skills.rest
pandejesal
pandejesalCOMMUNITY
Explore all skills by this author →
GitHub

discover

Maps repository structure, API surfaces, and governance rules into context files.

Updated Sep 14, 2026
Search Tags:#static analysis#multi-agent#code exploration#repository discovery#context mapping#api surface#governance rules
One-click install
npx skills add https://github.com/pandejesal/drone-nav-sar --skill discover-pandejesal
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: discover
Source: https://github.com/pandejesal/drone-nav-sar/tree/main/.swarm/bundled-skills/discover
Command: npx skills add https://github.com/pandejesal/drone-nav-sar --skill discover-pandejesal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Before modifying a codebase, an AI agent needs a reliable map of the repository: its public APIs, complexity hotspots, and project governance rules. This Skill provides the read-only DISCOVER protocol that gathers that context systematically instead of relying on ad-hoc exploration. ## Core Features & Use Cases - Explorer Delegation: Delegates repository discovery to the swarm's explorer agent, with an optional second pass focused on hidden requirements, unstated assumptions, and scope risks. - API Surface Analysis: Runs symbols and batch_symbols tools on key files to understand public API surfaces, plus complexity_hotspots to flag modules needing security review or full gates. - Governance Extraction: Locates governance files (AGENTS.md, CONTRIBUTING.md, CLAUDE.md, project-instructions.md, INSTRUCTIONS.md), extracts MUST and SHOULD rules with provenance, precedence, and conflict flags, and writes them to .swarm/context.md. - Use Case: When starting work on an unfamiliar multi-module repository, run the DISCOVER mode to produce a context.md file capturing API surfaces, risk hotspots, and binding project rules before any code changes are planned. ## Quick Start Activate DISCOVER mode to explore this repository and record its governance rules and API surfaces in .swarm/context.md.

Frequently Asked Questions about discover

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I map a repository's structure before making code changes?▼

Use a read-only discovery protocol that delegates exploration to an explorer agent, then runs symbol analysis on key files to understand public API surfaces. The results are recorded in a context file for downstream planning steps.

How to extract coding rules from AGENTS.md and CONTRIBUTING.md files?▼

Scan the repository with glob patterns for governance files like AGENTS.md, CONTRIBUTING.md, and CLAUDE.md, then extract MUST and SHOULD rules. Each rule is recorded with its source file, scope, precedence, strength, and any conflicts with other files.

What happens when two governance files have conflicting rules?▼

Conflicting rules are never flattened into one. Each rule keeps a conflict flag naming the contradicting file, and precedence is applied: AGENTS.md and project-instructions.md outrank CONTRIBUTING.md, INSTRUCTIONS.md, and CLAUDE.md.

Does repository discovery modify any project files?▼

No, the discovery protocol is read-only with respect to the repository. Its only write operation is appending extracted governance rules to the .swarm/context.md file under a Project Governance section.

When should complexity hotspot analysis run during discovery?▼

Run complexity_hotspots if it was not already executed during project discovery, checking context.md for existing analysis first. Modules flagged with security_review or full_gates recommendations are noted in context.md for later phases.

Related Skills

Explore More Software Engineering Skills→
autopus-aiautopus-ai
111

auto-map

Analyzes codebase structure, entry points, and dependencies to produce a summary.

Official
Basic
ZaxbyHubZaxbyHub

discover

Maps repository structure, API surfaces, and governance rules through read-only exploration.

Official
Intermediate
SpecForgeAISpecForgeAI

check_vulnerability

Scan project dependencies and code for security vulnerabilities.

Official
Advanced
automatedigitalautomatedigital
1

mcporter

Manage MCP servers via a unified command-line interface with JSON output.

Official
Intermediate