agentsclimarketplace

Evaluation and quality harness

Skill alainlebret/claude-agents/higher-ed-teaching-agents/skills/evaluation-and-quality-harness

Modular skill and workflow ecosystems for AI coding assistants. Structured, multi-agent pipelines for specialized professional domains.

Install
npx -y skills add alainlebret/claude-agents --skill evaluation-and-quality-harness

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Measures exactitude, quality, and stability of runs produced by the teaching-agent system using programmatic checks, rubric-based grading, and benchmark cases. Use when validating workflows, benchmarking outputs, or comparing runs.

SKILL.md

3.1 KB, as published. Nobody here has run it

Evaluation and Quality Harness

Goal

Systematically verify that a workflow run produced the expected artefacts, that those artefacts meet the quality criteria defined in the shared policies, and that results are stable across multiple runs (no random drift).

When to use

  • After completing a workflow run to certify it before publication or student distribution.
  • When comparing two versions of the same course or exam to measure improvement.
  • When benchmarking correction stability (same submission graded twice should yield the same score).

Inputs

  • run-manifest.json — list of produced artefacts and run metadata
  • quality-report.json — programmatic gate results from check_quality_gate.py
  • language-report.json — language consistency results from check_language_policy.py
  • mission.json — source of truth for expected quality level and constraints
  • rubric.md — used to verify grading reproducibility
  • shared/quality-metrics/quality-metrics.md — the quality dimensions to evaluate

Output contract

FileDescription
benchmark/harness-report.mdHuman-readable report: each quality dimension with a pass/review/fail verdict and evidence
benchmark/benchmark-cases.jsonList of benchmark cases run, inputs used, scores obtained, stability delta
benchmark/stability-delta.jsonIf run twice: score difference per criterion; acceptable delta ≤ 0.5 points

Quality dimensions evaluated

For each dimension, produce a verdict (pass / review / fail) with evidence:

DimensionWhat to check
Specification coverageAre all learning_outcomes from mission.json covered by at least one rubric criterion?
Scientific exactitudeDo technical claims in statement.md and teacher-notes.md match established facts?
Internal coherenceDoes the rubric total match the stated maximum? Do criteria refer to tasks that appear in the statement?
Level adequacyIs the expected cognitive load consistent with the academic level in mission.json?
Workload realismCan a student realistically complete all tasks in the stated duration?
EvaluabilityCan every rubric criterion be applied reproducibly without subjective interpretation?
StabilityRe-running the correction on the same submission yields scores within the acceptable delta.

Rules

  • Never invent evidence. If a dimension cannot be evaluated without executing code, state that explicitly and mark it review.
  • Always cite the specific artefact line or section that supports each verdict.
  • If overall_status is not pass after all checks, emit a prioritised list of fixes.
  • Distinguish programmatic failures (wrong output, missing file) from judgement failures (vague criterion).

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.