agentleFS
gokulsvisiongokulsvision/Crewm8-Social-Media-Manager-Skill-Graph/skills/research/social-profile-discover/SKILL.md

social-profile-discover

Skill17 starsChanged 7 months agoMITView on GitHub

Discover social media profiles for a person or company using search engines, platform-specific searches, and website extraction — returns canonical profile URLs across LinkedIn, X, Instagram, Facebook, TikTok, and YouTube.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before running prospect-social-audit on a new company

    line 30
  2. Distinctive:

    All target platforms are searched (or explicitly skipped)

    line 192

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Social Profile Discover

Systematically discover social media profiles for a person or company. The output feeds directly into prospect-social-audit for evaluation and CRM enrichment.

Purpose

Finding social profiles manually is inefficient and error-prone. This skill runs structured searches across platforms, extracts canonical profile URLs, and separates company profiles from personal profiles — so downstream skills get clean, verified data.

When to Use

  • Before running prospect-social-audit on a new company
  • Enriching a CRM contact with their social presence
  • Finding where a competitor or peer is active
  • Building a target account list for social engagement
  • Verifying that a discovered profile is actually the right person/company

Inputs Required

  • Name (person name or company name — required)
  • Company or context (for disambiguation — "this person works at X")
  • Website (optional — the best source of social links is the company's own footer)
  • Location (optional — helps disambiguate common names)
  • Target platforms (default: all — LinkedIn, X, Instagram, Facebook, TikTok, YouTube)

Procedure

Step 1: Check the website first

The company's own website is the most reliable source. Social icon links are usually in the footer, header, or Contact page.

firecrawl scrape "{website}" --format markdown

Extract all social URLs from href attributes:

  • linkedin.com/company/{slug}
  • linkedin.com/in/{slug} (personal)
  • instagram.com/{handle}
  • facebook.com/{page}
  • x.com/{handle} or twitter.com/{handle}
  • tiktok.com/@{handle}
  • youtube.com/@{handle} or youtube.com/channel/{id}

Step 2: Search per platform

For each platform not found on the website, search systematically:

LinkedIn (person):

firecrawl search "site:linkedin.com/in \"{name}\" {company} {title}" --limit 5

LinkedIn (company):

firecrawl search "site:linkedin.com/company \"{company_name}\" {location}" --limit 5

X / Twitter:

firecrawl search "site:x.com OR site:twitter.com \"{name}\" {company}" --limit 5

Instagram:

firecrawl search "site:instagram.com \"{company_name}\" {location}" --limit 5

Facebook (business page):

firecrawl search "site:facebook.com \"{company_name}\" {location}" --limit 5

TikTok:

firecrawl search "site:tiktok.com \"{name_or_company}\"" --limit 5

YouTube:

firecrawl search "site:youtube.com \"{company_name}\" channel" --limit 5

Step 3: Verify each candidate profile

For each potential profile match, verify:

  1. Name match: does the display name contain the expected name/company?
  2. Bio/description match: does the bio mention the expected industry, location, or company?
  3. Activity match: is the profile recently active (posts in last 90 days)?
  4. Follower match: is the follower count plausible for this person/company?

Firecrawl scrape the profile page to extract bio and recent activity:

# For LinkedIn profiles (may return limited data for non-public profiles)
firecrawl scrape "{profile_url}" --format markdown

# For Instagram
firecrawl scrape "{instagram_url}" --format markdown

# For X
firecrawl scrape "{x_url}" --format markdown

Step 4: Distinguish company vs. personal profiles

Profile TypeIndicators
Company pageMultiple employees listed, "company" in URL, industry description
Personal profileSingle person, job titles, "in" in LinkedIn URL, individual posts
Creator/business accountIndividual posting as a brand, often solo founders

Step 5: Compile canonical URLs

Return exactly one canonical URL per platform per entity (company vs person), or "Not found." Prefer:

  • Website footer links > platform search results > search engine results
  • Verified matches > unverified candidates
  • Active profiles > dormant profiles

Output Format

# Social Profile Discovery: {Name}

## Source Summary
- **Website checked:** {url} (socials found: {count})
- **Platforms searched:** {platforms}
- **Profiles found:** {found}/{total searched}

## Company Profiles
| Platform | URL | Verified? | Source |
|----------|-----|-----------|--------|
| LinkedIn | {url} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |
| Instagram | @{handle} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |
| X | @{handle} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |
| Facebook | {url} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |
| TikTok | @{handle} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |
| YouTube | {url} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |

## Person Profiles ({contact_name} — if sought)
| Platform | URL | Verified? | Source |
|----------|-----|-----------|--------|
| LinkedIn | {url} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |
| X | @{handle} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |
| Instagram | @{handle} or "Not found" | {Yes/Probable/Unverified} | {Website / Search} |

## Unverified Candidates (for manual review)
- {url} — {why unsure} — {recommendation}

## JSON Export (for CRM)
```json
{
  "companySocials": {
    "linkedin": "...",
    "facebook": "...",
    "instagram": "...",
    "twitter": "...",
    "youtube": "...",
    "tiktok": "..."
  },
  "contactSocials": {
    "linkedin": "...",
    "twitter": "...",
    "instagram": "..."
  }
}

## Done Criteria

The skill is complete when:
1. All target platforms are searched (or explicitly skipped)
2. Each found profile has a verification status (Yes/Probable/Unverified)
3. Company and personal profiles are clearly separated
4. JSON export is ready for CRM enrichment
5. Unverified candidates are listed with recommendations

## Pitfalls

- Assuming the first search result is correct (verify before accepting)
- Mixing company and personal profiles (LinkedIn URLs: /company/ vs /in/)
- Missing profiles because the handle doesn't match the company name (always check the website footer)
- Rate-limiting: Firecrawl and platform search may throttle (space searches out)
- Firecrawl sometimes returns limited Markdown from LinkedIn (restricted by auth walls)

## Verification

For each "Verified: Yes" profile URL, open the link. Does the profile clearly belong to the target person/company? If you hesitate, mark it as "Probable" or "Unverified."

## See Also

- **references/platform-specs.md** — character limits, aspect ratios, benchmarks
- **references/tool-requirements.md** — API auth options, tool paths per platform
- **skills/research/prospect-social-audit/SKILL.md** — evaluates discovered profiles

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.