agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/de-anthropocentric-research-engine/skills/assess-evidence-saturation/SKILL.md

assess-evidence-saturation

Skill505 starsChanged 51 days agoApache-2.0View on GitHub

Estimate marginal information gain of new evidence batches relative to the current corpus and classify continuing/near-saturation/saturated.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Do not compare incomparable batches, count duplicate sources as new information, or treat a low-quality batch as evidence of saturation.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

assess-evidence-saturation

Purpose

Compare the marginal information gain of a new evidence batch with the comparable prior batch and classify acquisition as continuing, near-saturation, or saturated.

Input contract

required: [current_corpus, prior_comparable_batch, novelty_schema]
optional: [topic_schema, quality_weights, stopping_policy]
constraints: [batches must share a declared universe and comparable novelty calculation]

Procedure

  1. Declare the eligible evidence universe, novelty dimensions, and current/prior batch boundaries.
  2. Compute new topic, independent-source, condition, or mechanism coverage for each comparable batch.
  3. Compare marginal information gain and record the evidence supporting the comparison.
  4. Classify continuing, near-saturation, or saturated and state the stopping rationale.

Output contract

produces: [declared_universe, batch_comparison, marginal_gain, saturation_state, stopping_rationale]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]

Quality gates

  • Numerator, denominator, batch increment, source references, direction, and rationale are reproducible.
  • The comparison uses the same novelty schema for both batches.
  • Saturation is not declared from corpus size alone.
  • Saturation describes acquisition only: it states that further retrieval adds little, never that the question the evidence addresses is answered.

Failure and counterexamples

Do not compare incomparable batches, count duplicate sources as new information, or treat a low-quality batch as evidence of saturation.

Provenance map

  • resolved: knowledge-acquisition-saturation-detection

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.

Check your setup, free