Habilidades wiki-researcher
🔍

wiki-researcher

Seguro

Conduct Deep Codebase Research with Evidence-Based Analysis

Shallow code reviews lead to misunderstandings and bugs. This skill enforces rigorous, evidence-based investigation of codebases through structured multi-turn analysis.

Suporta: Claude Codex Code(CC)
🥉 73 Bronze
1

Baixar o ZIP da skill

2

Upload no Claude

Vá em Configurações → Capacidades → Skills → Upload skill

3

Ative e comece a usar

Testar

A utilizar "wiki-researcher". How does the caching layer work?

Resultado esperado:

HIGH Confidence: CacheManager (src/cache/manager.ts:15) implements LRU eviction. Cache entries flow through RedisCacheAdapter (src/cache/redis.ts:42) which calls Redis SETEX with TTL. Default TTL is 300s (config.ts:78). Cache miss fallback to DataLoader (src/dataloader/index.ts:12) for batch fetching.

A utilizar "wiki-researcher". What handles payment failures?

Resultado esperado:

MEDIUM Confidence: PaymentService.processPayment (src/services/payments.ts:89) wraps Stripe calls in try-catch. Failures log to Sentry (line 112) and emit PAYMENT_FAILED event (line 115). Event consumers: EmailService sends notification (src/email/handlers.ts:78), webhook dispatcher triggers external callbacks (src/webhook/dispatcher.ts:45). Have not verified retry logic.

Auditoria de Segurança

Seguro
v1 • 2/25/2026

Static analysis flagged 5 high-risk patterns and 1 medium-risk pattern. All findings are false positives caused by markdown syntax misinterpretation (table pipes, list dashes). The skill is a legitimate codebase research tool with no network requests, file writes, or credential access. It provides structured methodology for deep code analysis using standard read-only tools (Glob, Grep, Read).

1
Arquivos analisados
71
Linhas analisadas
3
achados
1
Total de auditorias
Problemas de Risco Médio (1)
False Positive: Markdown Syntax Misinterpreted
Static scanner flagged 'Ruby/shell backtick execution' at line 63. This is a false positive - the line contains '- NEVER repeat findings from prior iterations' with no backtick execution. The scanner incorrectly identified markdown syntax.
Problemas de Baixo Risco (2)
False Positive: Cryptographic Algorithm Detection
Static scanner flagged 'Weak cryptographic algorithm' at lines 3, 37, 49, 70. These are false positives - the lines contain markdown table formatting characters (|) and list markers (-), not cryptographic algorithms.
False Positive: System Reconnaissance
Static scanner flagged 'System reconnaissance' at line 65. This is a false positive - the line contains '- Include Mermaid diagrams...' with no reconnaissance activity.
Auditado por: claude

Pontuação de qualidade

38
Arquitetura
100
Manutenibilidade
87
Conteúdo
50
Comunidade
96
Segurança
91
Conformidade com especificações

O Que Você Pode Construir

Understand Legacy Codebases

New team members rapidly learn complex systems by tracing actual code paths rather than relying on outdated documentation.

Architectural Decision Analysis

Evaluate design patterns, coupling, and technical debt before refactoring or adding new features.

Bug Investigation

Trace data flow and function calls to identify root causes of complex bugs spanning multiple modules.

Tente Estes Prompts

Basic Code Exploration
How does authentication work in this codebase?
Architecture Mapping
Map the data flow from API entry point to database storage for user creation.
Pattern Investigation
What design patterns are used in the payment processing module? Identify trade-offs and risks.
Deep System Analysis
Trace the complete request lifecycle from ingress through middleware, services, and data layers. Include all transformations, error handling, and external integrations.

Melhores Práticas

  • Provide specific topics or questions rather than generic 'analyze everything' requests
  • Use when you need depth rather than quick answers - this skill prioritizes thoroughness over speed
  • Combine with file navigation tools to jump to specific code locations mentioned in findings
  • Request Mermaid diagrams when visualizing complex architectures or data flows

Evitar

  • Avoid using for simple grep searches - use basic file search instead
  • Do not expect runtime behavior analysis - this skill traces static code paths only
  • Avoid asking about files outside the accessible workspace directory
  • Do not use for time-sensitive tasks - the 5-iteration process requires multiple tool calls

Perguntas Frequentes

How is this different from normal code analysis?
This skill enforces rigorous evidence standards. Every claim must cite file paths and line numbers. It uses 5 research iterations and explicitly distinguishes facts from inferences with confidence ratings.
Can it execute code or test functionality?
No. This skill only reads and analyzes source code. It cannot execute code, run tests, or observe runtime behavior.
How long does analysis take?
The skill performs 5 iterative passes over the codebase. Complex topics may require multiple tool calls across dozens of files. Expect thorough analysis to take longer than casual exploration.
What tools does it use?
Only read-only tools: Glob for file discovery, Grep for content search, and Read for file reading. It never writes files or executes commands.
Will it work on any programming language?
Yes. The skill traces code paths and structure, not specific language syntax. It works with any codebase where files can be read as text.
Can it find bugs or security issues?
It can identify suspicious patterns and logic flaws by tracing code paths. However, it is not a replacement for dedicated security scanners or dynamic analysis tools.

Detalhes do Desenvolvedor

Estrutura de arquivos

📄 SKILL.md