跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

competitor-social-research

Use when the user wants to research competitors' social media strategy, compare brands or creators, find what content is working in a niche, identify content gaps, or produce a practical social strategy brief from public social data.

科研3.3kskills/competitor-social-research/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/scrapecreators/social-media-research-skills/competitor-social-research/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Competitor Social Research

Overview

Analyze what competitors are doing on social and what appears to be working. This skill combines profile data, recent posts, outlier analysis, transcripts, and optionally comments to produce a practical competitor brief.

When to Use

Use this skill when the user asks to:

  • compare competitors on TikTok, Instagram, YouTube, LinkedIn, Facebook, X, Threads, or other social platforms
  • find what content is working in a niche
  • benchmark posting frequency, formats, topics, and engagement
  • identify content gaps or opportunities
  • build a social strategy from competitor research

Workflow

  1. Define competitors and platforms

    • Use provided handles/URLs.
    • If only company names are provided, search profiles first and confirm likely matches when ambiguity matters.
  2. Fetch profile snapshots

    • Followers/subscribers
    • Bio/positioning
    • Links
    • Verification/public metadata
  3. Fetch recent content

    • Pull comparable recent windows per competitor.
    • Track source URLs, dates, captions, formats, and metrics.
  4. Find outliers per competitor

    • Use each account's own median baseline.
    • Do not compare raw views between a huge brand and a small brand without context.
  5. Analyze content strategy

    • Content pillars
    • Formats
    • Hook styles
    • Posting cadence
    • Offers/CTAs
    • Use of founder/creator personality
    • Community/comment patterns
  6. Find gaps and opportunities Look for:

    • topics competitors avoid
    • formats that overperform but few competitors use
    • unanswered audience questions
    • weak hooks or repetitive content
    • platform whitespace

Useful ScrapeCreators Endpoints

Use the relevant profile/feed/detail/transcript/comment endpoints from scrapecreators-api. Common routes include:

  • TikTok: /v1/tiktok/profile, /v3/tiktok/profile/videos
  • Instagram: /v1/instagram/profile, /v2/instagram/user/posts, /v1/instagram/user/reels
  • YouTube: /v1/youtube/channel, /v1/youtube/channel-videos, /v1/youtube/channel/shorts
  • LinkedIn: /v1/linkedin/company, /v1/linkedin/company/posts
  • Facebook: /v1/facebook/profile, /v1/facebook/profile/posts, /v1/facebook/profile/reels
  • X/Twitter: /v1/twitter/profile, /v1/twitter/user-tweets
  • Threads: /v1/threads/profile, /v1/threads/user/posts
  • Bluesky: /v1/bluesky/profile, /v1/bluesky/user/posts

Output Format

# Competitor Social Research Brief

## Executive Summary
- Biggest opportunity:
- Competitor to study closest:
- Content format to test first:

## Competitor Snapshot
| Competitor | Platforms | Audience size | Posting cadence | Best-performing format | Notes |
|---|---|---:|---|---|---|

## What Is Working
### Competitor A
- Content pillars:
- Outlier examples:
- Hooks/formats:

## Cross-Competitor Patterns
1. ...
2. ...

## Gaps and Opportunities
| Opportunity | Evidence | Suggested test |
|---|---|---|

## Recommended Content Tests
1. ...
2. ...
3. ...

## Sources
- [Post/profile/ad](url)

Common Pitfalls

  • Do not compare competitors only by follower count. Engagement and outlier lift matter more.
  • Do not mix platforms without platform context. A good LinkedIn post and good TikTok are different artifacts.
  • Do not assume a profile match from a company name if multiple brands share the name.
  • Do not present competitor strategy as fact when it is inferred from public content. Say "appears to" or "suggests".

相似的 Skill

lead-research-assistant
ComposioHQ/awesome-claude-skills77k

lead-research-assistant

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

科研

13c-metabolic-flux
K-Dense-AI/scientific-agent-skills48k

13c-metabolic-flux

Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation, constrained multistart fitting, and flux-profile diagnostics. Use for 13C-MFA, carbon tracing, mass isotopomer distributions (MDVs/MIDs), positional isotopomers, parallel tracer experiments, and determining whether labeling data constrain a pathway flux. Distinguishes measured-label inference from COBRA flux balance analysis and flags experiments requiring nonstationary MFA.

科研

datamol
K-Dense-AI/scientific-agent-skills48k

datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

科研

biopython
K-Dense-AI/scientific-agent-skills48k

biopython

Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.

科研

bulk-rnaseq
K-Dense-AI/scientific-agent-skills48k

bulk-rnaseq

Prepares bulk RNA-seq FASTQ, Salmon, STAR or featureCounts output for gene-level differential expression. Covers nf-core/rnaseq and standalone quantification, biological replication, strandedness, reference provenance, validated count assembly and a PyDESeq2 handoff. Use for FASTQ-to-counts analysis, nf-core/rnaseq configuration, STAR/Salmon quantification, or building a counts matrix for DESeq2. For single-cell data use scanpy; for statistical fitting alone use pydeseq2.

科研

alphagenome
K-Dense-AI/scientific-agent-skills48k

alphagenome

Looks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), scores variants or scans windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and builds Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.

科研