Skip to content
Skills Library
AI & agents · Analysis

utility

/utility

Scores agent actions by expected gain, cost, uncertainty, and redundancy. Use when deciding whether to dispatch an agent or invoke a tool.

Licence
MIT
Last repository change
01.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
8
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 01.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Scores agent actions by expected gain, cost, uncertainty, and redundancy. Use when deciding whether to dispatch an agent or invoke a tool.

Original author description

Scores agent actions by expected gain, cost, uncertainty, and redundancy. Use when deciding whether to dispatch an agent or invoke a tool.

How it works

  1. Overview
  2. When To Use
  3. When NOT to Use
  4. Action Space
  5. Utility Function
  6. Termination Conditions
  7. Quick Start
  8. Detailed Resources
  9. Exit Criteria
Original SKILL.md headings · 111 lines, 567 words
SKILL.md preview
---
name: utility
description: Scores agent actions by expected gain, cost, uncertainty, and redundancy. Use when deciding whether to dispatch an agent or invoke a tool.
alwaysApply: false
category: infrastructure
tags:
- orchestration
- cost-control
- decision-making
- agent-dispatch
dependencies: []
provides:
  infrastructure:
  - utility-scoring
  - action-selection
  - termination-control
  patterns:
  - gain-estimation
  - cost-computation
  - redundancy-detection
usage_patterns:
- agent-dispatch-gating
- tool-call-decisions
- continuation-decisions
- model-tier-selection
complexity: intermediate
model_hint: standard
estimated_tokens: 600
progressive_loading: true
modules:
- modules/state-builder.md
- modules/gain.md
- modules/step-cost.md
- modules/uncertainty.md
- modules/redundancy.md
- modules/action-selector.md
- modules/integration.md
---
# Utility Skill

## Overview

A decision framework for agent orchestration based on Liu et al.,
"Utility-Guided Agent Orchestration for Efficient LLM Tool Use"
(arXiv:2603.19896).
Each candidate action is scored by subtracting weighted costs from
expected gain, producing a single utility value that guides action
selection.
The framework prevents over-calling tools and premature stopping by
making both errors costly.
Utility range is [-2.3, 1.0].

## When To Use

- Deciding whether to dispatch another agent or tool call
- Gating expensive tool calls (search, code execution, delegation)
- Selecting the right model tier for a sub-task
- Continuation decisions after receiving partial results
- Verification gating before writing or committing output

## When NOT to Use

- Single-step operations with one obvious action
- Trivial tasks where cost of scoring exceeds benefit
- Already-committed actions that cannot be undone

## Action Space

`A = {respond, retrieve, tool_call, verify, delegate, stop}`

| Action | Description |
|-----------|------------------------------------------------------|
| respond | Emit a final answer from current context |
| retrieve | Fetch additional information (search, read, lookup) |
| tool_call | Execute a tool (code runner, API, file write) |
| verify | Check a prior result for correctness or completeness |
| delegate | Spawn a sub-agent or hand off to a specialist |
| stop | Terminate the loop and return current state |

## Utility Function

```
U(a | s_t) = Gain(a | s_t)
           - λ₁ · StepCost(a | s_t)
           - λ₂ · Uncertainty(a | s_t)
           - λ₃ · Redundancy(a | s_t)
```

| Parameter | Default | Rationale |
|-----------|---------|---------------------------------------------------|
| λ₁ | 1.0 | Cost baseline; all other weights relative to this |
| λ₂ | 0.5 | Weak empirical correlation with outcome (r=0.0131) |
| λ₃ | 0.8 | Redundancy pruning yields ~10% token savings |

Utility range: **[-2.3, 1.0]**.
Positive values indicate the action is worth taking.
Values below the floor (-0.5 default) indicate the action should
be skipped.

## Termination Conditions

Stop the loop when **any** of the following is true:

- (a) Selected action is `stop`
- (b) Step budget exhausted (default: 10 steps)
- (c) All non-`stop` actions score below the floor (default: -0.5)

**High-gain override:** If `Gain >= 0.7` for any action, condition
(c) may be overridden.
Document the override and the gain value in your reasoning trace.

## Quick Start

Minimal 4-step advisory pattern:

1. **Construct state**: gather task context per
   `modules/state-builder.md`
2. **Score candidates**: evaluate each action in `A` per
   `modules/action-selector.md`
3. **Prefer highest utility**: select the action with the
   maximum `U(a | s_t)`, subject to termination conditions
4. **Log score and decision**: record the winning action,
   its utility value, and step count before executing

## Detailed Resources

- **State Builder**: `modules/state-builder.md`, how to
  populate `s_t` from task context
- **Gain**: `modules/gain.md`, estimating expected information
  or progress gain
- **Step Cost**: `modules/step-cost.md`, token, latency, and
  monetary cost tables
- **Uncertainty**: `modules/uncertainty.md`, confidence
  estimation and calibration
- **Redundancy**: `modules/redundancy.md`, detecting duplicate
  or low-delta actions
- **Action Selector**: `modules/action-selector.md`, scoring
  loop and tie-breaking rules
- **Integration**: `modules/integration.md`, wiring utility
  scoring into existing orchestration loops

## Exit Criteria

- [ ] State constructed with task goal and prior steps
- [ ] All six actions scored before selecting one
- [ ] Termination condition checked after each step
- [ ] Score and decision logged for each step taken
- [ ] High-gain overrides documented with gain value
Files in this package (8)
  • SKILL.md 5 KB
  • modules/action-selector.md 3 KB
  • modules/gain.md 2 KB
  • modules/integration.md 4 KB
  • modules/redundancy.md 2 KB
  • modules/state-builder.md 3 KB
  • modules/step-cost.md 2 KB
  • modules/uncertainty.md 2 KB

Versions

The database has no other skills named utility.

Database snapshot: 13.11.2026 · package version 3fd2c0799376 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100skill-review
    Use when reviewing or improving an existing agent skill. Covers triggering accuracy, content quality, redundancy with the base model, and measuring whether the skill actually changes behavior. Trigger on "my skill never triggers", "review this skill", "these two skills overlap",…
  • 100rules-stocktake
    Audit ~/.claude/rules for residency cost, staleness, redundancy and substrate absorption, and give each rule a verdict. Use when the rules may have bloated.
  • 100agent-tool
    Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.ai_framework }}.
  • 100agentic-uncertainty-quantifier
    Scores task uncertainty to calibrate memory depth and iteration count. Use for: quantify uncertainty, fast slow think, uncertainty score, how sure.
  • 96add-tool
    为 OCFT Agent 新增一个工具(数据查询、规则计算、文档检索等)。当需要让 Agent 访问新的数据表、执行新的业务规则或接入新数据源时使用。
  • 100agent-evaluation
    Measures a skill's practical value with fixed business tasks, paired with-skill and without-skill trials, explicit scoring, and honest uncertainty and cost reporting. Use when the user says "does this skill help", "benchmark our agent workflow", "compare this skill to the…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.