Codebase-only read-only research dispatcher. Thin wrapper around the ai-explore agent for architecture mapping, dependency tracing, pattern identification, and risk surfacing. Trigger for 'explore the codebase', 'where does X live', 'map this module', 'what depends on Y', 'trace this import chain'. Not for external evidence with citations; use /ai-research instead.
Scanned 5/27/2026
Install via CLI
openskills install arcasilesgroup/ai-engineering---
name: ai-explore
description: Codebase-only read-only research dispatcher. Thin wrapper around the ai-explore agent for architecture mapping, dependency tracing, pattern identification, and risk surfacing. Trigger for 'explore the codebase', 'where does X live', 'map this module', 'what depends on Y', 'trace this import chain'. Not for external evidence with citations; use /ai-research instead.
effort: cheap
argument-hint: "[question]"
tags: [exploration, research, codebase, architecture, mapping]
model_tier: haiku
mirror_family: antigravity-skills
generated_by: ai-eng sync
canonical_source: .claude/skills/ai-explore/SKILL.md
edit_policy: generated-do-not-edit
---
# Explore
## Quick start
```
/ai-explore "where does the install pipeline run hooks?"
/ai-explore "trace the import chain from cli_factory to the durable repository"
/ai-explore "what files reference the legacy ai_providers schema?"
```
## When to Use
- Architecture mapping: "How is the X module structured?"
- Dependency tracing: "What imports Y? What does Y import?"
- Pattern identification: "How do we typically handle Z?"
- Risk surfacing: "What's load-bearing in this code path?"
## When NOT to Use
- External evidence + citations needed -> use `/ai-research` instead.
- Code change needed -> use `/ai-build` or `/ai-simplify` instead.
- LLM-style code review -> use `/ai-review` instead.
## Process
Per D-133-09 this is a thin wrapper: dispatches the existing
`ai-explore` agent (`.agents/agents/ai-explore.md`) with the user's
question. The agent owns the heavy lifting (file-reading + grep tools
structured findings output).
1. **Capture the question.** Take the entire argument as the question.
2. **Dispatch agent.** Invoke `ai-explore` agent with the question.
3. **Report.** Return the agent's structured findings to the user.
## Output Contract
The agent emits structured Findings / Dependencies / Risks /
Recommendations sections. Wrapper passes them through unchanged.
## Common Mistakes
- Treating this skill as an external-research tool. It is codebase-only.
- Asking it to make changes. Pure read-only.
No comments yet. Be the first to comment!
Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.
SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.
Python backend development expertise for FastAPI, security patterns, database operations, Upstash integrations, and code quality. Use when: (1) Building REST APIs with FastAPI, (2) Implementing JWT/OAuth2 authentication, (3) Setting up SQLAlchemy/async databases, (4) Integrating Redis/Upstash caching, (5) Refactoring AI-generated Python code (deslopification), (6) Designing API patterns, or (7) Optimizing backend performance.
Drive the full internationalization journey for a project — detect the stack, recommend a library, set up the chosen library, wrap existing strings, and optionally connect a translation platform. Use when the user asks to add or configure i18n, internationalization, localization, multi-language support, or translations — including when they explicitly mention LinguiJS, Lingui, next-intl, "wrap strings", "find hardcoded text", "make my app translatable", or "set up translations". Triggers on g...
PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.