Dev & Engineering ✓ Microsoft · Official codebase-researcharchitectural-analysissource-citationsmermaid-diagramsgititerative-research

Wiki Codebase Researcher

Trace real code paths across files and produce evidence-backed system analysis.

FollowSkills review · FSRS-2.0
Not recommended
52/ 100 5-point scale 2.6 / 5
Trust17 / 25 · 3.4/5

The skill requires repository-context resolution, distinguishes remote and local citations, and insists on tracing real code while separating fact from inference, reducing misattribution and scope drift. It does not address sensitive-data handling, least-privilege permissions, external effects, rollback, or dependency security, so points are deducted.

Reliability7 / 20 · 1.8/5

The workflow, iterative lenses, and research boundaries are clearly specified, and unknowns must be reported explicitly. However, it depends on Git and resolvable repository context without defining diagnostics or recovery for missing Git, unreachable remotes, invalid branches, or failed cross-file tracing; static calibration also caps this dimension at 10.

Adaptability10 / 15 · 3.3/5

Activation scenarios are clear and fit cross-file architecture, data-flow, and pattern research, with an explicit focus on the requested topic. Non-fit cases, input/output contracts, semantic exclusions, Chinese-language support, and mainland-China network fit are not specified, so points are deducted.

Convention8 / 15 · 2.7/5

The SKILL.md has readable activation rules, core invariants, evidence standards, and a five-stage information architecture, with MIT licensing, author metadata, and version 1.0. It lacks installation and dependency notes, output examples, FAQs, known limitations, changelog, and a clear maintenance/update path, so points are deducted.

Effectiveness6 / 15 · 2.0/5

It provides a directly usable framework for deep codebase research, including code paths, evidence, implications, confidence, and open questions. The mandatory five iterations and diagram/table requirements may impose disproportionate cost, and no representative final output is verifiable from the supplied skill; static calibration therefore limits this score to 7 or below.

Verifiability4 / 10 · 2.0/5

The skill specifies file paths, function names, call chains, citations, and fact/inference separation, creating a useful audit model. It contains no key-path tests or third-party execution evidence, and this review is static only, so the score remains within the 5-point static limit.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 9ccaf7c3704a
Before you use it
  • Execution depends on Git repository context and a user response; no concrete fallback is specified for missing Git, unreachable remotes, or branch-resolution failures.
  • The mandatory five-iteration process and per-iteration Mermaid diagram and table may impose unnecessary time and context cost for simple questions.
  • Handling boundaries for secrets, sensitive code, and private repositories are unspecified, as are Chinese-language output requirements and mainland-China network considerations.
See the full review method →

What it does & when to use it

Wiki Researcher is for developers who need to understand a codebase, complex system, or cross-file pattern in depth. It first resolves the source-repository context, then conducts five research iterations covering architecture, data flow, integration, patterns, and synthesis. Its outputs emphasize actual code paths, file citations, Mermaid diagrams, and structured tables. It is designed for deep investigation rather than general code generation or quick answers.

It first checks the Git remote and determines the current branch, then asks whether the repository is local-only or has a source URL. Across five lenses, it traces entry points, call chains, data flow, dependencies, integrations, patterns, risks, and recommendations. It produces Mermaid architecture or flow diagrams, structured tables, file-and-line citations, confidence ratings, open questions, and explicit research boundaries.

  1. A backend engineer needs to explain how a feature operates across multiple files and wants the full call chain traced.
  2. An architect needs evidence-based component boundaries, dependency relationships, and external integration details.
  3. A new project engineer needs a structured understanding of a complex codebase with citations to the implementation.
  4. A technical writer needs source-grounded material for a codebase wiki, architecture page, or onboarding guide.

Pros & cons

Pros
  • Explicitly requires reading real implementations and tracing complete call chains.
  • Five research iterations cover architecture, data flow, dependencies, patterns, and synthesis.
  • Requires file citations, Mermaid diagrams, tables, confidence ratings, and open questions.
  • Available under the MIT license as part of Microsoft's Agent Skills collection.
Limitations
  • Research cannot begin until the source-repository context is resolved.
  • It requires Git, filesystem access, and potentially network access.
  • The supplied SKILL.md provides no test suite, concrete output schema, or implemented failure-recovery mechanism.
  • Research quality depends on the code and citation information that can be accessed.

How to install

Install the collection with npx skills add microsoft/skills. Select the needed skill in the wizard and install it into the chosen agent directory, such as .github/skills/ for GitHub Copilot. The README does not document a standalone command for installing only wiki-researcher.

How to use

After installation, request an in-depth investigation, for example: Analyze how X works across multiple files, trace the actual code path, and include file citations, Mermaid diagrams, and open questions. The source-repository context must be resolved before research begins.

FAQ

Does it cost money to use?
The source states an MIT license but does not document hosted-service pricing or other fees.
Can it research a local-only repository?
Yes. It asks whether the repository is local-only or has a source URL, then uses local path-and-line citations for local repositories.
What happens if there is no Git remote?
You must identify the repository as local-only, after which the skill uses local file paths and line numbers for citations.
Is it suitable for a quick, simple coding question?
Not primarily. Its activation criteria and process target multi-file investigation, architectural analysis, and complex system understanding.

More skills from this repository

All from microsoft/agent-skills

Dev & Engineering ✓ Microsoft · Official

Azure Identity for Python

A practical skill for securing Python Azure applications with Microsoft Entra ID credentials.

Dev & Engineering ✓ Microsoft · Official

Azure Event Hubs Java Skill

Build production-oriented Java event streaming applications on Azure Event Hubs.

Dev & Engineering ✓ Microsoft · Official

Azure Tables for Python

A practical guide to building authenticated Azure Tables applications with Python entity CRUD, queries, and partition-scoped batch operations.

Dev & Engineering ✓ Microsoft · Official

Azure Identity for TypeScript

Configure secure, flexible Microsoft Entra ID authentication for TypeScript Azure applications.

Automation & Ops ✓ Microsoft · Official

Azure Reliability Advisor

Assess and improve reliability for Azure Functions and App Service.

Dev & Engineering ✓ Microsoft · Official

Azure Cloud Architect

Guides coding agents through production-grade Azure architecture design and review using Azure Architecture Center practices.

Dev & Engineering ✓ Microsoft · Official

Azure AI Text Analytics for Python

Guides Python developers through Azure-powered text analysis and NLP workflows.

Automation & Ops ✓ Microsoft · Official

Azure Resource Architecture Visualizer

Analyze Azure resource groups and turn their dependencies into detailed Mermaid architecture diagrams.

Dev & Engineering ✓ Microsoft · Official

Azure Maps for .NET

Build .NET location features for search, routing, maps, geolocation, and weather.

Dev & Engineering ✓ Microsoft · Official

Azure AI Vision Image Analysis

Guides Python coding agents in implementing Azure AI Vision image understanding.

Dev & Engineering ✓ Microsoft · Official

Azure Blob Storage for Python

Guides secure, production-minded Blob Storage operations in Python.

Dev & Engineering ✓ Microsoft · Official

Azure Queue Storage for Python

Gives coding agents reliable Python patterns for secure Azure Queue Storage messaging and asynchronous task processing.

Automation & Ops ✓ Microsoft · Official

Azure AI Gateway Governance

Use Azure API Management to govern traffic across AI models, MCP tools, and agents.

Automation & Ops ✓ Microsoft · Official

AKS Automatic Readiness

Assess Kubernetes workloads for AKS Automatic compatibility and identify migration blockers before you switch.

Dev & Engineering ✓ Microsoft · Official

Azure Cosmos DB ARM for .NET

Provision and manage Azure Cosmos DB resources from .NET through ARM.

Dev & Engineering ✓ Microsoft · Official

Azure Playwright Workspace Manager

Provision and manage Microsoft Playwright Testing workspaces with .NET and Azure Resource Manager.

Dev & Engineering ✓ Microsoft · Official

Azure Cosmos DB for Python

A practical guide for building reliable Python applications on Azure Cosmos DB’s NoSQL API.

Dev & Engineering ✓ Microsoft · Official

Azure Key Vault SDK for Python

Gives Python coding agents practical guidance for securely managing Azure Key Vault secrets, keys, and certificates.

Dev & Engineering ✓ Microsoft · Official

Azure API Management for Python

Gives coding agents practical Python SDK patterns for managing Azure API Management services, APIs, products, subscriptions, and policies.

Dev & Engineering ✓ Microsoft · Official

Azure Monitor Query for Python

Generate Python code for querying Azure Monitor logs and metrics.

Related skills