Researching
- 38 installs
- 31 repo stars
- Updated August 2, 2026
- desplega-ai/ai-toolbox
Documents a codebase as-is by spawning parallel sub-agents and synthesizing their findings into a research document, without suggesting changes.
About
A Claude Code skill that conducts comprehensive read-only research across a codebase by fanning out parallel sub-agents and synthesizing their findings into a single research document. It is strictly descriptive - it documents what exists and how it works, never suggesting improvements or refactors. A solo developer reaches for it to quickly understand an unfamiliar area of a codebase before planning changes.
- Spawns parallel sub-agents to research a codebase
- Synthesizes findings into a research document
- Describe-only: never critiques or proposes refactors
- Autonomy modes: Autopilot / Critical / Verbose
Researching by the numbers
- 38 all-time installs (skills.sh)
- Ranked #883 of 1,879 Documentation skills by installs in the Skillselion catalog
- Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/desplega-ai/ai-toolbox --skill researchingAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 38 |
|---|---|
| repo stars | ★ 31 |
| Last updated | August 2, 2026 |
| Repository | desplega-ai/ai-toolbox ↗ |
What it does
Documents a codebase as-is by spawning parallel sub-agents and synthesizing their findings into a research document, without suggesting changes.
Who is it for?
Understanding an unfamiliar codebase area before planning work
Skip if: Proposing fixes or refactors
When should I use this skill?
You need to document how a part of the codebase works
What you get
- research document
Related skills
Lark MarkdownInstantly turn any markdown file into clean, formatted Lark/Figma-compatible documents without manual reformatting.488k
Lark DocCreate, read, update, summarize, rewrite and manage Feishu/Lark cloud documents directly from agent workflows.401k16.1kLark WikiCreate, organize, query, and manage documents, spaces, and members inside Lark (Feishu) knowledge bases directly from AI agent workflows.397k16.1k
Domain ModelingBuild and sharpen a project's domain model: pin down domain terminology in a glossary and record architectural decisions as ADRs.318k202k
Opensource Guide CoachGet expert, attribution-safe guidance on launching and sustaining an open-source project.270k71Readme I18nMaintain consistent, updatable language selector blocks across every README variant in a multilingual repository.270k71FAQ
Does it suggest improvements?
No, it is describe-only and never critiques the implementation or proposes refactors.
How does it stay fast on large codebases?
It spawns parallel background sub-agents to research and keeps raw tool output out of the main session.