Skip to content
Skills Library
Programming · Research

explore

/explore

Explore mode for codebase investigation and requirements clarification before committing to a change package. Use when requirements are unclear, a codebase investigation is needed before planning, options are being compared, or a risk scan is needed before a commit. Triggers on: "explore", "investigate", "look around", "understand the codebase", "scan for risks", "what's in here", "before I commit to anything". Stays in read-only observe mode — no files created — until an explicit artifact commit signal is received.

Licence
Apache-2.0
Last repository change
16.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 16.08.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Explore mode for codebase investigation and requirements clarification before committing to a change package. Use when requirements are unclear, a codebase investigation is needed before planning, options are being compared, or a risk scan is needed before a commit. Triggers on: "explore", "investigate", "look around", "understand the codebase", "scan for risks", "what's in here", "before I commit to anything". Stays in read-only observe mode — no files created — until an explicit artifact commit signal is received.

Triggers from the description

exploreinvestigatelook aroundunderstand the codebasescan for riskswhatbefore I commit to anything
Original author description

Explore mode for codebase investigation and requirements clarification before committing to a change package. Use when requirements are unclear, a codebase investigation is needed before planning, options are being compared, or a risk scan is needed before a commit. Triggers on: "explore", "investigate", "look around", "understand the codebase", "scan for risks", "what's in here", "before I commit to anything". Stays in read-only observe mode — no files created — until an explicit artifact commit signal is received.

How it works

  1. When to Enter Explore Mode
  2. While in Explore Mode
  3. Explicit Artifact Commit Triggers
  4. Explore Mode Summary Output
  5. Common Rationalizations
  6. Verification
Original SKILL.md headings · 76 lines, 411 words
SKILL.md preview
---
name: explore
description: >
  Explore mode for codebase investigation and requirements clarification before committing to a change package.
  Use when requirements are unclear, a codebase investigation is needed before planning, options are being compared,
  or a risk scan is needed before a commit. Triggers on: "explore", "investigate", "look around", "understand the codebase",
  "scan for risks", "what's in here", "before I commit to anything".
  Stays in read-only observe mode — no files created — until an explicit artifact commit signal is received.
---

# Explore Mode

Read-only investigation mode. Observe and analyze without creating artifacts until explicitly signaled to proceed.

## When to Enter Explore Mode

Enter explore mode when any of the following apply:

- Requirements are not yet clear; need to ask clarifying questions or read the codebase first
- A codebase investigation is needed before a plan can be written
- Option comparison is in progress (weighing approaches before deciding)
- Risk scan needed before committing to a change package scope

## While in Explore Mode

**No files are created or modified** until an explicit artifact commit signal is received.

Permitted actions in explore mode:
- Read files (`read` / `view` tools)
- Search codebase (`search` / `grep` tools)
- Ask the user clarifying questions
- Build an internal understanding of the system

Prohibited actions until signaled:
- Creating or modifying `changes/` files
- Creating or modifying any source or documentation file
- Running `sync-dotgithub.ps1`

## Explicit Artifact Commit Triggers

Explore mode ends and artifact creation begins **only** when one of the following explicit signals is received from the user:

1. `/proceed`
2. `"create change package"`
3. `"start brainstorm"`
4. `"I want to formalize this"`

Any other phrasing that sounds like "let's start writing" should be confirmed with the user before exiting explore mode: "Do you want me to create a change package now?"

## Explore Mode Summary Output

Before transitioning out of explore mode, produce a brief summary:

```
## Explore Summary
- **Scope**: [what was investigated]
- **Key Findings**: [2–5 bullet points]
- **Recommended Next Step**: [brainstorm / Simple or Standard plan / other, as selected under WORKFLOW.md]
- **Risk Signal**: [Low / Med / High — brief rationale]
```

This summary becomes input to the brainstorm or plan step.

## Common Rationalizations

在進行 explore 探索過程中,AI 可能以下列藉口略過關鍵步驟:

| 常見藉口 | 反制說明 |
|---------|---------|
| "看一看就夠了,不需要正式 explore" | ⛔ 非正式「看一看」沒有輸出物——Explore 必須產出 Findings 文件,才能作為 brainstorm/plan 的可靠輸入 |
| "程式碼庫我已經很熟了,可以直接進入計畫" | 熟悉感不等於對當前狀態的準確掌握——任何超過兩週未接觸的程式碼庫,或涉及 brownfield 改動,均應重新 explore |
| "Explore 會拖慢速度,直接開始實作更有效率" | 未探索就實作等於在未知地圖上規劃路線——explore 的時間投入遠低於因誤解現況而導致的返工成本 |

## Verification

在完成 explore 並準備移交產出物前,逐項確認(Gate = 交付前閘門;Verification = 自我完成確認):

- [ ] `rg "## Findings\|## Key Findings" <output-file>` 有匹配(Findings 段落已存在)
- [ ] Findings 含至少 2 個具體觀察(非「程式碼看起來正常」等模糊描述)
- [ ] Risk Signal 已填寫(Low / Med / High + 一句理由)
- [ ] Recommended Next Step 已依 `WORKFLOW.md` 的 Simple / Standard / High-Risk 模式明確記錄(brainstorm / plan / 其他具體行動)
- [ ] Explore 範圍(Scope)已明確描述(調查了哪些模組/路徑/決策點)
- [ ] 未建立或修改任何非 Explore 產出物的程式碼檔案(Explore = read-only)
- [ ] 產出摘要可直接貼入 brainstorm-agent 或 plan-agent 的輸入脈絡

Versions

RepositoryScoreLicence
This page · forgivesam168/ai-dev-workflow100Apache-2.0
yonatangross/orchestkit100MIT
yonatangross/orchestkit100MIT
rapiddweller/archkeel100MIT
zimoliao/scholaraio100MIT
artk0de/tearags-mcp100MIT
artk0de/tearags-mcp100MIT
artk0de/tearags-mcp100MIT
artk0de/tearags-mcp100MIT

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 9cb6d06bf9ba (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95codebase-explore
    Read-only codebase exploration and analysis. Use when the user asks "analyze codebase", "explore code", "what does this project do", "find files related to", "understand architecture", or needs to research the codebase before making changes. Cannot modify any files.
  • 100explore-codebase
    Performs in-depth codebase exploration at the start of a coding session. Builds comprehensive understanding of project structure, architecture, key components, and patterns. Use when starting a new session, when asked to understand or explore the codebase, when asked "what does…
  • 100investigate
    [Fix & Debug] Use when a workflow step or the user asks for read-only code-flow investigation. --mode=debug finds bug root causes; --mode=explain narrates purpose, flow and impact. Plans/decisions: understand.
  • 100investigate
    [Fix & Debug] Use when a workflow step or the user asks for read-only code-flow investigation. --mode=debug finds bug root causes; --mode=explain narrates purpose, flow and impact. Plans/decisions: understand.
  • 90nerd-explore
    Use when discovering codebase facts, context, patterns, constraints, or unknowns through focused, incremental, read-only investigation without diagnosing a failure or modifying state.
  • 90explore-codebase
    Explore codebase files, patterns, and structure for a given topic. USE WHEN gathering implementation context before planning or executing tasks, when asked to research the codebase, or when a planning agent needs a Sub-Agent A (Codebase Research). Returns a Codebase Research…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.