generic-discovery
Provides a structured checklist to understand project architecture before modifying code.
Install
mkdir -p .claude/skills/generic-discovery && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13673" && unzip -o skill.zip -d .claude/skills/generic-discovery && rm skill.zipInstalls to .claude/skills/generic-discovery
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.
Use before changing code to understand architecture, context, patterns, tests, and risks.Key capabilities
- →Inspect project structure
- →Read relevant documentation
- →Locate involved files and tests
- →Identify public contracts
- →Identify potential risks
How it works
This skill inspects the project structure, reads documentation, and locates files and tests to understand the architecture, context, and potential risks before any code changes.
Inputs & outputs
When to use generic-discovery
- →Understand codebase patterns
- →Identify risks before refactoring
- →Locate test suites for feature changes
About this skill
Generic Discovery
Use antes de qualquer alteração de código.
Objetivo
Entender arquitetura, contexto, padrões e riscos.
Checklist
- Inspecionar estrutura do projeto.
- Ler docs relevantes.
- Localizar arquivos envolvidos.
- Localizar testes.
- Identificar contratos públicos.
- Identificar riscos.
- Não alterar código nesta etapa.
Saída esperada
- Arquivos relevantes
- Padrões encontrados
- Riscos
- Lacunas
When not to use it
- →The task involves altering code
- →The task is not focused on understanding architecture or context
Limitations
- →The skill is used before any code alteration
- →The skill does not alter code during this stage
How it compares
This skill provides a structured checklist for understanding a codebase before making changes, ensuring a thorough architectural and risk assessment, unlike jumping directly into coding.
Compared to similar skills
generic-discovery side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| generic-discovery (this skill) | 0 | 2mo | No flags | Beginner |
| cursor-explorer-mcp | 6 | 8mo | No flags | Intermediate |
| analyzing-projects | 3 | 6mo | Review | Beginner |
| repo-research-analyst | 1 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
cursor-explorer-mcp
sepiabrown
Use for token-expensive operations requiring multi-file analysis - codebase exploration, broad searches, architecture understanding, tracing flows, finding implementations across files. Uses MCP cursor-agent server (company pays) with clean async interface. Do NOT use for single-file analysis, explaining code already in immediate context, or pure reasoning tasks.
analyzing-projects
CloudAI-X
Analyzes codebases to understand structure, tech stack, patterns, and conventions. Use when onboarding to a new project, exploring unfamiliar code, or when asked "how does this work?" or "what's the architecture?"
repo-research-analyst
parcadei
Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
ark-analysis
mckinsey
Analyze the Ark codebase by cloning the repository to a temporary location. Use this skill when the user asks questions about how Ark works, wants to understand Ark's implementation, or needs to examine Ark source code.
octocode-research
bgauryy
This skill should be used when the user asks to "research code", "how does X work", "where is Y defined", "who calls Z", "trace code flow", "find usages", "review a PR", "explore this library", "understand the codebase", or needs deep code exploration. Handles both local codebase analysis (with LSP semantic navigation) and external GitHub/npm research using Octocode tools.
spec
matteocervelli
>