# Serp Research

> Turn accepted search evidence into an intent, competitor, and information-gain brief.

- Skill: `lionelndong/serp-research` (Agent Skill)
- Install (CLI): `npx skillmds add lionelndong/serp-research`
- Raw SKILL.md: https://api.skillmd.com/api/skills/lionelndong/serp-research/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: lionelndong (https://skillmd.com/u/lionelndong)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/lionelndong/serp-research

---


# SERP Research and Beat Spec

## Inputs

Accepted candidate brief, keyword/parent-topic data, typed top-ten SERP rows, current product context, and allowed authoritative sources.

## Method

1. State the dominant intent and reader job in one sentence.
2. Analyze the leading results for format, depth, recurring sections, claims, visuals, links, and unanswered jobs.
3. Build a must-cover consensus list and a separate list of weaknesses or gaps.
4. Define a **BEAT SPEC**: required format, depth, H2 topics, decision aids, sources, visual roles, and the article’s counter-asset.
5. Choose one concrete information-gain asset: first-hand test, product proof, original comparison, data, expert/community synthesis, framework, or defensible point of view.
6. Use STEPPS only when the article needs a legitimate share/link hook; reject clickbait or off-intent ideas.

## Output

Research dossier, competitor matrix, must-cover list, named weak pages, BEAT SPEC, source list, and information-gain plan. Do not draft until this is complete.