agentsclimarketplace

Rubric builder

Skill alainlebret/claude-agents/higher-ed-teaching-agents/skills/rubric-builder

Builds rigorous grading rubrics for courses, TDs, TPs, exams, reports, and projects in higher education or professional training. Use when an instructor needs an explicit, defensible, non-redundant rubric with observable criteria, weighting, penalty rules, and handling of partial submissions.From its SKILL.md

Install
npx -y skills add alainlebret/claude-agents --skill rubric-builder

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.

SKILL.md

1.1 KB, 164 tokens by cl100k_base, as published. Nobody here has run it

Rubric Builder

Goal

Create a grading rubric that is explicit, fair, reproducible, and resistant to subjective drift.

Inputs

Read the mission, the subject, the reference solution if any, and the expected deliverables.

Output requirements

Produce a rubric with:

  • criteria and subcriteria;
  • points per criterion;
  • observable evidence for each criterion;
  • rules for partial credit;
  • non-double-penalty rules;
  • special-case rules;
  • final score calculation.

Rules

  • Prefer atomic criteria to vague holistic ones.
  • Separate functional correctness, build/integration, robustness, and code quality.
  • Do not assign the same failure to multiple penalties.
  • Explicitly define what happens when compilation fails.
  • Explicitly define what happens when files are missing.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most education skills give in 164 tokens

Counted across 169 of the 171 authors here whose files we hold, read 2026-08-07

  • Search for existing resources before creating new onesin 7 of 169, across 3 files
  • Check tool responses for errors before proceedingin 7 of 169, across 3 files
  • Reduce request frequency on rate limit errorsin 7 of 169, across 3 files
  • Confirm connection status is ACTIVE before running workflowsin 7 of 169, across 3 files
  • Execute prerequisite steps first in workflowsin 7 of 169, across 3 files
  • Handle pagination by fetching until exhaustedin 7 of 169, across 3 files
  • Re-authenticate if the connection expiredin 6 of 169, across 2 files
  • Always call RUBE_SEARCH_TOOLS first to get schemasin 6 of 169, across 2 files
  • Pass strictly schema-compliant tool argumentsin 6 of 169, across 2 files
  • Run the skill generator if the shared file is missingin 6 of 169, across 3 files
  • Create the coursein 5 of 169, across 3 files
  • List enrolled studentsin 5 of 169, across 3 files

Said here and by no other author read

  • Read the mission, subject, reference solution, and expected deliverables
  • List criteria and subcriteria
  • Assign points per criterion
  • Define rules for partial credit
  • Define non-double-penalty rules
  • Define special-case rules

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. 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.