Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Analyze Agent Data

ASecurity

Real-time environmental context API for AI agents. 6 intelligence feeds updated hourly to daily: Master Intelligence Digest (cross-domain synthesis), Moltbook community sentiment, GitHub trending repos, Polymarket prediction signals, Pulse narrative intelligence, and token marke…

19 stars
0 votes
0 copies
2 views
Added 9/19/2026
ai-agentstypescriptgotestinggitapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill analyze-agent-data --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Analyze Agent Data?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Analyze Agent Data
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-analyze-agent-data/badge)](https://www.skillsdirectory.com/skills/rondoflow-analyze-agent-data)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: analyze-agent-data
description: "Real-time environmental context API for AI agents. 6 intelligence feeds updated hourly to daily: Master Intelligence Digest (cross-domain synthesis), Moltbook community sentiment, GitHub trending repos, Polymarket prediction signals, Pulse narrative intelligence, and token marke…"
category: "Finance & Crypto"
author: community
version: "2.0.0"
icon: coins
---

# Moltalyzer — Real-Time Intelligence API for AI Agents

API at `https://api.moltalyzer.xyz`. All digest endpoints have a free tier — no auth, no account, no payment required.

Full API docs: [api.moltalyzer.xyz/docs](https://api.moltalyzer.xyz/docs) | OpenAPI spec: [api.moltalyzer.xyz/openapi.json](https://api.moltalyzer.xyz/openapi.json)

## Intelligence Feeds

| Feed | What It Covers | Free Endpoint | Cadence |
|------|---------------|---------------|---------|
| Master Intelligence | Cross-domain synthesis of all feeds | `GET /api/intelligence/latest` | 4 hours |
| Moltbook Community | AI agent discourse & sentiment | `GET /api/moltbook/digests/latest` | 1 hour |
| GitHub Trends | New repos, emerging tools, language trends | `GET /api/github/digests/latest` | 24 hours |
| Polymarket | Prediction market signals & predetermined outcomes | `GET /api/polymarket/latest` | 4 hours |
| Pulse Narratives | Cross-source narrative lifecycle tracking | `GET /api/pulse/ai-business/digest/latest` | 4 hours |
| Token Signals | On-chain signal detection & scoring | `GET /api/tokens/latest` | 4 minutes |

All free `/latest` endpoints: **1 request per 5 minutes per IP, no auth needed.**

## Quick Start — Polling Pattern

The recommended integration pattern: poll cheap index endpoints, fetch full data only when new.

```typescript
// All free, no auth, no setup
const BASE = "https://api.moltalyzer.xyz";

// 1. Check index (unlimited, free) to detect new data
const indexRes = await fetch(`${BASE}/api/intelligence/index`);
const { index, updatedAt } = await indexRes.json();

// 2. If new, fetch brief (unlimited, free) for a quick summary
const briefRes = await fetch(`${BASE}/api/intelligence/brief`);
const brief = await briefRes.json();
// brief.data: { title, executiveSummary, sentiment }

// 3. If actionable, fetch latest (1 req/5min, free) for full analysis
const latestRes = await fetch(`${BASE}/api/intelligence/latest`);
const latest = await latestRes.json();
// latest.data: { fullAnalysis, crossDomainInsights, narratives, signals, ... }
```

## Endpoint Tiers

Every feed has 3 tiers — index, brief, latest — designed for efficient polling:

| Tier | Rate Limit | Returns | Use For |
|------|-----------|---------|---------|
| `/index` | Unlimited | ID + timestamp + cadence | Change detection |
| `/brief` | Unlimited | Title + summary + key metrics | Quick situational awareness |
| `/latest` | 1 req/5min | Full analysis + all structured data | Deep analysis & decision-making |

## Additional Free Endpoints

```typescript
// Sample data (older snapshots, great for testing)
await fetch(`${BASE}/api/moltbook/sample`);      // 1 req/20min
await fetch(`${BASE}/api/github/sample`);         // 1 req/20min
await fetch(`${BASE}/api/polymarket/sample`);     // 1 req/20min
await fetch(`${BASE}/api/tokens/sample`);         // 1 req/20min
await fetch(`${BASE}/api/intelligence/sample`);   // 1 req/20min

// Submit feedback on digest quality
await fetch(`${BASE}/api/intelligence/feedback`, {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ rating: "good", digestId: "..." }),
});
```

## Viral Advisor (Flagship Product)

AI-powered content strategy using live intelligence data. Submit a post idea, get a complete ready-to-publish post with viral scoring and data-backed suggestions.

| Tier | Endpoint | Model |
|------|----------|-------|
| Standard | `POST /api/moltbook/advisor` | Claude Sonnet |
| Premium | `POST /api/moltbook/advisor/premium` | Claude Opus |

```typescript
const res = await fetch(`${BASE}/api/moltbook/advisor`, {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ prompt: "AI agents are replacing junior devs" }),
});
const data = await res.json();
// data.viralScore, data.suggestedTitle, data.suggestedContent, data.suggestions
```

> Advisor and other premium endpoints require payment. See [api.moltalyzer.xyz/docs](https://api.moltalyzer.xyz/docs) for pricing and payment options.

## Recommended Polling Intervals

| Feed | Update Cadence | Poll `/index` Every | Fetch `/latest` When |
|------|---------------|--------------------|--------------------|
| Intelligence | 4 hours | 10 minutes | Index changes |
| Moltbook | 1 hour | 5 minutes | Index changes |
| GitHub | 24 hours | 6 hours | Index changes |
| Polymarket | 4 hours | 15 minutes | Index changes |
| Pulse | 4 hours | 15 minutes | Index changes |
| Tokens | 4 minutes | 2 minutes | Index changes |

## Error Handling

- **429** — Rate limited. Respect `Retry-After` header (seconds to wait).
- **503** — Data stale (pipeline issue). Response includes `retryAfter` field.
- **404** — No data available yet.

All responses include `RateLimit-Remaining` and `RateLimit-Reset` headers.

## Reference Docs

For full response schemas, see `{baseDir}/references/response-formats.md`.
For more code examples and error handling patterns, see `{baseDir}/references/code-examples.md`.
For complete endpoint tables and rate limits, see `{baseDir}/references/api-reference.md`.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →