specs-explore
Explore codebase before committing to a change. Phase executor skill for specs.explore command.
How do I install this agent skill?
npx skills add https://github.com/giuseppe-trisciuoglio/developer-kit --skill specs-exploreIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill is a standard codebase exploration utility designed to help an agent investigate project structure and document potential changes. It contains explicit safety rules to prevent modification of existing code and focuses on information gathering.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
specs-explore Skill
Investigate the codebase, think through problems, compare approaches, and return a structured analysis. Only create exploration.md when --spec is provided.
What You Receive
The orchestrator will give you:
- A topic or feature to explore
--specpath (optional)--langframework (optional)
Execution Steps
Step 1: Understand the Request
Parse what the user wants to explore:
- Is this a new feature? A bug fix? A refactor?
- What domain does it touch?
Step 2: Investigate the Codebase
Read relevant code to understand:
- Current architecture and patterns
- Files and modules that would be affected
- Existing behavior that relates to the request
- Potential constraints or risks
INVESTIGATE:
├── Read entry points and key files
├── Search for related functionality (Grep)
├── Check existing tests (Glob)
├── Look for patterns already in use
└── Identify dependencies and coupling
Step 3: Analyze Options
If there are multiple approaches, compare them:
| Approach | Pros | Cons | Complexity |
|---|---|---|---|
| Option A | ... | ... | Low/Med/High |
| Option B | ... | ... | Low/Med/High |
Step 4: Persist Artifact (if --spec is provided)
If --spec=docs/specs/001-add-jwt-auth is specified, write to docs/specs/001-add-jwt-auth/exploration.md:
## Exploration: {topic}
### Current State
{How the system works today relevant to this topic}
### Affected Areas
- `path/to/file.ext` — {why it's affected}
- `path/to/other.ext` — {why it's affected}
### Approaches
1. **{Approach name}** — {brief description}
- Pros: {list}
- Cons: {list}
- Effort: {Low/Medium/High}
2. **{Approach name}** — {brief description}
- Pros: {list}
- Cons: {list}
- Effort: {Low/Medium/High}
### Recommendation
{Your recommended approach and why}
### Risks
- {Risk 1}
- {Risk 2}
### Ready for Proposal
{Yes/No — and what the user should know}
Step 5: Return Result
Return the same structured analysis (inline), plus:
Status Report:
- status:
done|blocked|partial - executive_summary: 1-sentence description of what was explored and key recommendation
- artifact:
{spec}/exploration.md(if--specprovided) or "none" - next_recommended:
specs.brainstorm(if spec provided) ornone(if standalone) - risks: risks discovered, or "None"
Rules
- The ONLY file you MAY create is
exploration.mdinside the spec folder (if--specprovided) - DO NOT modify any existing code or files
- ALWAYS read real code, never guess about the codebase
- Keep your analysis CONCISE — summary, not a novel
- If you can't find enough information, say so clearly
- If the request is too vague, ask for clarification
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/giuseppe-trisciuoglio/developer-kit/specs-explore">View specs-explore on skillZs</a>