wiki-qa
Analyzes your local or remote repository to answer questions about code functionality and structure.
Install
mkdir -p .claude/skills/wiki-qa && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1232" && unzip -o skill.zip -d .claude/skills/wiki-qa && rm skill.zipInstalls to .claude/skills/wiki-qa
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Answers questions about a code repository using source file analysis. Use when the user asks a question about how something works, wants to understand a component, or needs help navigating the codebase.Key capabilities
- →Resolves git context to link citations to remote repositories
- →Generates structural maps including component role tables
- →Creates architectural documentation using Mermaid diagrams
- →Indexes codebase by file path and line number
How it works
It performs file discovery and code reading to map query concepts to specific implementation locations, formatting results with persistent citation links.
Inputs & outputs
When to use wiki-qa
- →Understanding how a specific feature is implemented
- →Finding where a component is defined
- →Navigating a large or unfamiliar codebase
- →Asking questions about code logic
About this skill
Wiki Q&A
Answer repository questions grounded entirely in source code evidence.
When to Activate
- User asks a question about the codebase
- User wants to understand a specific file, function, or component
- User asks "how does X work" or "where is Y defined"
Source Repository Resolution (MUST DO FIRST)
Before answering any question, you MUST determine the source repository context:
- Check for git remote: Run
git remote get-url originto detect if a remote exists - Ask the user: "Is this a local-only repository, or do you have a source repository URL (e.g., GitHub, Azure DevOps)?"
- Remote URL provided → store as
REPO_URL, use linked citations:[file:line](REPO_URL/blob/BRANCH/file#Lline) - Local-only → use local citations:
(file_path:line_number)
- Remote URL provided → store as
- Determine default branch: Run
git rev-parse --abbrev-ref HEAD - Do NOT proceed until source repo context is resolved
Procedure
- Resolve source repo context (see above)
- Detect the language of the question; respond in the same language
- Search the codebase for relevant files
- Read those files to gather evidence
- Synthesize an answer with inline linked citations
Response Format
- Use
##headings, code blocks with language tags, tables, bullet lists - Cite sources inline using resolved format:
- Remote:
[src/path/file.ts:42](REPO_URL/blob/BRANCH/src/path/file.ts#L42) - Local:
(src/path/file.ts:42)
- Remote:
- Include a "Key Files" table mapping files to their roles (with linked citations in the "File" column)
- Include at least 1 Mermaid diagram when the answer involves architecture, data flow, or relationships — a diagram makes the answer 10x more useful
- Use tables for any structured data in the answer (component lists, API endpoints, config options, comparisons)
- If information is insufficient, say so and suggest files to examine
Rules
- ONLY use information from actual source files
- NEVER invent, guess, or use external knowledge
- Think step by step before answering
When not to use it
- →On non-repository directories lacking version control
- →When questioning non-code documentation files
Prerequisites
Limitations
- →Limited by the initial accuracy of repository context detection
- →Cannot interpret runtime state, only static code definitions
How it compares
It anchors answers to specific lines of source code, replacing general codebase descriptions with verifiable evidence.
Compared to similar skills
wiki-qa side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| wiki-qa (this skill) | 3 | 3mo | No flags | Intermediate |
| deepwiki-rs | 25 | 9mo | Review | Intermediate |
| python-code-style | 9 | 6mo | Review | Intermediate |
| code-review-excellence | 19 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by microsoft
View all by microsoft →You might also like
deepwiki-rs
sopaco
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.
python-code-style
wshobson
Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.
code-review-excellence
wshobson
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
code-walk-thru
pchalasani
Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.
cookbook-audit
anthropics
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
schema-markup
davila7
When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.