agentleFS
nicojunknicojunk/claude-ig/skills/ig-competitor/SKILL.md

ig-competitor

Skill17 starsChanged 8 months agoMITView on GitHub

Competitor research and analysis via delegation to the ig-research skill. Identifies target accounts, delegates data collection, synthesizes findings into actionable hooks, formats, and content gaps.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. workflownicojunk/claude-skills★ 099% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository13 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for specific accounts, or suggest based on these criteria:

    line 29
  2. Distinctive:

    Document the selected accounts with handles and reasoning for selection.

    line 38
  3. Distinctive:

    Document hook patterns and CTA strategies

    line 48
  4. Distinctive:

    If ig-research is unavailable, fall back to manual data collection using available API tools or web research tools.

    line 52
  5. Distinctive:

    Read all generated research reports:

    line 56
  6. Distinctive:

    Before delivering the report, verify:

    line 116

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

IG Competitor -- Competitor research via delegation

Key references:

  • references/competitor-framework.md -- competitor selection criteria, analysis dimensions, comparison matrix
  • references/account-baseline.md -- own account metrics for gap analysis

NOTE: This is a DELEGATION skill. The primary data collection happens via the ig-research skill. This skill orchestrates the research, reads results, and synthesizes recommendations.


Phase 1: Target Selection

Identify which competitor accounts to research:

  1. Ask the user for specific accounts, or suggest based on these criteria:
    • Same niche (fitness, nutrition, health for German-speaking audience)
    • Similar follower count range (0.5x to 5x of own account)
    • Active posting (at least 3 posts/week)
    • High engagement relative to follower count
  2. Select 3-5 target accounts. More than 5 dilutes the analysis.
  3. Load references/competitor-framework.md for the analysis dimensions to apply.
  4. Load references/account-baseline.md for own account metrics (needed for gap analysis).

Document the selected accounts with handles and reasoning for selection.

Phase 2: Delegation

For each target account, invoke the ig-research skill:

  1. Pass the account handle and the analysis dimensions from competitor-framework.md.
  2. The ig-research skill will:
    • Collect public data (post frequency, content types, engagement patterns)
    • Analyze content pillars and topic distribution
    • Document hook patterns and CTA strategies
    • Note visual style and branding approach
  3. Each research run produces a report file. Note the output paths.

If ig-research is unavailable, fall back to manual data collection using available API tools or web research tools.

Phase 3: Report Reading

Read all generated research reports:

  1. Load each competitor report file.
  2. Extract key data points per competitor:
    • Posting frequency and consistency
    • Top-performing content (by visible engagement: likes, comments)
    • Content pillar distribution
    • Hook patterns used (categorize into hook-library.md categories)
    • CTA strategies
    • Audience interaction style (comment responses, story engagement)
    • Affiliate/partnership approach

Compile into a comparison matrix.

Phase 4: Synthesis

Analyze the collected data for actionable insights:

Hook Adaptation

  • Which hook patterns are competitors using successfully that we are NOT using?
  • List 3-5 hooks to adapt (not copy) with German examples:
    • Original: "[competitor hook]"
    • Adapted: "[our version in German]"
    • Why it works: [psychological trigger]

Format Testing

  • Which formats are competitors using that we are underrepresenting?
  • Prioritize by: (a) competitor success with the format, (b) our audience alignment
  • Recommend 2-3 format experiments with specific topic suggestions

Content Pillar Insights

  • What topics do competitors cover that we do not?
  • What topics do WE cover that competitors do not (our differentiation)?
  • Where is there topic saturation across all competitors (avoid or differentiate)?

Engagement Tactics

  • How do competitors drive saves, shares, and DMs?
  • Which CTA patterns are most effective?
  • Comment response strategies worth adopting

Phase 5: Gap Analysis

Cross-reference competitor findings with own account baseline:

DimensionOur AccountCompetitor AvgGapPriority
Posting FrequencyX/weekY/week+/-ZHigh/Med/Low
Reel RatioX%Y%+/-Z%High/Med/Low
Carousel RatioX%Y%+/-Z%High/Med/Low
Avg Engagement RateX%Y%+/-Z%High/Med/Low
Hook DiversityX categoriesY categories+/-ZHigh/Med/Low
CTA VarietyX typesY types+/-ZHigh/Med/Low

Flag any gap where competitor average exceeds our metric by more than 30% as high priority.

Differentiation Check

Equally important: identify what we do BETTER than competitors. These are strengths to double down on, not change.

Phase 6: Quality Check

Before delivering the report, verify:

  • At least 3 competitor accounts analyzed
  • Comparison matrix includes all key dimensions
  • Hook adaptations are original (adapted, not copied verbatim)
  • Gap analysis references actual baseline data
  • Recommendations are specific and actionable
  • Differentiation strengths are identified (not just gaps)

Phase 7: Delivery

Output as a structured Markdown report:

## Competitor Analysis Report

**Accounts Analyzed:** [list of handles]
**Own Account Baseline:** [key metrics summary]
**Date:** [date]

### Competitor Comparison Matrix
| Metric | Our Account | [Comp 1] | [Comp 2] | [Comp 3] |
|--------|------------|----------|----------|----------|

### Hooks to Adapt
1. **[Pattern Name]:** "[adapted hook in German]" -- Source: [competitor]
2. ...

### Formats to Test
1. [format] -- [why, based on competitor data]
2. ...

### Content Gaps (We Should Add)
- [topic/format gap]

### Our Strengths (Double Down)
- [differentiator]

### Gap Analysis Summary
| Dimension | Gap | Priority | Recommended Action |
|-----------|-----|----------|-------------------|

### 30-Day Action Plan
1. [specific action from synthesis]
2. [specific action from synthesis]
3. [specific action from synthesis]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.