eval-guidance-actionability
Original：🇺🇸 English
Translated
Score assistant responses for guidance & actionability on a strict 1-5 scale, then return strict JSON only with dimension, score, rationale, and improvement suggestions. Use when the user asks to evaluate how actionable, helpful, or step-by-step a response is.
2installs
Added on
NPX Install
npx skill4agent add whitespectre/ai-assistant-evals eval-guidance-actionabilityTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →Eval Guidance & Actionability
Use this skill to evaluate whether an assistant response provides clear, usable guidance the user can act on.
Inputs
Require:
- The assistant response text to evaluate.
- (Optional) The user’s request or goal (helps judge whether guidance matches what’s needed).
Internal Rubric (1–5)
5 = Provides concrete, actionable steps; prioritized; includes key details/constraints; user could execute without guessing
4 = Mostly actionable; minor missing details or ordering, but still usable
3 = Some guidance, but generic; missing important steps/details; requires user to infer next actions
2 = Largely non-actionable; mostly high-level advice; lacks steps or specifics
1 = No usable guidance; purely vague, deflective, or irrelevant to “what to do next”
4 = Mostly actionable; minor missing details or ordering, but still usable
3 = Some guidance, but generic; missing important steps/details; requires user to infer next actions
2 = Largely non-actionable; mostly high-level advice; lacks steps or specifics
1 = No usable guidance; purely vague, deflective, or irrelevant to “what to do next”
Workflow
- Check whether the response includes specific next actions (steps, checklist, examples, decision points).
- Check completeness (missing prerequisites, constraints, caveats).
- Score on a 1-5 integer scale using the rubric only.
- Write concise rationale tied directly to rubric criteria.
- Produce actionable suggestions that improve actionability.
Output Contract
Return JSON only. Do not include markdown, backticks, prose, or extra keys.
Use exactly this schema:
{
"dimension": "guidance_actionability",
"score": 1,
"rationale": "...",
"improvement_suggestions": [
"..."
]
}
Hard Rules
- must always equal
dimension."guidance_actionability" - must be an integer from 1 to 5.
score - must be concise (max 3 sentences).
rationale - Do not include step-by-step reasoning.
- must be a non-empty array of concrete edits.
improvement_suggestions - Never output text outside the JSON object.