ワンクリックで
exploration-tracking
Exploration map management for tracking discussed areas and uncharted territory during DISCUSS phase
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Exploration map management for tracking discussed areas and uncharted territory during DISCUSS phase
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Interactively elicit, capture, and maintain software/system requirements as a living, traceable repository. Use whenever the user wants to gather, write, refine, or organize requirements — including producing or updating an SRS (software/system requirements specification), writing ADRs / architecture decision records, building a requirements traceability graph (DAG), or keeping a decision ledger. Trigger proactively when the working folder already holds requirements artifacts (a `requirements/` folder of YAML, `decisions/` ADRs, an `srs.md`, or `ledger.md`), or when the user shares documents that are clearly specs, RFCs, or feature briefs and wants them structured. Also use for phrases like "let's spec this out", "interview me about what we're building", "capture these requirements", "write a decision record", or "turn these notes into a spec". Not for project management, code review, application code, dependency manifests like requirements.txt, or hardware "system requirements" (RAM/CPU).
Use this skill whenever the user wants to create a bash script that drives an autonomous coding loop — scripts that run Claude Code on a schedule (cron, GitHub Actions, systemd timer) or on-demand to make repository improvements, execute plans, triage issues, or otherwise do agentic work with minimal human intervention. Triggers include phrases like "scout script", "autonomous script", "agent harness", "script that runs on a schedule", "script that implements a plan", ".scripts/*.sh", or any request for a bash script whose body is "run Claude Code with a prompt and commit the results". Always use this skill before writing such a script — it encodes the interview flow, the adversarial-reviewer pattern, and the locking/ledger conventions.
Task structure and atomic commit patterns for granular, verifiable work units
Conflict identification and resolution patterns for requirements, decisions, and plans
Context window management techniques for maintaining efficiency and preventing context bloat
Phase coordination, agent handoffs, and workflow state machine management
| name | exploration-tracking |
| description | Exploration map management for tracking discussed areas and uncharted territory during DISCUSS phase |
| triggers | ["exploration map","territory tracking","discussion progress","uncharted areas"] |
This skill provides techniques for maintaining awareness of explored vs. uncharted territory during the DISCUSS phase, ensuring comprehensive coverage and documented gaps.
| Symbol | Status | Meaning |
|---|---|---|
| ✓ | EXPLORED | Fully discussed, decisions made |
| ◐ | PARTIAL | Started but incomplete, some findings |
| → | CURRENT | Currently exploring this area |
| ○ | UNCHARTED | Identified but not yet explored |
| ⊘ | SKIPPED | User chose to skip (reason recorded) |
| ⚑ | FLAGGED | Needs follow-up or has blockers |
[MAIN TOPIC]
├── ✓ EXPLORED: [Area 1]
│ ├── ✓ [Sub-area 1.1] - [Summary of findings]
│ └── ◐ PARTIAL: [Sub-area 1.2] - [What we know, what's unclear]
├── → CURRENT: [Area 2]
│ ├── ✓ [Sub-area 2.1] - [Completed]
│ └── ○ UNCHARTED: [Sub-area 2.2]
├── ○ UNCHARTED: [Area 3]
│ └── [Suspected sub-topics]
└── ⊘ SKIPPED: [Area 4] - [Reason]
| Level | Purpose | Example |
|---|---|---|
| L1 | Main topic areas | "Authentication", "Data Storage" |
| L2 | Sub-areas within topic | "Login flow", "Session management" |
| L3 | Specific details | "Password requirements", "Token expiry" |
| L4+ | Deep specifics | "Bcrypt vs Argon2", "JWT claims" |
1. Add Exploration Map section to ITEM-XXX.md
2. Set topic from user's initial request
3. Identify initial L1 areas from topic
4. Mark all as UNCHARTED
5. Set status to IN_PROGRESS
1. Mark previous CURRENT as appropriate status
- EXPLORED if complete
- PARTIAL if interrupted
- SKIPPED if user chose to skip
2. Mark new area as CURRENT
3. Record timestamp
4. Add any newly discovered sub-areas
When conversation reveals new areas:
1. Identify where in tree the area belongs
2. Add as child of appropriate parent
3. Mark as UNCHARTED
4. Note discovery context
1. Change status to EXPLORED
2. Add summary of findings
3. Link to relevant decisions (DECISION-XXX)
4. Record timestamp
5. Update CURRENT to next area
1. Change status to SKIPPED
2. Record reason for skipping
3. Note if should revisit later
4. Move to next area
1. Change status to FLAGGED
2. Record what's blocking
3. Note required action
4. Continue to next area
At regular intervals and phase transitions:
**Exploration Checkpoint**
Current position: [CURRENT AREA]
Just explored: [What we covered]
Key findings: [Summary]
**Map so far:**
[Visual tree with status indicators]
**Options:**
1. Dig deeper into [current area]
2. Move to [next uncharted area]
3. Return to [partial area]
4. Skip [current] and note reason
5. Mark discussion complete
| Choice | Action |
|---|---|
| Dig deeper | Add sub-areas to current, continue exploring |
| Move on | Mark current as EXPLORED, go to next UNCHARTED |
| Return to partial | Mark current as PARTIAL, resume flagged area |
| Skip | Mark as SKIPPED with reason, go to next |
| Complete | Finalize map, transition to PLAN phase |
1. Mark current position appropriately
2. Navigate to target area in map
3. Update target status to CURRENT
4. Resume exploration with prior context
5. Note backtrack in exploration log
Coverage Analysis:
- Total areas identified: [N]
- Fully explored: [X] (✓)
- Partially explored: [Y] (◐)
- Uncharted: [Z] (○)
- Skipped: [W] (⊘)
- Flagged: [V] (⚑)
Coverage: [X/(N-W)]%
Uncharted areas:
1. [Area] - [Why not explored]
2. [Area] - [Why not explored]
Skipped areas:
1. [Area] - [Reason skipped]
Flagged areas:
1. [Area] - [What's blocking]
| Coverage | Recommendation |
|---|---|
| 90%+ | Safe to proceed to PLAN |
| 70-89% | Review uncharted areas with user |
| <70% | Continue DISCUSS phase |
See questioning.md for adaptive questioning patterns that drive exploration.