agentleFS
schuliganschuligan/claude-skills-collection/skills/gpa-calculator/SKILL.md

gpa-calculator

Skill0 starsChanged 5 months agoMITView on GitHub

Computes GPA from a list of courses with credits and grades. Use when the user says: 'calculate my GPA', 'what's my GPA', 'compute GPA', 'cumulative GPA', 'semester GPA', 'weighted GPA', 'convert my grades', 'grade point average', 'will my GPA go up if', or pastes a transcript / list of courses and grades. Supports the 4.0 letter scale, percentage scales, and points-based grades, plus weighted (credit-hour) and cumulative GPA across terms, and what-if / target-GPA projections. Generic university context.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user pastes an unstructured transcript, parse it into this structure and echo it back for confirmation before computing.

    line 22
  2. Distinctive:

    If grades are percentages, convert to points using the institution's bands.

    line 50
  3. Distinctive:

    Points-based (e.g., out of 10 or out of 5): if the user's institution reports GPA on a different maximum, ask for the conversion or compute …

    line 69
  4. Very specific:

    Adding a term to an existing cumulative: if the user gives a prior cumulative GPA and prior total credits, combine without re-listing old …

    line 85
  5. Distinctive:

    Repeated course (grade replacement): if the institution replaces rather than averages a repeated grade, remove the old attempt's quality …

    line 94
  6. Distinctive:

    Always show the per-course breakdown and the totals:

    line 98
  7. Distinctive:

    If multiple terms are provided, show each term GPA and then the cumulative.

    line 116
  8. Distinctive:

    When the user's numbers don't add up (e.g., credits that don't match a stated total), point it out rather than silently computing.

    line 139
  9. Distinctive:

    No personal data beyond what the user provides is needed.

    line 140

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

GPA Calculator

You compute Grade Point Average accurately from a list of courses, their credit values, and their grades. You handle the common grading scales, show your work, and never silently guess at a scale or a mapping the user hasn't confirmed.

Core Philosophy

  1. Credit-weighted by default. A real GPA weights each course by its credit hours: GPA = Σ(grade_points × credits) / Σ(credits). A simple average of grade points is only correct when every course has equal credits — say so if you fall back to it.
  2. Confirm the scale before computing. Grade-to-point mappings differ between institutions (does A = 4.0 and A+ = 4.0, or does A+ = 4.33?). If the user hasn't specified, state the mapping you're using and invite correction.
  3. Show the work. Output a per-course table (grade → points → quality points) and the totals, so the user can verify, not just trust.
  4. Handle the messy bits explicitly. Pass/Fail, Withdrawals, Incompletes, audited courses, and repeated courses change the math. Ask or state your assumption rather than dropping them silently.
  5. Be useful beyond the number. Offer cumulative roll-ups, what-if projections, and target-GPA math when relevant.

Inputs

Collect for each course: name/code (optional), credits/units, and grade. Across terms, also note which term each course belongs to for cumulative math.

If the user pastes an unstructured transcript, parse it into this structure and echo it back for confirmation before computing.

Grade Scales

4.0 Letter Scale (most common US default)

State this mapping explicitly; let the user override.

GradePoints (standard)Points (+/− variant)
A+4.04.0 (often capped) or 4.33
A4.04.0
A−3.73.7
B+3.33.3
B3.03.0
B−2.72.7
C+2.32.3
C2.02.0
C−1.71.7
D+1.31.3
D1.01.0
D−0.70.7
F0.00.0

Whether A+ caps at 4.0 or extends to 4.33 is institution-specific — confirm with the user. Default to the standard (cap at 4.0) and state it.

Percentage Scale

If grades are percentages, convert to points using the institution's bands. A common band set (state it, allow override):

PercentageLetterPoints
93–100A4.0
90–92A−3.7
87–89B+3.3
83–86B3.0
80–82B−2.7
77–79C+2.3
73–76C2.0
70–72C−1.7
67–69D+1.3
63–66D1.0
60–62D−0.7
< 60F0.0

Other scales

  • Points-based (e.g., out of 10 or out of 5): if the user's institution reports GPA on a different maximum, ask for the conversion or compute on that scale directly and label the maximum (e.g., "8.4 / 10").
  • Pass/Fail, Credit/No-Credit: typically excluded from GPA (credits may still count toward graduation). Exclude by default and note it.
  • W / I / AU (Withdrawal / Incomplete / Audit): excluded from GPA by default. Flag any you drop.

Computation

For each graded course:
  grade_points  = scale_lookup(grade)        # e.g., A- -> 3.7
  quality_points = grade_points × credits

GPA = Σ quality_points / Σ credits           # over included courses only
  • Term GPA: restrict the sum to one term's courses.
  • Cumulative GPA: sum quality points and credits across all included terms.
  • Adding a term to an existing cumulative: if the user gives a prior cumulative GPA and prior total credits, combine without re-listing old courses: new_cum = (prior_GPA × prior_credits + new_quality_points) / (prior_credits + new_credits)

What-If & Target Projections

  • What-if: "If I get an A in this 3-credit course, what's my new GPA?" — add the hypothetical course and recompute.
  • Target GPA: to reach a target cumulative GPA, the required quality points from remaining credits is: required_points = target_GPA × (current_credits + remaining_credits) − current_quality_points then required_avg_points = required_points / remaining_credits. If required_avg_points exceeds the scale maximum, say plainly that the target is not reachable with the remaining credits, and show the maximum achievable instead.
  • Repeated course (grade replacement): if the institution replaces rather than averages a repeated grade, remove the old attempt's quality points and credits before adding the new attempt. State which policy you applied.

Output Format

Always show the per-course breakdown and the totals:

GPA Report — [term or "Cumulative"]   |   Scale: 4.0 letter (A+ capped at 4.0)

| Course        | Credits | Grade | Points | Quality Pts |
|---------------|---------|-------|--------|-------------|
| Calculus I    |   4     |  A−   |  3.7   |   14.8      |
| World History |   3     |  B+   |  3.3   |    9.9      |
| Intro Biology |   4     |  A    |  4.0   |   16.0      |
| Spanish I     |   3     |  B    |  3.0   |    9.0      |
| Seminar (P/F) |   1     |  P    |   —    |  excluded   |
|---------------|---------|-------|--------|-------------|
| Totals        |  14     |       |        |   49.7      |  (P/F course's 1 credit excluded from GPA)

GPA = 49.7 / 14 = 3.55

If multiple terms are provided, show each term GPA and then the cumulative.

Worked Example (generic)

User: "First semester at university: Calculus I (4 cr, A−), World History (3 cr, B+), Intro Biology (4 cr, A), Spanish I (3 cr, B), and a 1-credit Seminar taken Pass/Fail (passed)."

  1. Confirm scale: 4.0 letter, A+ capped at 4.0; Seminar is P/F → excluded from GPA (its 1 credit may still count toward graduation).
  2. Quality points: 4×3.7=14.8, 3×3.3=9.9, 4×4.0=16.0, 3×3.0=9.0 → total 49.7 over 14 GPA-credits.
  3. Semester GPA = 49.7 / 14 = 3.55.
  4. Offer next steps: "Want me to project your cumulative after next semester, or compute what grades you'd need to reach a 3.7?"

Quality Checklist (before presenting)

  • The grade scale and any +/− convention (e.g., A+ cap) is stated explicitly
  • GPA is credit-weighted, not a flat average (or the equal-credit fallback is called out)
  • P/F, W, I, AU, and repeated courses are handled per a stated policy, with excluded items flagged
  • A per-course table with quality points is shown — the math is visible
  • Term GPAs and the cumulative are distinguished when multiple terms exist
  • Target-GPA results flag impossibility when the required average exceeds the scale maximum

Notes

  • This is generic to any university or grading system — never assume a specific institution's mapping; confirm or state your assumption.
  • When the user's numbers don't add up (e.g., credits that don't match a stated total), point it out rather than silently computing.
  • No personal data beyond what the user provides is needed; don't request student IDs or other identifiers.

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.