agentleFS
DikDnsDikDns/upi-rpl-laporan-magang/skills/penilaian-penyelia/SKILL.md

penilaian-penyelia

Skill4 starsChanged 6 months agoMITView on GitHub

Generate official Lembar Penilaian Penyelia (supervisor assessment form) DOCX per pedoman v6 — blank for hand-scoring or prefilled with scores

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    If missing → "Jalankan /rpl-magang:init dulu." Stop.

    line 33
  2. Distinctive:

    If an older config lacks that key, the generator uses the bundled pedoman-v6 default automatically — no re-init required (re-run …

    line 36
  3. Very specific:

    If config.json has student_identity, use it as defaults (nama→nama_mahasiswa, nim, mitra→nama_institusi, penyelia→nama_penyelia).

    line 41
  4. Distinctive:

    Ask (batch with AskUserQuestion where sensible):

    line 44
  5. Distinctive:

    Ask: "Form mau dikosongin (penyelia isi nilai tangan) atau langsung diisi nilai?"

    line 55
  6. Very specific:

    Write data JSON to /tmp/penilaian_data_[timestamp].json:

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
<objective> Generate the official "Lembar Penilaian Penyelia" DOCX (pedoman v6 lampiran): identity header, the pedoman's indicator table (Nilai 0–100), Jumlah & Rata-rata, footnotes, and the supervisor signature block. Blank by default (printed on the mitra's letterhead and scored by hand); optionally prefilled with scores the student already holds. Output: Penilaian_Penyelia_[NamaMahasiswa].docx </objective><constants> CONFIG_PATH = ~/.claude/magang-tools/config.json PYTHON = ~/.claude/magang-tools/venv/bin/python GEN_SCRIPT = ~/.claude/magang-tools/scripts/generate_penilaian.py </constants><steps>

Step 1 — Check config

test -f ~/.claude/magang-tools/config.json && echo "ok" || echo "missing"

If missing → "Jalankan /rpl-magang:init dulu." Stop.

The generator reads penilaian_penyelia (indicators, scale, note) from config. If an older config lacks that key, the generator uses the bundled pedoman-v6 default automatically — no re-init required (re-run /rpl-magang:init to refresh).

Step 2 — Collect identity

If config.json has student_identity, use it as defaults (nama→nama_mahasiswa, nim, mitra→nama_institusi, penyelia→nama_penyelia). Confirm, don't re-ask from zero.

Ask (batch with AskUserQuestion where sensible):

  • Nama Penyelia (default from student_identity.penyelia)
  • Nama Institusi Mitra (default from student_identity.mitra)
  • Nama Mahasiswa (default from student_identity.nama)
  • NIM (default from student_identity.nim)
  • Waktu Pelaksanaan (contoh: "Februari 2026 – Juni 2026")
  • Posisi Penyelia (contoh: "Lead Engineer")
  • Tempat & tanggal tanda tangan (contoh: "Bandung, 1 Juni 2026")

Step 3 — Blank or prefilled?

Ask: "Form mau dikosongin (penyelia isi nilai tangan) atau langsung diisi nilai?"

  • Kosong → no nilai (default).
  • Isi → ask the 10 indicator scores (0–100). Show the indicator list from config penilaian_penyelia.indicators so numbering matches. Build a nilai object keyed "1".."10".

Step 4 — Generate DOCX

Write data JSON to /tmp/penilaian_data_[timestamp].json:

{
  "nama_penyelia": "...",
  "nama_institusi": "...",
  "nama_mahasiswa": "...",
  "nim": "...",
  "waktu_pelaksanaan": "...",
  "posisi_penyelia": "...",
  "tempat_tanggal": "...",
  "nilai": {}
}

(nilai empty object = blank form; otherwise keys "1".."10".)

Output path: --output-dir if given, else current dir. Filename Penilaian_Penyelia_[NamaMahasiswa_tanpa_spasi].docx.

Run:

~/.claude/magang-tools/venv/bin/python ~/.claude/magang-tools/scripts/generate_penilaian.py \
    --data /tmp/penilaian_data_[timestamp].json \
    --output "[output_path]"

Parse output JSON → final path (auto-versioned). Cleanup temp file.

Step 5 — Summary

✅ Lembar Penilaian Penyelia berhasil dibuat!
  File : [output_path]
  Mode : [kosong / terisi]

Next steps:
  1. Cetak di atas KOP surat resmi institusi mitra (placeholder [ KOP ... ] dihapus/diganti)
  2. Kalau kosong: penyelia isi nilai tiap indikator (skala 0–100)
  3. Penyelia tanda tangan + tulis posisi + bubuhkan stempel
  Catatan: kalau institusi sudah punya form penilaian sendiri, form ini tidak berlaku.
</steps>

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.