agent-output-evaluator
Evaluate plans/tasks/outputs for schema and quality violations.
Source facts
- Repository
- sunpar/agentic_development
- Last source activity
- May 22, 2026 at 15:56
- Detected SKILL.md language
- English
- Stars
- 0
- Forks
- 0
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview- name
- agent-output-evaluator
- description
- Evaluate plans/tasks/outputs for schema and quality violations.
# Agent Output Evaluator
## Trigger
Use for quality audits of generated outputs.
## Inputs
- plan/task files, skill outputs, fixtures.
## Outputs
- Rubric-based score and specific violations.
## Procedure
1. Validate required task fields.
2. Validate wave safety and scope constraints.
3. Detect vague tasks and oversized PR assumptions.
4. Provide fix recommendations.
## Guardrails
- Keep scoring reproducible and artifact-based.
## Success criteria
- Every failure includes exact path + reason.
View on GitHub