agentleFS
Sign inStart free
EffortlessMetricsEffortlessMetrics/demo-swarm/.claude/skills/explore/SKILL.md

explore

Skill0 starsChanged 9 months agoApache-2.0View on GitHub

Systematically explore a codebase to answer questions or understand structure.

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 7

    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:

    Start with Grep for keyword search

    line 16
  2. Distinctive:

    Follow a specific flow:

    line 22
  3. Distinctive:

    Start at entry point

    line 23
  4. Distinctive:

    Document each layer touched

    line 25
  5. Distinctive:

    Never modify code during exploration

    line 49
  6. Distinctive:

    Use sub-agents (Task tool) for parallel exploration

    line 50
  7. Distinctive:

    Read files before making claims about them

    line 51

“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 Skill

Systematically explore a codebase to answer questions or understand structure.

Exploration Modes

Structure Mode

Map the codebase architecture:

  1. Find entry points (main, index, app) — use Glob for file discovery
  2. Identify major modules/packages
  3. Trace dependency flow
  4. Document key abstractions

Search Mode

Find specific functionality:

  1. Start with Grep for keyword search
  2. Follow imports/references
  3. Map call chains
  4. Identify all touch points

Trace Mode

Follow a specific flow:

  1. Start at entry point
  2. Step through execution path — use Read for content inspection
  3. Document each layer touched
  4. Note data transformations

Output Format

## Question/Goal
<what we're trying to understand>

## Findings
<structured answer>

## Key Files
| File | Purpose | Relevance |
|------|---------|-----------|
| path | what it does | why it matters |

## Architecture Notes
<diagrams, flow descriptions>

## Open Questions
<what's still unclear>

Rules

  • Never modify code during exploration
  • Use sub-agents (Task tool) for parallel exploration
  • Read files before making claims about them
  • Note assumptions explicitly

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