Skip to content
SkillModel-led816 tokens in use

Competitor Social Research

Benchmarks competitors' social accounts across platforms, finds what content is working for each, and ends with gaps and content tests to run.

6,856 stars on the repository MIT LicenseScrapeCreators/social-media-research-skills · skills/competitor-social-research
npx skills add ScrapeCreators/social-media-research-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Competitor Social Research costs

49tokens idle
816tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldeclarednetworkdeclaredwrites filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure23/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity24
  • Maintenance8
  • Community40
  • Maturity24
  • Momentum40

Competitor Social Research lets an agent compare brands or creators on TikTok, Instagram, YouTube, LinkedIn, Facebook, X, Threads and Bluesky. It pulls profile snapshots and recent posts, finds outliers against each account’s own baseline and analyzes content pillars, formats, hooks and cadence.

It closes with a brief: an executive summary, a competitor snapshot table, cross-competitor patterns, gaps and opportunities, recommended content tests and source links.

What You Get

  • An executive summary naming the biggest opportunity and the first format to test
  • A snapshot table of platforms, audience size, cadence and best-performing format per competitor
  • Per-competitor notes on pillars, outlier examples and hook styles, plus cross-competitor patterns
  • A table of gaps with evidence and a suggested test, and a list of recommended content tests with sources

Common Use Cases

  • Benchmarking posting frequency and formats against three or four rivals
  • Finding content formats that overperform but few competitors use
  • Building a social strategy brief from competitor research
  • Spotting unanswered audience questions in a niche

What Makes It Unique

It judges each competitor against its own baseline, so a large brand and a small one are never ranked by raw views. It keeps platforms separate, asks the agent to confirm ambiguous profile matches, and words inferred strategy with hedges such as “appears to” and “suggests”.

Under The Hood

The skill is one SKILL.md of instructions with no scripts. It points the agent to profile, feed, detail, transcript and comment endpoints of the ScrapeCreators REST API, called with the SCRAPECREATORS_API_KEY environment variable, and refers to the companion scrapecreators-api skill for endpoint details. Its frontmatter allows the shell, file reading and writing, and web fetches, so the agent can run commands, call the API over the network and write the brief to a file.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers