Skill explaining-codebases
✓ VerifiedMenghasilkan penjelasan interaktif untuk codebase, termasuk peta arsitektur, diagram data-flow, dan walkthrough kode yang dianotasi.
- Bintang GitHub
- 22
- File
- 4
- Commit terakhir
- 26 Okt 2026
- Lisensi
- MIT
- Tool yang diizinkan
- —
Apa fungsi skill explaining-codebases?
Menghasilkan penjelasan interaktif untuk codebase, termasuk peta arsitektur, diagram data-flow, dan walkthrough kode yang dianotasi.
Ringkasan dibuat dari SKILL.md skill ini.
Tentang skill explaining-codebases
Developer yang perlu melakukan onboarding kontributor baru atau memahami repositori yang kompleks dapat menggunakan skill ini untuk menghasilkan dokumentasi interaktif. Skill ini mengubah file source, service, atau repositori asli menjadi explainer interaktif mandiri yang mencakup peta arsitektur, diagram data-flow, dan walkthrough kode yang dianotasi. Agent harus memuat skill ini saat pengguna meminta untuk memvisualisasikan arsitektur atau menelusuri cara kerja mekanisme tertentu di dalam sebuah codebase.
Prosesnya mengandalkan navigasi kode asli untuk mengidentifikasi entry points, struktur modul, dan konsep spine dari sebuah fitur. Skill ini menghasilkan output high-fidelity seperti execution-trace steppers dan sequence diagrams yang menunjukkan bagaimana item bergerak melalui berbagai tahapan. Untuk memastikan akurasi, skill ini memerlukan proses menjalankan fact-checking-explainers guna memverifikasi bahwa setiap snippet yang dikutip dan klaim fungsional sesuai dengan implementasi pada path dan baris tertentu. Skill ini bekerja secara tandem dengan creating-explainers untuk menangani template HTML akhir, prosa, dan penyempurnaan lainnya.
Apa yang bisa dilakukan agent dengannya
- 1Onboarding anggota tim baruBuat ringkasan arsitektur yang menunjukkan bagaimana modul dan abstraksi utama saling terhubung dalam sebuah proyek baru.
- 2Deep-dive ke algoritma spesifikHasilkan execution-trace stepper untuk menelusuri satu algoritma secara mendalam lengkap dengan state dan baris kode yang disorot.
- 3Visualisasi pergerakan dataHasilkan sequence diagram untuk mengilustrasikan bagaimana sebuah request atau pesan bergerak melalui berbagai tahapan sistem.
- 4Verifikasi akurasi dokumentasi kodePastikan semua snippet kode dan klaim fungsional dalam sebuah explainer sesuai dengan implementasi saat ini.
Ditulis dari SKILL.md milik skill tersebut. Setiap use case diverifikasi dengan kutipan darinya.
Cara install skill explaining-codebases
Setiap perintah menyalin folder skill ke direktori skills client. Restart client atau mulai sesi baru untuk memuatnya.Install skill explaining-codebases di Plugin
/plugin marketplace add analyticalmonk/explain-this /plugin install explain-this@explain-this
Install skill explaining-codebases di Claude Code
~/.claude/skills/explaining-codebases/SKILL.md
$ npx degit analyticalmonk/explain-this/skills/explaining-codebases ~/.claude/skills/explaining-codebasesInstall skill explaining-codebases di Claude Code (project)
.claude/skills/explaining-codebases/SKILL.md
$ npx degit analyticalmonk/explain-this/skills/explaining-codebases .claude/skills/explaining-codebasesInstall skill explaining-codebases di Codex
~/.agents/skills/explaining-codebases/SKILL.md
$ npx degit analyticalmonk/explain-this/skills/explaining-codebases ~/.agents/skills/explaining-codebasesInstall skill explaining-codebases di Gemini CLI
~/.gemini/skills/explaining-codebases/SKILL.md
$ npx degit analyticalmonk/explain-this/skills/explaining-codebases ~/.gemini/skills/explaining-codebasesInstall skill explaining-codebases di Claude.ai
npx degit analyticalmonk/explain-this/skills/explaining-codebases explaining-codebases && zip -r explaining-codebases.zip explaining-codebases # claude.ai → Customize → Skills → + → Create skill → Upload a skill → explaining-codebases.zip
Pengecekan otomatis
Berjalan 15 Nov 2026Laporan lengkap →Lolos cek otomatis kami. Ini bukan audit keamanan: baca skripnya sebelum membiarkan agent menjalankannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkauanalyticalmonk/explain-this/skills/explaining-codebases is public and reachablegithub.com/analyticalmonk/explain-this/tree/HEAD/skills/expl ↗Lolos
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit 2026-10-26github.com/analyticalmonk/explain-this/commits ↗Lolos
- Skrip tanpa unduh-lalu-jalankan atau pencurian kredensialNo scripts in the skill folderLolos
- Tidak ada instruksi tersembunyi di SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/analyticalmonk/explain-this/blob/HEAD/skills/expl ↗Lolos
- Tool yang diizinkan otomatis dibatasiNo pre-approved tools; the agent asks before using onegithub.com/analyticalmonk/explain-this/blob/HEAD/skills/expl ↗Lolos
- SKILL.md mengikuti format Agent SkillsValid name and description; says when to use it; 69 linesgithub.com/analyticalmonk/explain-this/blob/HEAD/skills/expl ↗Lolos
SKILL.md
Lihat di GitHubExplaining Codebases
Overview
This skill explains code as it actually exists - a repository, a service, or a set of source files. The output is the same distill-style, single self-contained interactive explainer that creating-explainers produces. What differs is the intake (navigating real code instead of reading a paper) and the figure types (architecture diagrams, data-flow, execution traces, annotated code walkthroughs). It handles both onboarding overviews of a whole codebase and deep-dives on one mechanism.
Required Background
REQUIRED: Use creating-explainers for everything about the output - the HTML template, voice and style, base figure archetypes, color palettes, the outline/scaffold/prose/polish workflow, and the quality checklist. This skill only adds what is specific to code. Do not duplicate that material here.
When to Use
Use when the subject is code:
- Architecture / onboarding overview - how a project is structured: its modules, how data flows between them, the key abstractions, how the pieces fit. For a new contributor who needs the map.
- Single-mechanism deep-dive - how one algorithm, feature, or subsystem works, traced through the real implementation.
The skill picks the angle from the request and confirms it with the user during intake (overview and deep-dive want different figures and different depth).
When NOT to use: a paper, a topic, or any non-code source. Use creating-explainers instead.
Code Intake
See references/code-intake.md. In short: pick the angle, navigate the repository to find entry points and module structure, identify the spine concept (the one path or idea the article tracks), map the architecture, and pull real code snippets anchored to path:line. Quote actual code; never paraphrase code as if quoting it.
Code-Specific Figures
See references/code-figure-archetypes.md for the patterns:
- Architecture / module diagram - modules as boxes, dependencies as arrows
- Data-flow / sequence diagram - an item (request, message, token) moving through stages
- Execution-trace stepper - step through an algorithm with state and the current line highlighted
- Annotated code walkthrough - a code block whose lines reveal annotations as you step or hover
The mechanics (DPR-aware initCanvas, the IIFE pattern, animation loops) come from the base figure-archetypes.md in creating-explainers. The code-figure reference only covers how to apply them to code.
The Fact-Check Gate for Code
REQUIRED before delivery: run fact-checking-explainers. For a codebase explainer the source of truth is the code itself. Every claim about what the code does, and every quoted snippet, is checked against the actual implementation at a specific path and line. Code drifts; a snippet that was accurate yesterday may be wrong today. The interactive explainer is not done until it passes.
Workflow
Same staged workflow as creating-explainers, with code intake in place of the text intakes:
1. Code intake -> navigate, pick angle, find the spine, map architecture, pull real snippets
2. Outline -> propose sections + figure list, get user approval
3. Scaffold -> copy the article template, fill metadata
4. Prose pass -> write all sections with figure placeholders
5. Figures pass -> implement each interactive figure
6. Post-draft fact-check -> verify every claim and snippet against the real code (REQUIRED, blocking)
7. Polish -> run the creating-explainers Quality Checklist to completion
Pause for user approval after the outline. Everything about scaffolding, prose, figures, polish, and the delivery checklist follows creating-explainers.
Common Mistakes
| Mistake | Fix |
|---|---|
| Explaining code that does not exist, or that you imagined | Open the files. Every claim traces to real code at a real path. |
| Snippets drift from the real source | Quote exactly, with path:line. Never tidy code into something the repo does not contain. |
| Architecture diagram does not match the real module structure | Build the diagram from the actual imports and call sites, not a guess. |
| Scope too broad (a whole framework in one article) | Pick one subsystem or one mechanism. Breadth dilutes; depth teaches. |
| Pasting a huge file as a "figure" | Figures illustrate a point the prose just set up. Trim to the lines that matter. |
Berkas dalam skill ini
4Pertanyaan seputar skill explaining-codebases
Bagaimana cara install skill explaining-codebases di Claude Code?
Jalankan npx degit analyticalmonk/explain-this/skills/explaining-codebases ~/.claude/skills/explaining-codebases. Claude Code memuat skill dari ~/.claude/skills (semua proyek) atau .claude/skills (satu proyek) dan menggunakan skill saat deskripsinya cocok dengan tugas.
Client mana saja yang bisa menggunakan skill explaining-codebases?
Client apa pun yang membaca format Agent Skills: Claude Code, Codex, Gemini CLI, dan claude.ai (unggah sebagai ZIP). Script dalam skill hanya berjalan di client yang mengizinkan eksekusi kode.
Bagaimana skill ini memastikan penjelasan kode akurat?
Skill ini mewajibkan langkah fact-checking di mana setiap klaim dan snippet kode diverifikasi terhadap implementasi aktual pada path dan baris tertentu.
Kapan saya sebaiknya tidak menggunakan skill ini?
Jangan gunakan skill ini untuk makalah, topik umum, atau sumber non-kode lainnya; gunakan skill creating-explainers sebagai gantinya.