Agent skill

unikit-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements in {{engine_name}} projects. Use when the user wants to think through something before implementing, investigate architecture, compare approaches, analyze systems, research patterns, or understand existing code. Activate when user says "explore", "investigate", "research", "let's think about", "compare options", "analyze system", "how does X work", or wants to deeply understand something before coding. Also use when discussing {{engine_name}} architecture decisions, Zenject bindings

majiayu000534★ · 1 repos on radarProfile →
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill unikit-explore --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 29 KB
Bundled scripts: none
Version: 2.1
Declared author: unikit
Allowed tools: -Read-Glob-Grep-Write-Edit-Bash(ls
Path: skills/analysis/unikit-explore/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Explains that the skill is a thinking partner for exploring ideas, investigating problems, and clarifying requirements in {{engine_name}} projects. It activates when the user uses triggers such as "explore", "investigate", "research", or related phrases. The mode is explicitly non-implementing: you may read files and investigate code but must not modify project code; if asked to implement, you should remind the user to exit explore mode first.

How it works

The skill defines exploration-oriented behavior: it remains non-implementation, supports subagent delegation with an Explore subagent when needed, and relies on a flexible, ask-first approach. It emphasizes visualization, mapping architecture, Zenject bindings, and system analysis. It can use an Agent subagent for parallel codebase investigation or fallback to Glob/Grep/Read if Agent is unavailable. It instructs to adapt to the topic with no fixed steps, and to surface multiple directions without forcing decisions.

When to use it

Use when the user wants to think through architecture decisions, compare approaches, analyze systems, research patterns, or understand existing code. It is particularly noted for discussions around {{engine_name}} architecture decisions and Zenject bindings.

What it can touch

Tools allowed: Read, Glob, Grep, Write, Edit, Bash(ls *), Bash(find *), Bash(wc *), Agent, AskUserQuestion, WebSearch, WebFetch. It can read files, search codebases, and interact with the user to gather questions or concerns. It can spawn a subagent of type Explore when needed for parallel codebase investigation.

Caveats

  • It is explicitly non-implementing: if the user asks to implement something, the user should exit explore mode first.
  • It operates under the project context bootstrap rules, requiring silent loading of project context before interaction.
  • The stance encourages curiosity and open threads rather than prescriptive answers, and relies on codebase grounding for decisions.
From the SKILL.md

# UniKit Explore — Thinking Partner for {{engine_name}} Projects Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes. **IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER implement features or modify project code. If the user asks to implement something, remind them to exit explore mode first (e.g., start with `/unikit-plan`). **This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore. ## Language Awareness — BLOCKING PRE-REQUISITE **BEFORE producing ANY output**, silently read `.unikit/system/LANGUAGE_RULES.md` and apply its rules to ALL subsequent output. If the file is missing or unreadable, fall back to English. Do not produce any user-facing output until language rules are loaded. Do not announce, confirm, or mention the language setting. <!-- unikit:agents codex --> ## Subagent Delegation — BLOCKING PRE-REQUISITE When the workflow reaches a step that requires a subagent (`Agent`), the assistant MUST automatically spawn the subagent if agent execut

What's inside
Steps it walks through
  1. Language Awareness — BLOCKING PRE-REQUISITE
  2. Subagent Delegation — BLOCKING PRE-REQUISITE
  3. Artifact Ownership
  4. Insight routing table
  5. The Stance
  6. What You Might Do
  7. Step 0: Bootstrap Context (MANDATORY)
  8. Required reads (always, every time)
  9. Stack documentation enrichment (context7)
  10. Optional reads (check if relevant)
  11. Why this matters
  12. Input handling
  13. Exploration mode detection
  14. When a plan exists
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the unikit-explore skill do?

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements in {{engine_name}} projects. Use when the user wants to think through something before implementing, investigate architecture, compare approaches, analyze systems, research patterns, or understand existing code. Activate when user says "explore", "investigate", "research", "let's think about", "compare options", "analyze system", "how does X work", or wants to deeply understand something before coding. Also use when discussing {{engine_name}} architecture decisions, Zenject bindings

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill unikit-explore --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going