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

logbook

Skill4 starsChanged 6 months agoMITView on GitHub

Generate weekly/biweekly logbook (Catatan Harian & Kehadiran) for MBKM/P3NK — supports single week, batch, and import from existing files

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. PapyGaragos/skills★ 2same name
    2. spleenteo/maestro★ 1same name
    3. stradinov/neb★ 1same name
    4. sethatwood/belay★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 11 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If missing → tell user: "Jalankan /rpl-magang:init dulu sebelum membuat logbook." Stop.

    line 49
  2. Distinctive:

    default → Single week mode (Step 2a)

    line 58
  3. Distinctive:

    Ask (can batch these questions):

    line 62
  4. Distinctive:

    Read the file at the provided path.

    line 71
  5. Distinctive:

    Ask if there's anything to correct or add.

    line 99
  6. Distinctive:

    Ask: "Berapa minggu yang mau dibuat sekaligus?" (e.g.

    line 103
  7. Very specific:

    Read student_identity from config.json.

    line 109
  8. Distinctive:

    If absent or different → ask:

    line 112
  9. Very specific:

    After collecting (or correcting), persist back to config.json under student_identity so laporan / logbook / pks reuse it without re-asking:

    line 118
  10. Distinctive:

    If a day was off (holiday, izin) → include entry with note: "Tidak masuk — [alasan]"

    line 136
  11. Very specific:

    If --output-dir in args → use that

    line 141
  12. Distinctive:

    Default → current working directory

    line 142
  13. Distinctive:

    Write .md draft with this structure:

    line 146
  14. Distinctive:

    Ask: "Mau langsung export ke DOCX sekarang?"

    line 175
  15. Very specific:

    Write to temp file: /tmp/logbook_data_[week].json

    line 179
  16. Very specific:

    If No → tell user how to re-run later: "/rpl-magang:logbook --week [N]"

    line 190

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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 a Catatan Harian & Kehadiran Peserta logbook following the UPI template. Save as .md draft first, then export to .docx. Supports single week, batch weeks, and converting existing free-format notes to the template. </objective><constants> CONFIG_PATH = ~/.claude/magang-tools/config.json PYTHON = ~/.claude/magang-tools/venv/bin/python LOGBOOK_SCRIPT = ~/.claude/magang-tools/scripts/generate_logbook.py LINKS_SCRIPT = ~/.claude/magang-tools/scripts/extract_pdf_links.py </constants><data-format> `generate_logbook.py` menerima dua bentuk JSON (backward-compatible):
  1. Flat (lama): {..., entries:[{tanggal, uraian_aktivitas}]} → satu tabel, satu baris per hari, satu blok tanda tangan di akhir.
  2. Per-pekan: {..., weeks:[{label, periode, entries:[{tanggal, items:[...]}]}]} → satu tabel + satu tanda tangan per pekan, ganti halaman antar pekan.

Catatan render di dalam sel Uraian:

  • items (list) → tiap item jadi bullet point (untuk hari dengan banyak aktivitas). String uraian_aktivitas tetap dipakai bila ada.
  • *teks* → italic (istilah teknis/asing), `teks` → monospace code (perintah/berkas). Nama brand/ID (ClickUp IR-xxxx, dsb) biarkan biasa.

Pilihan bentuk ikut permintaan mahasiswa: bisa "1 baris = 1 hari" atau "1 baris = 1 pekan dengan rentang tanggal + bullet". Tanyakan bila ambigu. </data-format>

<steps>

Step 1 — Check config

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

If missing → tell user: "Jalankan /rpl-magang:init dulu sebelum membuat logbook." Stop.

Load config to get logbook template structure and formatting.

Step 2 — Determine mode

Check $ARGUMENTS:

  • --import /path → Import mode (Step 2b)
  • --batch → Batch mode (Step 2c)
  • default → Single week mode (Step 2a)

Step 2a — Single week mode

Ask (can batch these questions):

  • Nomor minggu (contoh: 1, 2, 3...)
  • Tanggal mulai minggu ini (contoh: 2 Juni 2025)
  • Tanggal selesai minggu ini (contoh: 6 Juni 2025)

Step 2b — Import mode

Tell user: "Gw akan konversi file kamu ke format template UPI."

Read the file at the provided path.

Analyze its content and extract:

  • Tanggal per entry
  • Uraian aktivitas per entry
  • Nama penyelia (if found)

Jika file PDF (mis. export ClickUp/Notion/Docs): teksnya bisa berupa gambar — baca per halaman (Read dengan pages) untuk isi, lalu ekstrak hyperlink yang tersemat:

~/.claude/magang-tools/venv/bin/python ~/.claude/magang-tools/scripts/extract_pdf_links.py \
    --pdf "[path.pdf]"

Enrich (opsional, kalau ada link + tooling): untuk tiap link, ambil detail agar uraian akurat:

  • clickup → ClickUp MCP clickup_get_task (custom id seperti IR-9633) untuk judul/ID/status task atau bug.
  • gitlab → glab mr view <iid> -R <project-path> untuk judul/state Merge Request.
  • google → catat sebagai dokumen pendukung (judul saja).

Gabungkan hasilnya ke uraian (judul MR, ID bug, status) sehingga aktivitas harian deskriptif dan terverifikasi. Lewati enrich bila MCP/glab tak tersedia atau user tak mengizinkan akses.

Show extracted entries to user for review: "Ini yang berhasil gw parse dari file kamu:" Ask if there's anything to correct or add.

Step 2c — Batch mode

Ask: "Berapa minggu yang mau dibuat sekaligus?" (e.g. 4) Then for each week, ask for the date range. Activities will be collected per week in Step 4.

Step 3 — Collect student identity

Read student_identity from config.json. If present, confirm: "Pakai data ini? Nama: [X], NIM: [Y], Mitra: [Z], Penyelia: [W]"

If absent or different → ask:

  • Nama Mahasiswa (lengkap)
  • NIM
  • Nama Mitra (nama lengkap perusahaan/instansi)
  • Nama Penyelia (nama supervisor di perusahaan)

After collecting (or correcting), persist back to config.json under student_identity so laporan / logbook / pks reuse it without re-asking:

{ "student_identity": { "nama": "...", "nim": "...", "mitra": "...", "penyelia": "..." } }

Step 4 — Collect daily activities

For each working day in the week(s), ask for:

  • Tanggal (format: Senin, 2 Juni 2025)
  • Uraian Aktivitas

User can provide activities in any form — informal notes, English, bullet points. Always expand and rewrite as formal Bahasa Indonesia sentences (2–3 kalimat per entry). Example:

Input: "fixing bug payment timeout" Output: "Melakukan identifikasi dan perbaikan bug pada modul payment service yang menyebabkan kegagalan transaksi akibat kondisi timeout. Perbaikan diverifikasi melalui pengujian unit test dan dinyatakan berhasil."

If a day was off (holiday, izin) → include entry with note: "Tidak masuk — [alasan]"

Step 5 — Save .md draft

Determine output directory:

  • If --output-dir in args → use that
  • Default → current working directory

Draft filename: Logbook_[NamaMhs]_Minggu[N].md (spaces → underscore)

Write .md draft with this structure:

# CATATAN HARIAN & KEHADIRAN PESERTA
## KEGIATAN MBKM KEGIATAN PROGRAM MSIB / P3NK (MAGANG MANDIRI) PADA MITRA

**Nama Mahasiswa :** [nama]
**NIM             :** [nim]
**Nama Mitra      :** [mitra]
**Nama Penyelia   :** [penyelia]

| No. | Tanggal | Uraian Aktivitas | Paraf Penyelia |
|-----|---------|-----------------|----------------|
| 1   | [tanggal] | [aktivitas] | |
| 2   | ...     | ...             | |

---

Peserta,                              Penyelia,



[Nama Mahasiswa]                      [Nama Penyelia]
NIM: [NIM]

Tell user: "Draft disimpan di [path]. Cek dulu sebelum export ke DOCX."

Step 6 — Export to DOCX

Ask: "Mau langsung export ke DOCX sekarang?"

If Yes:

  1. Build data JSON from collected info
  2. Write to temp file: /tmp/logbook_data_[week].json
  3. Run:
~/.claude/magang-tools/venv/bin/python ~/.claude/magang-tools/scripts/generate_logbook.py \
    --data /tmp/logbook_data_[week].json \
    --output "[output_dir]/Logbook_[NamaMhs]_Minggu[N].docx"
  1. Parse output JSON → get final path (auto-versioned if file existed)
  2. Tell user: "DOCX berhasil dibuat: [path]"
  3. Cleanup temp file.

If No → tell user how to re-run later: "/rpl-magang:logbook --week [N]"

Step 7 — Summary

Show:

✅ Logbook Minggu [N] selesai!
  Draft : [path].md
  DOCX  : [path].docx (atau belum di-export)
  Entries: [N] hari

Next: cetak DOCX, minta tanda tangan penyelia di kolom Paraf, scan jadi PDF.
Nama file final: Logbook_[NamaMhs].pdf
</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.