New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Explain Codebase

by atherio-danp in atherio-danp/cde-dotnetcc

Explain how a specific area / file / feature / topic actually works — grounded line-by-line in the real code, with file:line citations.

No licenceAuto-check: notesAI & LLM Engineering

Install Explain Codebase

skills CLI
$ npx skills add atherio-danp/cde-dotnetcc --skill explain-codebase -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install atherio-danp/cde-dotnetcc explain-codebase --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/atherio-danp/cde-dotnetcc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/explain-codebase .claude/skills/explain-codebase && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
explain-codebase
GitHub stars
109
Token cost
~893 tokens
SKILL.md length
366 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
None found

At a glance

Explain how a specific area / file / feature / topic actually works — grounded line-by-line in the real code, with file:line citations.

  • Works in 7 steps: Read the named inputs FULLY first. If… → Locate (cheap, broad). Grep keywords +… → Trace the real execution path,… → …
  • Asked to explain
  • SKILL.md covers Method and Output
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Explain Codebase is an agent skill from atherio-danp/cde-dotnetcc. Explain how a specific area / file / feature / topic actually works — grounded line-by-line in the real code, with file:line citations. Use when asked to explain, trace, or understand a part of the code (e.g. "explain the model router", "how does the agentic pipeline work", "trace what CreateProject does"). Read-only; documentarian, not critic.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Model routing and gateways and Citation management. The repository describes itself as: Claude Code harness for .NET developers.

When your agent uses it

  • Asked to explain
  • Understand a part of the code (e.g

Example prompts

  • “explain the model router”
  • “how does the agentic pipeline work”
  • “trace what CreateProject does”
  • “/explain-codebase”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash, Skill, mcp__serena__initial_instructions, mcp__serena__get_symbols_overview, mcp__serena__find_symbol, mcp__serena__find_referencing_symbols, mcp__serena__find_declaration, mcp__serena__find_implementations, mcp__serena__search_for_pattern, mcp__serena__get_diagnostics_for_file, mcp__serena__list_dir, mcp__serena__find_file

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read the named inputs FULLY first. If the request references files/symbols, Read them completely — no
  2. Locate (cheap, broad). Grep keywords + Glob patterns + Serena find_symbol/search_for_pattern to find
  3. Trace the real execution path, line-by-line. Follow the actual call chain — entry → validation → business
  4. Cite everything as file:line (or file:start-end). Every claim is anchored to code you actually read.
  5. Runtime questions → go up the rungs. For "what does it actually do at runtime / with real data," consult
  6. Docs are leads, not facts. If a doc/rule says X but the code does Y, the code wins — explain the code
  7. Flag gaps honestly. Unresolved symbol, unclear path, dead code → say "unverified" — never fill it with

What it can do on your machine

Read from SKILL.md and the folder at commit c72a3f9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Bash
    • Skill
    • mcp__serena__initial_instructions
    • mcp__serena__get_symbols_overview
    • mcp__serena__find_symbol
    • mcp__serena__find_referencing_symbols
    • mcp__serena__find_declaration

    …and 5 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Explain Codebase loads about 893 tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~893

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Glob, Grep, Bash, Skill, mcp__serena__initial_instructions, mcp__serena__get_symbols_overview,

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 366 words (~893 tokens).

“Explain how a part of the codebase actually works — grounded in the real code, never assumptions. Obey the source-of-truth authority hierarchy in CLAUDE.md (code → SQL → telemetry → docs → AI output; the higher rung wins). You are…”

— opening of SKILL.md by atherio-danp
name
explain-codebase
allowed-tools
Read, Glob, Grep, Bash, Skill, mcp__serena__initial_instructions, mcp__serena__get_symbols_overview, mcp__serena__find_symbol, mcp__serena__find_referencing_symbols, mcp__serena__find_declaration, mcp__serena__find_implementations, mcp__serena__search_for_pattern, mcp__serena__get_diagnostics_for_file, mcp__serena__list_dir, mcp__serena__find_file
argument-hint
<area / file / feature / topic to explain>

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/explain-codebase of atherio-danp/cde-dotnetcc.

Open the folder on GitHubat commit c72a3f9

Compare with similar skills

Explain Codebase next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Explain Codebase compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Explain Codebase this skillatherio-danp/cde-dotnetcc109—~893Automated safety check: NotesNone
Survey Generatorrohitg00/pro-workflow2.9k1 repos~1.6kAutomated safety check: PassNone
Sciverseopendatalab/Sciverse-Agent-Tools119—~3kAutomated safety check: PassCustom licence
RAG Cite Sourceslyonzin/knowledge-rag290—~1.4kAutomated safety check: PassMIT
Research Lookupdavila7/claude-code-templates32k10 repos~5kAutomated safety check: NotesMIT
Citation Systemkangarooking/system-prompt-skills205—~655Automated safety check: PassMIT

Similar skills

  • Survey Generator

    rohitg00/pro-workflow

    Compile a structured literature survey on any AI/ML topic. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub starsUsed in 1 repo~1.6k tokens
    Research & ScienceAuto-check passed

  • Sciverse

    opendatalab/Sciverse-Agent-Tools

    A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original…

    119 GitHub stars~3k tokensUpdated 17 days ago
    AI & LLM EngineeringAuto-check passed

  • RAG Cite Sources

    lyonzin/knowledge-rag

    Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section.

    290 GitHub stars~1.4k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Research Lookup

    davila7/claude-code-templates

    Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter.

    32k GitHub starsUsed in 10 repos~5k tokens
    Research & ScienceAuto-check: notes

  • Citation System

    kangarooking/system-prompt-skills

    当系统提示需要设计引用格式、信息溯源机制、来源标注系统时调用。适用于文档问答、搜索增强生成（RAG）、代码引用、浏览器辅助等需要让用户追溯信息来源的场景。不适用于纯创作类输出（如故事、诗歌），不适用于无需溯源的常识问答，也不适用于注入防御（虽然两者都涉及内容可信度）。

    205 GitHub stars~655 tokensUpdated 5 mo ago
    AI & LLM EngineeringAuto-check passed

  • Interview Cheatsheet

    wanshuiyin/ARIS-in-AI-Offer

    Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab).

    574 GitHub starsUsed in 1 repo~3.4k tokens
    AI & LLM EngineeringAuto-check: notes

More from atherio-danp/cde-dotnetcc

All 13 skills in this repo

  • MCP Csharp

    atherio-danp/cde-dotnetcc

    Create, debug, test, and publish MCP (Model Context Protocol) servers in C using the official ModelContextProtocol SDK — tools/prompts/resources, stdio vs HTTP transport, MapMcp hosting.

    109 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check: notes

  • Microbenchmarking

    atherio-danp/cde-dotnetcc

    Create, run, configure, and interpret BenchmarkDotNet microbenchmarks in the .NET API — measure and compare approaches, runtime configs, or package versions.

    109 GitHub stars~979 tokensUpdated 2 mo ago
    Auto-check: notes

  • Otel Instrumentation

    atherio-danp/cde-dotnetcc

    Add or change OpenTelemetry tracing, metrics, and structured logging in the .NET API (apps/api) — OTLP exporter setup, custom ActivitySource spans, IMeterFactory metrics, log/trace correlation.

    109 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check: notes

  • Dotnet AI Stack

    atherio-danp/cde-dotnetcc

    Choose and wire AI features in the .NET backend — LLM calls, agentic tool-calling/multi-step workflows, RAG/vector search, structured output, streaming.

    109 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check: notes

  • Dotnet Performance Review

    atherio-danp/cde-dotnetcc

    Scan .NET/C code for performance anti-patterns (async, memory/strings, collections/LINQ, regex, serialization, I/O) with tiered severity, reporting findings without editing.

    109 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check: notes

  • Efcore Patterns

    atherio-danp/cde-dotnetcc

    Add or change EF Core (Npgsql/PostgreSQL) persistence in the .NET backend — entities, EF configurations, repositories, queries, migrations.

    109 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check: notes

Categories

Questions about Explain Codebase

What does Explain Codebase do?

Explain how a specific area / file / feature / topic actually works — grounded line-by-line in the real code, with file:line citations. Explain Codebase is an agent skill from atherio-danp/cde-dotnetcc. Explain how a specific area / file / feature / topic actually works — grounded line-by-line in the real code, with file:line citations.

When should I use Explain Codebase?

Explain Codebase fits situations like: asked to explain; understand a part of the code (e.g.

How do I install Explain Codebase in Claude Code?

Run `npx skills add atherio-danp/cde-dotnetcc --skill explain-codebase -a claude-code`. Or copy the skill folder (.claude/skills/explain-codebase in atherio-danp/cde-dotnetcc) into .claude/skills/explain-codebase in your project. Claude Code loads it when a task matches its description.

How do I install Explain Codebase in Codex?

Run `npx skills add atherio-danp/cde-dotnetcc --skill explain-codebase -a codex`. Or copy the skill folder (.claude/skills/explain-codebase in atherio-danp/cde-dotnetcc) into .agents/skills/explain-codebase in your project. Codex loads it when a task matches its description.

Can I use Explain Codebase in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add atherio-danp/cde-dotnetcc --skill explain-codebase -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/explain-codebase, .gemini/skills/explain-codebase, .github/skills/explain-codebase and .opencode/skills/explain-codebase in your project.

What does Explain Codebase need to run?

SKILL.md names no scripts, command-line tools or credentials: Explain Codebase is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash, Skill, mcp__serena__initial_instructions, mcp__serena__get_symbols_overview, mcp__serena__find_symbol, mcp__serena__find_referencing_symbols, mcp__serena__find_declaration, mcp__serena__find_implementations, mcp__serena__search_for_pattern, mcp__serena__get_diagnostics_for_file, mcp__serena__list_dir, mcp__serena__find_file.

Does Explain Codebase access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Explain Codebase safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Explain Codebase use?

No licence was found for Explain Codebase or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Explain Codebase use?

About 893 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Explain Codebase?

Skills that share tags, products or a category with Explain Codebase: Survey Generator (rohitg00/pro-workflow, 2.9k stars), Sciverse (opendatalab/Sciverse-Agent-Tools, 119 stars), RAG Cite Sources (lyonzin/knowledge-rag, 290 stars) and Research Lookup (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Explain Codebase?

atherio-danp (a GitHub user) maintains it in atherio-danp/cde-dotnetcc, which has 109 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on July 26, 2026.

Source: atherio-danp/cde-dotnetcc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.