init
Skill4 starsChanged 6 months agoMITView on GitHub
One-time setup — parse pedoman PDF, review extracted config, and save for use by other rpl-magang skills
147 other projects use a version of this.
Adopted by
Most recently taken up by
- rohaquinlop/dsh-setuptheir own version, first seen Nov 16, 2026
- Luclegay/claude-memory-kittheir own version, first seen Nov 16, 2026
- GoBeromsu/craft-skillstheir own version, first seen Nov 16, 2026
- arxdsilva/ai-loopstheir own version, first seen Nov 16, 2026
- FAHTHIZ/oasistheir own version, first seen Nov 16, 2026
- kele-dev/Claude-Orchestrator-Skilltheir own version, first seen Nov 16, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
gaebalaiSkillcodex-system
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
Also in 3 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions147 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 147
- microsoft/vscode★ 195ksame name
- mcollina/skills★ 2ksame name
- skyllwt/OmegaWiki★ 1.7ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- TokenRollAI/cc-plugin★ 483same name
- pipecat-ai/gradient-bang★ 420same name
- AlexPEClub/ai-coding-starter-kit★ 382same name
- dannysmith/tauri-template★ 317same name
137 more not listed
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.
- laporan-compileSkill
- laporanSkill
- logbookSkill
- penilaian-penyeliaSkill
- pksSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 8 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 134 edited versions we read keep these.
8
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
- Very specific: line 13
Run once to set up rpl-magang.
- Distinctive: line 32
If config exists → show warning: "Config sudah ada dari sebelumnya.
- Very specific: line 37
If $ARGUMENTS contains --pdf, extract path from there.
- Distinctive: line 47
If not found → ask again.
- Distinctive: line 66
Ask the following (can batch into one AskUserQuestion call or multiple):
- Distinctive: line 115
If user provides corrections → apply them to the config dict.
- Distinctive: line 116
If user types 'lanjut' or equivalent → proceed.
- Distinctive: line 120
Ask: "Punya template PKS DOCX sendiri?
- Very specific: line 122
If path provided → validate it exists → set pks_template_path in config.
- Very specific: line 123
If skipped → pks_template_path remains null (use built-in).
- Distinctive: line 127
Ask (boleh skip dengan Enter): "Mau simpan identitas biar nggak ditanya ulang tiap skill?
- Very specific: line 166
Write config to ~/.claude/magang-tools/config.json.
- Distinctive: line 172
Use the Write tool to write the final config JSON.
“Common” is measured: kept by at least 6 in 10 of the 134 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.
Files
<objective>
Run once to set up rpl-magang. Parse the user's pedoman PDF, show the extracted config for review and correction, then save to ~/.claude/magang-tools/config.json. All other rpl-magang skills depend on this config.
</objective><constants>
TOOLS_DIR = ~/.claude/magang-tools
CONFIG_PATH = ~/.claude/magang-tools/config.json
PYTHON = ~/.claude/magang-tools/venv/bin/python
INIT_SCRIPT = ~/.claude/magang-tools/scripts/init_pedoman.py
</constants><steps>Step 1 — Check existing config
Run:
test -f ~/.claude/magang-tools/config.json && echo "exists" || echo "not_found"If config exists → show warning: "Config sudah ada dari sebelumnya. Re-init akan menimpa konfigurasi yang lama." Ask:
- "Lanjut re-init?" → if No, stop.
Step 2 — Collect pedoman PDF path
If $ARGUMENTS contains --pdf, extract path from there.
Otherwise ask:
"Berikan path ke file pedoman PDF kamu (contoh: ~/Downloads/Pedoman_MBKM.pdf):"
Validate the path exists before continuing:
test -f "[PATH]" && echo "ok" || echo "not_found"If not found → ask again.
Step 3 — Parse pedoman PDF
Run:
~/.claude/magang-tools/venv/bin/python ~/.claude/magang-tools/scripts/init_pedoman.py --pdf "[PDF_PATH]"Parse the JSON output.
If exit code 2 (pdf_parse_failed) → go to Step 3b (manual fallback).
If exit code 0 → go to Step 4 (review).
Step 3b — Manual config fallback
Tell user: "PDF tidak bisa dibaca otomatis. Gw akan tanya manual."
Ask the following (can batch into one AskUserQuestion call or multiple):
- Program studi (default: Rekayasa Perangkat Lunak)
- Nama kampus (default: Kampus UPI di Cibiru)
- Font laporan (default: Arial)
- Ukuran font body (default: 11pt)
- Spasi baris (default: 1.5)
- Margin kiri/atas/bawah/kanan dalam cm (default: 4/3/3/3)
- Style kutipan (default: APA)
- Struktur Bab I (sub-sections, comma-separated)
- Struktur Bab II (sub-sections)
- Struktur Bab III (sub-sections)
- Struktur Bab IV (sub-sections)
- Komponen penilaian (comma-separated)
Build config dict from answers. Skip Step 4, go to Step 5.
Step 4 — Show extracted config for review
Display extracted info in a readable format. Example:
📋 Hasil ekstraksi dari pedoman:
FORMATTING:
Font : Arial 11pt
Spasi : 1.5
Margin : 4cm kiri, 3cm atas/bawah/kanan
Kutipan : APA
STRUKTUR LAPORAN:
Bab I : Pendahuluan (1.1 Latar Belakang, 1.2 Manfaat & Tujuan, ...)
Bab II : Profil Institusi Mitra (2.1, 2.2, ...)
Bab III : Pelaksanaan Kegiatan (3.1, 3.2, ...)
Bab IV : Kesimpulan dan Saran (4.1, 4.2)
KOMPONEN PENILAIAN:
1. Aspek kemampuan kompetensi dan ketrampilan
2. Aspek personal dan sosial
3. ...Sanity-check the extracted structure before showing it (safety net on top of the extractor):
- Duplicate section numbers within a bab (e.g. two
3.1) → keep the one matching the bab's real outline, drop the stray. - A section whose chapter digit ≠ its bab (e.g. a
4.1 Substansisitting in Bab IV alongside the real4.1 Kesimpulan) → drop the off-topic one; the real Bab IV is "Kesimpulan dan Saran". - Titles cut mid-word or with stray characters → clean them. Flag anything you fix so the student can confirm: "Gw rapihin [X] karena [alasan] — bener?"
Then ask: "Ada yang perlu dikoreksi? Kalau ada, sebutkan field mana dan nilai yang benar. Kalau sudah oke ketik 'lanjut'."
If user provides corrections → apply them to the config dict. If user types 'lanjut' or equivalent → proceed.
Step 5 — Ask for custom PKS template (optional)
Ask: "Punya template PKS DOCX sendiri? Kalau ada, berikan path-nya. Kalau tidak, skip (Enter)."
If path provided → validate it exists → set pks_template_path in config.
If skipped → pks_template_path remains null (use built-in).
Step 5b — Identitas mahasiswa (opsional)
Ask (boleh skip dengan Enter): "Mau simpan identitas biar nggak ditanya ulang tiap skill? (boleh skip)"
- Nama Mahasiswa (lengkap)
- NIM
- Nama Mitra (perusahaan/instansi)
- Nama Penyelia (supervisor di tempat magang)
Bila diisi, simpan ke config sebagai student_identity:
{ "student_identity": { "nama": "...", "nim": "...", "mitra": "...", "penyelia": "..." } }Skill laporan / logbook / pks membaca ini dan hanya minta konfirmasi,
tidak tanya ulang. Bila skip, student_identity tidak ditulis (skill akan
menanyakannya saat dibutuhkan, lalu menyimpannya balik).
Step 5c — Konfirmasi konvensi penamaan file (opsional)
Tampilkan template nama file default dari config dan tanyakan apakah ada yang mau diubah:
📁 Konvensi penamaan file P3NK (dari panduan):
form_konversi : Form_Mk_Konversi_MBKM_{nama_mhs}.xlsx
loa : LoA_{nama_mhs}.pdf
logbook : Logbook_{nama_mhs}.pdf
laporan : Laporan_MBKM_{nama_mhs}.pdf
transkrip_nilai : Transkrip_Nilai_{nama_mhs}.pdf
pks : PKS_{nama_perusahaan}.pdf
presentasi : presentasi_{nama_mhs}.mp4
sertifikat : Sertifikat_{nama_kegiatan}_{nama_mhs}.pdfTanya: "Ada template nama file yang mau diubah? Kalau sudah sesuai, ketik 'lanjut'."
Jika user ubah salah satu → update key yang relevan di config["file_naming"].
Jika skip/lanjut → biarkan default.
Step 6 — Save config
Write config to ~/.claude/magang-tools/config.json.
mkdir -p ~/.claude/magang-toolsUse the Write tool to write the final config JSON.
Step 8 — Generate per-bab skills
Run:
~/.claude/magang-tools/venv/bin/python \
~/.claude/magang-tools/scripts/generate_bab_skills.py \
--config ~/.claude/magang-tools/config.json \
--output-dir ~/.claude/magang-tools/generated-skillsParse JSON output. If error → show error, continue (skills can be regenerated later).
Sync generated skills to plugin cache:
CACHE=$(ls -d ~/.claude/plugins/cache/rpl-magang/rpl-magang/*/skills 2>/dev/null | sort -V | tail -1)
if [ -n "$CACHE" ]; then
for skill_dir in ~/.claude/magang-tools/generated-skills/laporan-bab-*/; do
dir="${skill_dir%/}"
[ -d "$dir" ] && cp -r "$dir" "$CACHE/"
done
fiShow which skills were generated:
🔧 Skills yang di-generate dari pedoman kamu:
/rpl-magang:laporan-bab-1 — BAB I [title from config]
/rpl-magang:laporan-bab-2 — BAB II [title from config]
/rpl-magang:laporan-bab-3 — BAB III [title from config]
/rpl-magang:laporan-bab-4 — BAB IV [title from config]Step 7 — Confirm
Show:
✅ Setup selesai! Config disimpan di ~/.claude/magang-tools/config.json
Skills siap digunakan:
/rpl-magang:laporan — cover, lembar pengesahan, kata pengantar
/rpl-magang:laporan-compile — compile semua section jadi DOCX
/rpl-magang:logbook — buat logbook mingguan
/rpl-magang:pks — buat PKS
/rpl-magang:penilaian-penyelia — buat lembar penilaian penyelia
⚠️ RESTART CLAUDE CODE untuk mengaktifkan skill bab yang baru di-generate:
/rpl-magang:laporan-bab-1, laporan-bab-2, laporan-bab-3, laporan-bab-4</steps>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
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.

