agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/aggregate-ranking/SKILL.md

aggregate-ranking

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.

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:

    Every ranked candidate has a traceable value for each required criterion or an explicit unresolved marker.

    line 31

≈ “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

aggregate-ranking

Purpose

Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.

Input contract

required: [candidate_set, criterion_results, aggregation_rule]
optional: [tie_break_rule, missing_value_policy, uncertainty_annotations]
constraints: [criterion directions and scales must be declared; no silent imputation]

Procedure

  1. Align candidate identifiers, criterion directions, units, and validity flags.
  2. Apply the supplied aggregation rule without changing weights or directions.
  3. Propagate missingness and uncertainty; apply the declared tie-break only after aggregation.
  4. Return ordered candidates with component contributions and recommendation status.

Output contract

produces: [ordered_recommendation, aggregate_scores, contribution_table, unresolved_comparisons]
delta_fields: [findings, evidence_updates, decisions, uncertainties]

Quality gates

  • Every ranked candidate has a traceable value for each required criterion or an explicit unresolved marker.
  • Aggregation reproduces the supplied rule and preserves criterion direction.
  • Ties and sensitivity to tie-breaks are reported.

Parameterization

Caller supplies candidate schema, criterion scales/directions, weights or aggregation formula, tie-break rule, and missing/uncertainty policy.

Failure and counterexamples

Reject mixed units without normalization; reject a recommendation when a hard criterion is unresolved.

Provenance map

  • resolved: priority-synthesis
  • resolved: scoring-synthesis

Preserved source criteria ledger

sourcecriterion
priority-synthesisAll scoring dimensions are present for every gap.
priority-synthesisWeight vector sums to 1.0 within +/-0.001.
priority-synthesisPriority list is sorted descending; ties use feasibility sub-score.
priority-synthesisTop N is N=min(3,total gaps) and includes attack-path suggestions.
scoring-synthesisFinal recommendation includes recommended alternative, confidence, key assumptions, and risk warnings.

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