agentleFS
yogsoth-aiyogsoth-ai/convergence/skills/category-sorting/SKILL.md

category-sorting

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

Classify candidates into predefined categories using ELECTRE-Tri, FlowSort, AHPSort, or DRSA methods.

The file

Files
SKILL.md

Category Sorting

Purpose: Classify candidate alternatives into predefined categories (e.g., A/B/C grades, compliant/non-compliant), supporting ELECTRE-Tri, FlowSort, AHPSort, DRSA, and other classification methods.

When to use:

  • User needs to classify alternatives rather than rank them
  • Predefined category boundaries exist (e.g., pass/fail, excellent/good/poor)
  • Need to independently determine category membership for each alternative

Budget

Base SOPTarget±10% Range
criterion-definition5-8 criteria4-9
weight-elicitation-sop1 weight vector1
threshold-setting1 threshold set1
alternative-scoring1 score matrix1
scoring-synthesis1 classification1

State Ledger

strategy: category-sorting
status: pending
categories_defined: false
criteria_defined: false
weights_computed: false
thresholds_set: false
scores_computed: false
classified: false
result: null

Available Tactics

  • scoring-matrix-construction — Build scoring foundation
  • screening-then-scoring — Hybrid workflow: screen first, then classify

Available SOPs

Import (from tactics)

  • criterion-definition
  • weight-elicitation-sop
  • alternative-scoring
  • threshold-setting

Subagent

  • scoring-synthesis

Execution Guidance

  1. Define category definitions and boundary conditions
  2. Invoke criterion-definition to determine classification criteria
  3. Invoke threshold-setting to set category boundaries
  4. Score each alternative independently and determine category membership
  5. Handle borderline cases (pessimistic vs optimistic assignment)

Output Format

## Classification Results

**Method:** [ELECTRE-Tri / FlowSort / AHPSort / DRSA]
**Category Definitions:** [A=Excellent, B=Good, C=Needs Improvement, D=Unqualified]

### Classification Table
| Alternative | Category | Confidence | Boundary Distance |
|-------------|----------|------------|-------------------|

### Borderline Cases
[List alternatives near category boundaries and their sensitivity]

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.