agentleFS
Sign inStart free
Runtime-3rr0rRuntime-3rr0r/canvas-scanner/skills/grade-calculator/SKILL.md

grade-calculator

Skill2 starsChanged 57 days agoMITView on GitHub

Use when computing grade scenarios or final-needed scores.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Weights: read the grading table from the course COURSE-BRAIN.md (or README) — e.g.

    line 17
  2. Very specific:

    Compute: run skills/grade-calculator/scripts/grade_calc.py with weights/current/target, or do the algebra directly: needed_component = …

    line 19
  3. Distinctive:

    Don't guess weights — read them.

    line 24
  4. Distinctive:

    If the user only gives "an A", confirm the exact letter boundary (A- vs A) before computing.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Config: resolve <PLACEHOLDER> tokens from ~/.hermes/school-config.md (see canvas-course-sync → School config). Never edit SKILL.md with real values.

Grade Calculator

Answer "what do I need on the final/exam to land X?" from real data, never vibes.

When to Use

  • User asks: "what do I need on the final for a B+", "can I still get an A", "how much is X worth"
  • During the weekly sweep, when new grades come in (refresh the scenario then)

Procedure

  1. Weights: read the grading table from the course COURSE-BRAIN.md (or README) — e.g. participation 10 / homework 15 / quizzes 25 / exams 50.
  2. Current scores: pull from the last Canvas sweep (assignments page read) or the user; keep placeholders for ungraded items if unknown.
  3. Compute: run skills/grade-calculator/scripts/grade_calc.py with weights/current/target, or do the algebra directly: needed_component = (target - sum(weight_i * score_i for finished)) / remaining_weight — the remaining weight is the big exam (or a weighted bucket if multiple open items).
  4. Show it as a small table (component, weight, score, contribution) + the one-number answer. If the answer is >100 or <0, say plainly "not reachable" / "already banked" — the math is the point.
  5. Remember the professor's rounding rules if known (e.g. video-quiz ≥50% → 100%) before finalizing.

Pitfalls

  • Don't guess weights — read them. A missing weight silently changes the answer.
  • Scores change mid-semester: the number is only as fresh as the sweep; state the data date.
  • If the user only gives "an A", confirm the exact letter boundary (A- vs A) before computing.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free