Agent Native

score-soundness

This skill evaluates the mathematical soundness of a theory by examining falsification reports and assigning a numerical score from 0 to 1.

by ImbueOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (imbue-ai)

Agents
Claude Code
License
AGPL-3.0 (copyleft)
Pin
a2ee48cpinned Oct 9, 2026
Context cost
about 450 tokenswhen the skill loads
GitHub stars
36on imbue-ai/catalyst
Scripts
None found

What it does

“Score the mathematical soundness of a given theory based on its existing falsification reports.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill evaluates the mathematical soundness of a theory by examining falsification reports and assigning a numerical score from 0 to 1. It filters out empirical or experimental falsifications to focus only on logical inconsistencies and mathematical errors, then calculates the soundness score based on the severity and centrality of any mathematical flaws found.

When to use it

  • Validating mathematical theories before deployment or use
  • Assessing the logical consistency of formal proofs or algorithms
  • Evaluating theory robustness when multiple review reports exist
  • Determining theory reliability for critical applications

When not to

  • Assessing empirical or experimental validity of theories
  • Scoring theories without documented falsification reviews
  • Evaluating non-mathematical domains or practical implementations

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add imbue-ai/catalyst --skill score-soundness

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install imbue-ai/catalyst score-soundness@a2ee48c34741df5d4549d97b22aa44589d9eaa6a

Installs the commit we checked (a2ee48c).

Copy by hand

Download the folder at a2ee48c and put it in .claude/skills/score-soundness for Claude Code and in .agents/skills/score-soundness for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at a2ee48c

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "score-soundness" by Imbue.

Source, pinned to commit a2ee48c34741df5d4549d97b22aa44589d9eaa6a:
https://github.com/imbue-ai/catalyst/tree/a2ee48c34741df5d4549d97b22aa44589d9eaa6a/src/claude_skills/skills/score-soundness

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/score-soundness/ for Claude Code and .agents/skills/score-soundness/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/imbue/score-soundness

SKILL.md at the pin

---
name: score-soundness
description: "Score the mathematical soundness of a given theory based on its existing falsification reports."
argument-hint: "the theory ID to score (e.g. T_20260414_143100_d4e5f6)"
user-invocable: false
---

This skill explains how to assess and score the mathematical soundness of a given theory based on its existing falsification reports.

## Soundness Score Execution Steps
1. **Understand the Theory**: If you haven't yet, carefully read the `theory.md` file to understand the theory that you are scoring.
2. **Review Falsification Reports**: Read the `review.md` files for each falsification review.
  - IGNORE any *experimental* or *empirical* falsifications! Instead, focus ONLY on *mathematical* falsifications that point out logical inconsistencies or mathematical errors. If a statement is falsified only experimentally, then treat it as valid for the purpose of this scoring exercise.
  - Each `review.md` file will contain a section `## Target Hypothesis` that describes which statement within the theory is being evaluated, and a `## Conclusion` section which summarizes whether or not the statement was indeed falsified. Read these sections first to understand whether any falsifications were found. You should then read the rest of the review as needed, in order to understand whether the falsification was mathematical or empirical in nature (and disregard it if it is only empirical or experimental).
3. **Score Soundness**: Calculate a soundness score between 0 and 1 for the theory based on the falsification reviews. 1 = zero *mathematical* issues were raised in the reviews, 0.75 = some smaller *mathematical* issues were raised in the reviews, but they are not central to the core theory, 0.5 = a severe *mathematical* flaw was raised in a review which falsifies a key claim of the theory, 0 = several severe *mathematical* flaws were raised throughout multiple reviews, invalidating practically all of the theory. Use your judgment to assign intermediate scores in other scenarios.

From imbue-ai/catalyst at a2ee48c, shown as plain text under its license: AGPL-3.0 (copyleft). The license text is in LICENSE.

View SKILL.md on GitHub at a2ee48c

Files

1 file, 2.0 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at a2ee48c
All 50 skills from Imbue

More from Imbue

  • architect

    Generates an architecture document for a feature by reading the existing spec, analyzing the codebase deeply, and conducting guided Q&A with the user to…

    Claude Code · about 4K tokens · pinned 6 days ago

  • build

    This skill executes a multi-step implementation plan by working through task files sequentially.

    Claude Code · about 1.1K tokens · pinned 6 days ago

  • build-sculptor-extension

    Build or modify Sculptor extensions, which are runtime ES modules that add panels, overlays, widgets, home views, or settings UI to the Sculptor frontend.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.3K tokens · pinned 6 days ago

  • fix-bug

    Fixes bugs using test-driven development with an interactive or autonomous workflow.

    Claude Code · about 9.8K tokens · pinned 6 days ago

  • handoff

    This skill hands off ongoing work to a fresh agent, either in the same workspace or a new isolated workspace, while preserving context through a synthesized…

    Claude Code · about 1.1K tokens · pinned 6 days ago

  • help

    This skill fetches the latest Sculptor documentation from GitHub and answers user questions about how to use Sculptor's features, including workspaces…

    Claude Code · about 880 tokens · pinned 6 days ago

All Docs and writing skills

Related in Docs and writing

  • n8n-docs-assistant

    This skill answers questions about n8n configuration, setup, credentials, nodes, and troubleshooting by retrieving information from current n8n documentation.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 450 tokens · pinned 6 days ago

  • algodocs-automation

    This skill automates Algodocs document processing tasks through Composio's toolkit via the Rube MCP server.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

  • remotion-docs

    This skill enables agents to search and retrieve Remotion documentation via the Algolia API and fetch pages as Markdown.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 320 tokens · pinned 6 days ago

  • remotion-docs

    This skill searches the Remotion documentation using the Algolia API and retrieves documentation pages as Markdown.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 320 tokens · pinned 6 days ago

  • receipts

    This skill generates a personal Claude Code usage report from local session transcripts stored in ~/.claude/projects, mining activity across projects without…

    by AnthropicOfficial publisher

    Contains scripts

    Claude Code · about 4.1K tokens · pinned 6 days ago

  • solo

    This skill enables an agent to work through a single difficult mathematics problem independently within one session.

    by AnthropicOfficial publisher

    Claude Code · about 1.4K tokens · pinned 6 days ago

Open roles at Imbue

No open roles at Imbue on the Agent Native jobs board right now.

Browse the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use