Agent skill

Code Search Assistant

Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity.

Apache-2.0Auto-check passedDevelopment

Install Code Search Assistant

skills CLI

$ npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a claude-code

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

GitHub CLI

$ gh skill install ArabelaTso/Skills-4-SE code-search-assistant --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/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/code-search-assistant .claude/skills/code-search-assistant && 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/

Paste into Claude Code

Install the "code-search-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/code-search-assistant into .claude/skills/code-search-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-search-assistant", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/code-search-assistant

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ArabelaTso/Skills-4-SE code-search-assistant --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/code-search-assistant .agents/skills/code-search-assistant && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "code-search-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/code-search-assistant into .agents/skills/code-search-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-search-assistant", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ArabelaTso/Skills-4-SE code-search-assistant --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/code-search-assistant .cursor/skills/code-search-assistant && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "code-search-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/code-search-assistant into .cursor/skills/code-search-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-search-assistant", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/ArabelaTso/Skills-4-SE.git --path skills/code-search-assistant

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ArabelaTso/Skills-4-SE code-search-assistant --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/code-search-assistant .gemini/skills/code-search-assistant && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "code-search-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/code-search-assistant into .gemini/skills/code-search-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-search-assistant", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ArabelaTso/Skills-4-SE code-search-assistant

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/code-search-assistant .github/skills/code-search-assistant && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "code-search-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/code-search-assistant into .github/skills/code-search-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-search-assistant", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ArabelaTso/Skills-4-SE code-search-assistant --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/code-search-assistant .opencode/skills/code-search-assistant && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "code-search-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/code-search-assistant into .opencode/skills/code-search-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-search-assistant", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: code-search-assistant
GitHub stars: 253
Token cost: ~1.9k tokens
SKILL.md length: 595 words
Files: 1
Skills in repo: 151
Repo updated: Aug 21, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity.

Works in 8 steps: Analyze Input Snippet → Define Search Scope → Search by Call Chain Similarity → …
Finding related code
SKILL.md covers Overview, Workflow and Tips
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Search Assistant is an agent skill from ArabelaTso/Skills-4-SE. Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Use when finding related code, locating similar implementations, discovering code dependencies, or identifying code that performs similar operations. Outputs ranked file lists with matching code snippets and relevance scores.

Its SKILL.md is about 1.9k 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 Development, covering Codebase onboarding. The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.

When your agent uses it

Finding related code
Locating similar implementations
Discovering code dependencies
Identifying code that performs similar operations

Example prompts

“/code-search-assistant”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

Analyze Input Snippet
Define Search Scope
Search by Call Chain Similarity
Search by Textual Similarity
Search by Functional Similarity
Rank and Score Results
Format Results
[file_path] (Score: 0.72)

What it can do on your machine

Read from SKILL.md and the folder at commit 4f38503. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript and markdown).
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

Code Search Assistant loads about 1.9k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 595 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~101
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k

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 passed

The automated check found no risky patterns in SKILL.md.

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

The full file from ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 595 words, ~1,860 tokens.

Download SKILL.mdSave it as .claude/skills/code-search-assistant/SKILL.md (or your agent's skills folder).

name: code-search-assistant
description: Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Use when finding related code, locating similar implementations, discovering code dependencies, or identifying code that performs similar operations. Outputs ranked file lists with matching code snippets and relevance scores.

Code Search Assistant

Overview

Search codebases to find code related to a given snippet using multi-dimensional similarity analysis: call chain patterns, textual structure, and functional behavior. Results are ranked and presented with matching code snippets.

Workflow

1. Analyze Input Snippet

Extract key characteristics from the provided code snippet:

Structural elements:

Function/method calls made
Classes/types used
Control flow patterns (loops, conditionals, try-catch)
Data structures (arrays, objects, maps)

Functional elements:

Purpose/intent of the code
Input/output behavior
Side effects (I/O, state changes, API calls)
Domain concepts (authentication, validation, transformation)

Textual elements:

Variable and function names
String literals and constants
Comments and documentation
Code tokens and keywords

2. Define Search Scope

Determine where to search:

Full repository: Search all code files
Specific directories: Focus on relevant modules
File type filter: Limit to specific languages

Use Glob to identify candidate files:

**/*.js, **/*.py, **/*.java, etc.

3. Search by Call Chain Similarity

Find code with similar function call patterns and dependencies.

Search strategy:

Extract function/method calls from input snippet
Use Grep to find files containing those function calls
Read matching files to analyze call sequences
Score based on:
- Number of shared function calls (weight: 40%)
- Order of function calls (weight: 30%)
- Shared imported modules/libraries (weight: 30%)

Example:

javascript

// Input snippet calls: fetch(), JSON.parse(), setState()
// High match: Code that calls fetch() → JSON.parse() → setState()
// Medium match: Code that calls fetch() and setState() in different order
// Low match: Code that only calls fetch()

4. Search by Textual Similarity

Find code with similar structure and token patterns.

Search strategy:

Extract key identifiers from input snippet (function names, variable names)
Use Grep to find files with similar identifiers
Read matching files to compare code structure
Score based on:
- Shared variable/function names (weight: 35%)
- Similar control flow structure (weight: 35%)
- Shared keywords and operators (weight: 30%)

Similarity indicators:

Same loop patterns (for, while, forEach, map)
Similar conditional logic (if-else chains, switch statements)
Matching data structure operations (array methods, object access)
Similar string/number operations

5. Search by Functional Similarity

Find code that performs similar operations or solves similar problems.

Search strategy:

Identify the functional purpose of input snippet
Search for code with similar purpose using semantic patterns
Look for:
- Similar input/output transformations
- Equivalent algorithms (different implementations, same result)
- Parallel business logic
- Alternative approaches to same problem

Functional categories:

Data transformation: Mapping, filtering, reducing, sorting
Validation: Input checking, format validation, constraint enforcement
I/O operations: File reading/writing, API calls, database queries
Authentication/Authorization: Login, permission checks, token handling
Error handling: Try-catch patterns, error recovery, logging

Search patterns:

// For validation code, search for:
- "validate", "check", "verify" in function names
- Conditional checks with error throwing
- Regular expression patterns

// For API calls, search for:
- HTTP client usage (fetch, axios, requests)
- Endpoint URLs or API patterns
- Response handling and error cases

Show full SKILL.md (210 more words)Show less

6. Rank and Score Results

Combine similarity scores to rank results:

Scoring formula:

Total Score = (Call Chain Score × 0.35) +
              (Textual Score × 0.30) +
              (Functional Score × 0.35)

Score ranges:

0.8-1.0: Very high similarity (likely duplicate or variant)
0.6-0.8: High similarity (related implementation)
0.4-0.6: Medium similarity (similar patterns or purpose)
0.2-0.4: Low similarity (some shared elements)
0.0-0.2: Minimal similarity (weak connection)

Ranking adjustments:

Boost files in same directory (+10%)
Boost files with similar names (+5%)
Penalize test files (-10%) unless input is a test
Penalize generated/vendor code (-20%)

7. Format Results

Present results in ranked order with context:

Result format:

markdown

## Search Results for: [Brief snippet description]

### 1. [file_path] (Score: 0.85)

**Similarity breakdown**:
- Call chain: 0.90 (shares fetch, JSON.parse, setState calls)
- Textual: 0.75 (similar variable names and structure)
- Functional: 0.90 (performs same data fetching and state update)

**Matching code** (lines 45-62):
```[language]
[relevant code snippet from the file]

Why it matches: [Brief explanation of similarity]

2. [file_path] (Score: 0.72)

[... repeat format ...]


**Output guidelines**:
- Show top 10 results by default
- Include file path with line numbers
- Show relevant code snippet (10-20 lines)
- Explain why each result matches
- Group results by score tier if many results

## Search Optimization Tips

**For better call chain matching**:
- Include import statements in input snippet
- Provide complete function calls with arguments
- Include chained method calls

**For better textual matching**:
- Use descriptive variable names in input
- Include comments describing intent
- Provide complete code blocks, not fragments

**For better functional matching**:
- Describe what the code does in comments
- Include typical input/output examples
- Show error handling patterns

## Example Usage

**Input snippet**:
```javascript
async function fetchUserData(userId) {
  try {
    const response = await fetch(`/api/users/${userId}`);
    const data = await response.json();
    return data;
  } catch (error) {
    console.error('Failed to fetch user:', error);
    return null;
  }
}

Search process:

Call chain: Search for fetch(), response.json(), console.error()
Textual: Search for async functions with try-catch, similar variable names
Functional: Search for API data fetching patterns, error handling

Expected results:

Other API fetch functions (high similarity)
Data retrieval functions using different libraries (medium similarity)
Functions with similar error handling (low-medium similarity)

Tips

Start with a complete, representative code snippet (10-30 lines)
Include context (imports, surrounding code) for better matching
For large codebases, narrow search scope to relevant directories
Adjust score weights based on what matters most (calls vs. structure vs. purpose)
Review medium-scored results (0.4-0.6) for unexpected but useful matches
Use results to discover alternative implementations or refactoring opportunities

Files

Just SKILL.md in skills/code-search-assistant of ArabelaTso/Skills-4-SE.

Open the folder on GitHubat commit 4f38503

Compare with similar skills

Code Search Assistant 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.

Code Search Assistant compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Code Search Assistant this skillArabelaTso/Skills-4-SE	253	—	~1.9k	Automated safety check: Pass	Apache-2.0	1 mo ago
Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything	85k	1 repos	~1.2k	Automated safety check: Pass	MIT	2 days ago
Understand ExplainEgonex-AI/Understand-Anything	85k	1 repos	~1.3k	Automated safety check: Pass	MIT	2 days ago
Repomix Codebase Exploreryamadashy/repomix	29k	1 repos	~2.7k	Automated safety check: Pass	MIT	4 days ago
Project Onboarding Guide from Knowledge GraphEgonex-AI/Understand-Anything	85k	—	~1.2k	Automated safety check: Pass	MIT	2 days ago
Deepwiki Rssopaco/deepwiki-rs	3.1k	—	~748	Automated safety check: Pass	MIT	23 days ago

Similar skills

Codebase Knowledge Graph Q&A
Egonex-AI/Understand-Anything
Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.
85k GitHub starsUsed in 1 repo~1.2k tokens
DevelopmentAuto-check passed
Understand Explain
Egonex-AI/Understand-Anything
Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.
85k GitHub starsUsed in 1 repo~1.3k tokens
DevelopmentAuto-check passed
Repomix Codebase Explorer
yamadashy/repomix
Packs a local or remote repository into a single AI-friendly file with the Repomix CLI, then reads and searches that output to explain structure, find patterns or report metrics.
29k GitHub starsUsed in 1 repo~2.7k tokens
DevelopmentAuto-check passed
Project Onboarding Guide from Knowledge Graph
Egonex-AI/Understand-Anything
Writes an onboarding guide for new team members from a project's existing knowledge graph, after checking that the graph still matches the current commit.
85k GitHub stars~1.2k tokensUpdated 2 days ago
DevelopmentAuto-check passed
Deepwiki Rs
sopaco/deepwiki-rs
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation.
3.1k GitHub stars~748 tokensUpdated 23 days ago
DevelopmentAuto-check passed
GitDiagram Repository Overview
ahmedkhaleel2004/gitdiagram
Explains the architecture of a public GitHub repository through GitDiagram: how the code is organized, the main components with paths, and a Mermaid diagram.
18k GitHub stars~427 tokensUpdated yesterday
DevelopmentAuto-check passed

Questions about Code Search Assistant

What does Code Search Assistant do?

Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Code Search Assistant is an agent skill from ArabelaTso/Skills-4-SE. Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity.

When should I use Code Search Assistant?

Code Search Assistant fits situations like: finding related code; locating similar implementations; discovering code dependencies; identifying code that performs similar operations.

How do I install Code Search Assistant in Claude Code?

Run `npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a claude-code`. Or copy the skill folder (skills/code-search-assistant in ArabelaTso/Skills-4-SE) into .claude/skills/code-search-assistant in your project. Claude Code loads it when a task matches its description.

How do I install Code Search Assistant in Codex?

Run `npx skills add ArabelaTso/Skills-4-SE --skill code-search-assistant -a codex`. Or copy the skill folder (skills/code-search-assistant in ArabelaTso/Skills-4-SE) into .agents/skills/code-search-assistant in your project. Codex loads it when a task matches its description.

Can I use Code Search Assistant 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 ArabelaTso/Skills-4-SE --skill code-search-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-search-assistant, .gemini/skills/code-search-assistant, .github/skills/code-search-assistant and .opencode/skills/code-search-assistant in your project.

What does Code Search Assistant need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Search Assistant is instructions for the agent only.

Does Code Search Assistant 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 Code Search Assistant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Search Assistant use?

Code Search Assistant is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Search Assistant use?

About 1.9k tokens (SKILL.md is roughly 7.4k 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 Code Search Assistant?

Skills that share tags, products or a category with Code Search Assistant: Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 85k stars), Understand Explain (Egonex-AI/Understand-Anything, 85k stars), Repomix Codebase Explorer (yamadashy/repomix, 29k stars) and Project Onboarding Guide from Knowledge Graph (Egonex-AI/Understand-Anything, 85k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Search Assistant?

ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 151 skills in this directory. The repository was last updated on August 21, 2026.

Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Code Search Assistant

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Code Search Assistant

Overview

Workflow

1. Analyze Input Snippet

2. Define Search Scope

3. Search by Call Chain Similarity

4. Search by Textual Similarity

5. Search by Functional Similarity

6. Rank and Score Results

7. Format Results

2. [file_path] (Score: 0.72)

Tips

Files

Compare with similar skills

Similar skills

More from ArabelaTso/Skills-4-SE

Related

Questions about Code Search Assistant