Skip to content
Agentmart
Submit a tool

explore-api

Use when researching an unfamiliar external API before integration to verify feasibility, integration patterns, and limitations

Skill by giladresisi

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/giladresisi-explore-api

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when researching an unfamiliar external API before integration to verify feasibility, integration patterns, and limitations

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/explore-api

What's inside

Skill name
explore-api
Description
Use when researching an unfamiliar external API before integration to verify feasibility, integration patterns, and limitations
License
MIT
Instructions
177 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Explore External API

## Mission
Systematically research external APIs to prevent integration bugs and validate assumptions before implementation.

## When to Use
- Integrating with unfamiliar external APIs or SDKs
- Using new features of existing APIs
- Switching between API versions or providers
- Any time API documentation needs verification

## Research Workflow

### Phase 1: Documentation Discovery
1. **Official Documentation**
   - Primary API reference: [URL]
   - SDK documentation: [URL]
   - Authentication guide: [URL]
   - Rate limits and quotas: [URL]

2. **Compatibility Matrix**
   - Supported versions: [list]
   - Language SDK versions: [list]
   - Known limitations: [list]
   - Deprecation notices: [check]

3. **Community Resources**
   - GitHub issues for known bugs
   - Stack Overflow common problems
   - Blog posts with integration examples

### Phase 2: API Capability Verification
1. **Endpoint/Feature Support**
   - Required feature: [name] - Supported? ✓/✗
   - API method: [name] - Available in version X? ✓/✗
   - Event types (for streaming): [list actual types]

2. **Authentication & Configuration**
   - Auth method: [API key, OAuth, JWT, etc.]
   - Required environment variables: [list]
   - Configuration precedence: [env vars > config file > defaults]

3. **Request/Response Formats**
   - Request parameters: [required, optional, defaults]
   - Response structure: [schema or example]
   - Error response format: [structure]
   - Pagination pattern (if applicable): [method]

### Phase 3: Integration Pattern Research
1. **Official SDK Usage**
   - Initialization pattern: [code example]
   - Basic request example: [code]
   - Error handling pattern: [code]
   - Async/streaming pattern: [code if applicable]

2. **Environment Setup**
   - Import order requirements: [if any]
   - Initialization timing: [when to init client]
   - Configuration loading: [before/during/after init]

3. **Existing Examples**
   - Official examples: [URLs]
   - Working code samples: [URLs]
   - Integration tutorials: [URLs]

### Phase 4: Proof of Concept
Create minimal working example to validate understanding:

```python
# Minimal POC to verify API works as expected
# Test: [what this proves]
```

**Expected Outcome:** [describe success criteria]
**Fallback Plan:** [alternative if POC fails]

### Phase 5: Risk Assessment
1. **Known Issues**
   - Issue: [description]
     - Impact: [high/medium/low]
     - Mitigation: [approach]

2. **Breaking Changes**
   - Version X → Y changes: [list]
   - Migration required: ✓/✗
   - Backward compatibility: ✓/✗

3. **Rate Limits & Quotas**
   - Requests per minute: [limit]
   - Daily quota: [limit]
   - Retry strategy: [approach]

## Output Format

### API Research Document
Create file: `.agents/research/[api-name]-research.md`

Contents:
- API Overview & Version
- Supported Features Matrix
- Integration Patterns & Code Examples
- Configuration Requirements
- Validation Strategy
- Known Issues & Mitigations
- Reference Links

### Quick Reference for Plan
Generate summary block for embedding in plan-feature.md:

```markdown
## API: [Name] v[Version]

**Documentation:** [Primary URL]
**SDK:** [Library] v[Version] - Compatible: ✓/✗

**Key Findings:**
- Feature [X] supported via [method]
- Event type: [actual name] (not [assumed name])
- Requires: [specific config/setup]

From giladresisi/ai-dev-env, MIT.

More from giladresisi/ai-dev-env

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Mar 6, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from giladresisi

Cite this page

explore-api skill. Agent Mart. https://agentmart.dev/skills/giladresisi-explore-api (last updated 2026-10-24)