hypogenic ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and confirm Git is available: git --version.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/hypogenic ~/.claude/skills/
  5. Verify that scripts/, references/, and assets/ came along inside ~/.claude/skills/hypogenic/.
  6. Install Python 3.10+ and uv if you plan to run HypoGeniC itself (the bundled audit scripts need only the standard library).
  7. Restart Claude Code and ask something like "plan a hypogenic run and audit my dataset manifest".
  8. Keep API keys in environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY) only — never in JSON/YAML configs.
View source on GitHub ↗License: MIT