Index of every page on this site: llms.txt
All skills
alptugharun avatar

/local-business-intelligence

@2b12408
Run it yourself

Turns permitted Google Maps, Places, Places Aggregate and user-owned Business Profile signals into market, content, creator-location, sponsorship and agency insights. Use for local-business research, local content gaps, venue scouting, market-density questions, GBP performance analysis or human-reviewed local partnership discovery.

  • 1 file
  • 3.9 KB
  • MIT
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/alptugharun/ai-social-media-toolkit/local-business-intelligence

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈91 tokens for metadata: the name and description. ≈887 when used: this file.

Description uses 4.5% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈363 characters, or 4.5%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Local Business Intelligence

Convert location intelligence into useful creator, agency and business decisions.

This skill is a workflow layer, not a scraping engine.

Required References

Read:

  • references/EVIDENCE-POLICY.md
  • references/MAPS-AI-OPPORTUNITY-PLAYBOOK.md

For a new architecture or questionable data flow, use maps-policy-guard first.

Modes

Market Density / Expansion

Use aggregate or permitted live data to answer:

  • How dense is this category in the target area?
  • How does one area compare with another?
  • Where does a service appear under-represented?
  • Which hypotheses should be investigated further?

Prefer Places Aggregate API for density/count questions.

Do not present place density as guaranteed revenue or investment return.

Live Place Discovery

Use live place search for a narrow, user-requested task.

Examples:

  • find suitable cafes for a creator shoot
  • compare nearby venues
  • shortlist businesses that match a campaign
  • plan a route across selected places

Return only what is necessary for the task.

Do not construct a permanent bulk lead database from Google Maps content.

Owned Business Profile Performance

When the user has authorized access to managed locations, analyze:

  • Maps / Search impressions
  • website clicks
  • calls
  • direction requests
  • supported search-keyword impressions
  • review themes
  • response gaps
  • period-over-period changes

Separate observed metrics from interpretation.

Review Intelligence

For authorized / user-provided reviews:

  • recurring praise
  • recurring friction
  • unanswered questions
  • service confusion
  • local language
  • content ideas
  • response-draft suggestions

Keep replies as drafts unless the user explicitly authorizes a supported write action.

Creator Location Scout

Inputs:

  • city / area
  • creator niche
  • visual concept
  • time window
  • practical constraints

Output:

  • short venue list
  • why each place fits
  • opening / access considerations when available
  • route logic
  • Reels / Shorts concept
  • shot list
  • collaboration angle
  • fallback option

Local Sponsor-Fit Shortlist

Inputs:

  • creator audience
  • niche
  • campaign idea
  • geography
  • brand exclusions

Output:

  • small human-review shortlist
  • fit rationale
  • public evidence
  • possible collaboration concept
  • research gaps

Do not auto-send mass outreach.

Local Content Gap Engine

Combine first-party / authorized signals such as:

  • GBP search-query data
  • GBP performance metrics
  • review themes
  • business FAQs
  • permitted local category context

Create:

  • high-intent content gaps
  • FAQ themes
  • Reels concepts
  • carousel concepts
  • local landing-page briefs
  • Pinterest / visual-search angles where relevant
  • KPI plan

Evidence Labels

Every important claim should be labeled implicitly or explicitly as:

  • Observed
  • Inferred
  • Recommended

Output

Local Business Intelligence Brief

Objective

  • Business / creator:
  • Geography:
  • Mode:
  • Time window:

Evidence

Signal Source Date Observation Confidence

Findings

Prioritize actionable findings.

Recommended Tests

Test Why Effort KPI

Content / Campaign Opportunities

Only when relevant.

Data & Policy Check

  • source:
  • persistence:
  • authorization:
  • human approval required:
  • policy status:

Next Decision

Choose the smallest useful next action.

Core Principle

Use local data to make a better decision, not to manufacture a larger database.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 2b12408. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 days ago.

Activeupdated 2 months ago
metadata
{
  "version": "0.1.0",
  "author": "Alptuğ Harun"
}

README badge

README badge for alptugharun/ai-social-media-toolkit/local-business-intelligence