skill-selection-evals

Eval-only skill for measuring skill routing accuracy. Not invoked directly — contains selection evals that test whether the agent picks the correct skill for a given prompt.

10 stars

Best use case

skill-selection-evals is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Eval-only skill for measuring skill routing accuracy. Not invoked directly — contains selection evals that test whether the agent picks the correct skill for a given prompt.

Teams using skill-selection-evals should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-selection-evals/SKILL.md --create-dirs "https://raw.githubusercontent.com/raddue/crucible/main/skills/skill-selection-evals/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skill-selection-evals/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill-selection-evals Compares

Feature / Agentskill-selection-evalsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Eval-only skill for measuring skill routing accuracy. Not invoked directly — contains selection evals that test whether the agent picks the correct skill for a given prompt.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Skill-Selection Evals

This is not an executable skill. It contains evaluation data for measuring the accuracy of skill selection (routing) decisions.

## Purpose

Crucible's 49 execution evals measure quality once a skill is invoked. Selection evals measure whether the **right skill gets invoked** in the first place.

## Eval Types

- **Direct selection**: Given a prompt, does the agent pick the correct skill?
- **Negative selection**: Given a prompt that sounds like skill X but is not, does the agent avoid the false positive?
- **Context-dependent**: Same verb, different context, different correct skill.
- **Cascade ordering**: Multi-skill tasks requiring correct invocation order.

## Boundaries Tested

1. **test-methodology** — TDD vs test-coverage vs adversarial-tester
2. **review-direction** — temper vs review-feedback
3. **adversarial-scope** — red-team vs inquisitor vs audit vs siege
4. **completion-claims** — verify vs finish
5. **bug-handling** — debugging vs verify vs audit

## Difficulty Ratings

Each eval is rated easy/medium/hard based on routing ambiguity. This enables stratified baseline measurement — distinguishing between improvements that lift hard cases (high value) vs confirming easy cases already work (low signal).

## See Also

- `evals/evals.json` — the eval data
- `GRADING.md` — grading criteria and baseline measurement protocol

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.