agentleFS
DJDeborahDJDeborah/research-mechanics-skills/skills/research-significance/SKILL.md

research-significance

Skill0 starsChanged 46 days agoMITView on GitHub

Develop evidence-bounded research significance for mechanics, metamaterials and robotics: connect a changed scientific or design decision to mechanisms, rival explanations and discriminating tests. Use for contribution framing and hypothesis prioritization.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. t-uda/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the significance contract.

    line 13
  2. Distinctive:

    Write a short significance paragraph plus a table mapping contribution → evidence → limitation → next test.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research significance

Turn an interesting result into a defensible explanation of why it changes a scientific or engineering decision.

  1. Identify the target decision, baseline capability, proposed change, physical mechanism, observable, and intended scope. Ask for missing information only when it changes the decision; otherwise record an assumption.
  2. Read the significance contract. Start from the user's evidence, not an adjective such as novel, programmable or unprecedented. Distinguish a new geometry from a new mechanism, prediction or accessible design space.
  3. Give at least one plausible rival mechanism and one discriminating test with a measurable failure condition. If claiming predictive transfer, identify calibration and holdout groups before fitting.
  4. Fill assets/significance.json in the working project. Keep proposed significance separate from established findings. Run python <skill-dir>/scripts/audit_significance.py <project>/significance.json --out <project>/significance-audit.json.
  5. Write a short significance paragraph plus a table mapping contribution → evidence → limitation → next test. A passing audit checks the contract, not scientific truth or importance. Do not inflate the paragraph to make it pass.

For numerical mechanisms, request the actual physical registration and stability evidence appropriate to the claim. A force drop, zero eigenvalue, lower-energy candidate and realized landing answer different questions. For robots, a simulated controller does not establish hardware feasibility.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.