agentleFS
Sign inStart free
JkudjoJkudjo/oh-my-cursor/skills/explore/SKILL.md

explore

Skill1 starsChanged 7 months agoMITView on GitHub

Read-only codebase exploration — understand structure, data flow, and conventions before changing anything

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before designing a plan that touches multiple files

    line 14
  2. Distinctive:

    When you need to understand data flow, entry points, or conventions

    line 15

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

explore

Invoke this skill to understand a codebase or subsystem before making changes.

When to use

  • Starting work in an unfamiliar part of the codebase
  • Before designing a plan that touches multiple files
  • When you need to understand data flow, entry points, or conventions

What it does

  1. No code changes — read-only throughout
  2. Maps the relevant subsystem:
    • Entry points and main files
    • Data flow and call graph
    • Key types and interfaces
    • External dependencies
    • Conventions and patterns in use
  3. Produces an Exploration Report:
    ## Exploration: <topic>

### Files
- `path/to/file.ts` — role and responsibility

### Data flow
[description of how data moves]

### Conventions
[naming, patterns, idioms in use]

### Key decisions
[non-obvious design choices]

### Entry points for changes
[where to start if you need to modify this]
  4. Saves report to memory key explore-<topic>

Example

@explore "how the authentication middleware works"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free