Skip to content
Back to skills

Draft Yonsei Attendance Correction

ASecurity

Create an unsent Korean attendance-correction draft and evidence checklist from a user-confirmed discrepancy found on the authorized live attendance page; use a screenshot, pasted record, export, or JSON only when the live page is unavailable or intentionally supplied. Use when the user wants a reviewable request draft while official submission, status changes, attendance check-in, and external communication remain disabled.

  • 8 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 1, 2026
ai-agentspythonbash

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 1, 2026

npx -y skills add mrcha033/yonsei-skills --skill draft-yonsei-attendance-correction --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Draft Yonsei Attendance Correction?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Draft Yonsei Attendance Correction
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mrcha033-draft-yonsei-attendance-correction/badge)](https://www.skillsdirectory.com/skills/mrcha033-draft-yonsei-attendance-correction)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: draft-yonsei-attendance-correction
description: Create an unsent Korean attendance-correction draft and evidence checklist from a user-confirmed discrepancy found on the authorized live attendance page; use a screenshot, pasted record, export, or JSON only when the live page is unavailable or intentionally supplied. Use when the user wants a reviewable request draft while official submission, status changes, attendance check-in, and external communication remain disabled.
---

# Draft Yonsei Attendance Correction

Create one deterministic, unsent correction draft.

## Prepare the input

Accept the disputed record and evidence in ordinary language or as an attached
screen. Convert only the confirmed fields to a private temporary JSON file. Do
not ask the user to write JSON, and do not infer a recipient or requested status
that the user did not state.

## Run

```bash
python3 "$SKILL_DIR/scripts/draft_correction.py" --input correction.json
```

Provide `captured_at` and a `correction` object containing course code, title, class date, recorded status, requested status, reason, and an `evidence` array. `recipient` is optional and is never inferred.

Review the structured fields, message text, evidence checklist, and `ready_for_user_review`. The output always states `draft_only: true` and `submitted: false`.

## Boundaries

- Never accept or execute `submit`, `send`, `apply_change`, or automatic-action flags.
- Never enter an attendance code, attest presence, use location or beacon data, or perform check-in.
- Process only user-supplied attachments, statements, or JSON and reject credential/session fields.
- Do not claim a correction was accepted; the user must review and submit through the official path.

Files in this skill

  • SKILL.md1.7 KB
  • agents/openai.yaml290 B
  • scripts/draft_correction.py9.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.