Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

Começar

researching-codebase

Estrelas0

Forks0

Atualizado22 de fevereiro de 2026 às 20:55

Investigates codebase before planning. Use before any non-trivial implementation task to gather context in isolation.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

qte77

qte77/RDI-AgentBeats-MAS-GraphJudge

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

name	researching-codebase
description	Investigates codebase before planning. Use before any non-trivial implementation task to gather context in isolation.
argument-hint	["topic-or-question"]
context	fork
agent	Explore
allowed-tools	Read, Grep, Glob

Codebase Research (ACE-FCA)

Query: $ARGUMENTS

Gathers codebase context in isolation before planning. Prevents search artifacts from polluting main context.

Core Principles

Documentation-only - Describe what exists, where, and how it works
No evaluations - Never suggest improvements or critique implementation
Evidence-based - Provide file paths, line numbers, and code references
Isolation - Research runs in fork context; return only distilled findings

When to Use

Before planning non-trivial implementations
When unfamiliar with relevant codebase areas
Before architectural decisions

Workflow

Read mentioned files first - If specific files mentioned, read completely before exploring
Decompose the question - Break query into researchable components
Explore codebase - Investigate architecture, patterns, constraints
Identify scope - Determine relevant areas based on findings
Distill - Return structured summary using output format below

Output Format

Follow ACE-FCA quality equation: Correct + Complete + Minimal noise

---
research_query: "<original question>"
timestamp: "<ISO 8601>"
files_examined: <count>
---

## Key Files

| File | Purpose | Key Lines |
|------|---------|-----------|
| `path/to/file.ext` | Brief purpose | L42-58 |

## Patterns

- **Pattern name**: Description with file reference (`path:line`)

## Constraints

- Constraint with evidence (`path:line`)

Evidence Requirements

Every claim must include:

File path: Exact location (src/auth/login.ts)
Line numbers: Specific lines (L42-58 or L127)
Code reference: Function/class name when relevant

Bad: "Authentication uses JWT tokens" Good: "Authentication uses JWT tokens (src/auth/jwt.ts:L23-45, verifyToken function)"

References

See .claude/rules/context-management.md and .claude/rules/core-principles.md.

Mais deste repositório

mesmo repositório

committing-staged-with-message

qte77/RDI-AgentBeats-MAS-GraphJudge

Generate commit message for staged changes, pause for approval, then commit. Stage files first with `git add`, then run this skill.

2026-02-220

generating-interactive-userstory-md

qte77/RDI-AgentBeats-MAS-GraphJudge

Interactive Q&A to build UserStory.md from user input. Use when the user wants to create a user story document or start the assisted workflow.

2026-02-220

generating-prd-json-from-prd-md

qte77/RDI-AgentBeats-MAS-GraphJudge

Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.

2026-02-220

generating-prd-md-from-userstory-md

qte77/RDI-AgentBeats-MAS-GraphJudge

Transforms UserStory.md into PRD.md by extracting features and converting user stories into functional requirements.

2026-02-220

reviewing-code

qte77/RDI-AgentBeats-MAS-GraphJudge

Provides concise, focused code reviews matching exact task complexity requirements. Use when reviewing code quality, security, or when the user asks for code review.

2026-02-220

testing-python

qte77/RDI-AgentBeats-MAS-GraphJudge

Writes tests following TDD (using pytest and Hypothesis) and BDD best practices. Use when writing unit tests, integration tests, or BDD scenarios.

2026-02-220

Codebase Research (ACE-FCA)

Query: $ARGUMENTS

Gathers codebase context in isolation before planning. Prevents search artifacts from polluting main context.

Core Principles

Documentation-only - Describe what exists, where, and how it works

No evaluations - Never suggest improvements or critique implementation

Evidence-based - Provide file paths, line numbers, and code references

Isolation - Research runs in fork context; return only distilled findings

When to Use

Before planning non-trivial implementations

When unfamiliar with relevant codebase areas

Before architectural decisions

Workflow

Read mentioned files first - If specific files mentioned, read completely before exploring

Decompose the question - Break query into researchable components

Explore codebase - Investigate architecture, patterns, constraints

Identify scope - Determine relevant areas based on findings

Distill - Return structured summary using output format below

Output Format

Follow ACE-FCA quality equation: Correct + Complete + Minimal noise

--- research_query: "<original question>" timestamp: "<ISO 8601>" files_examined: <count> --- ## Key Files | File | Purpose | Key Lines | |------|---------|-----------| | `path/to/file.ext` | Brief purpose | L42-58 | ## Patterns - **Pattern name**: Description with file reference (`path:line`) ## Constraints - Constraint with evidence (`path:line`)

Evidence Requirements

Every claim must include:

File path: Exact location (src/auth/login.ts)

Line numbers: Specific lines (L42-58 or L127)

Code reference: Function/class name when relevant

Bad: "Authentication uses JWT tokens" Good: "Authentication uses JWT tokens (src/auth/jwt.ts:L23-45, verifyToken function)"

References

See .claude/rules/context-management.md and .claude/rules/core-principles.md.