Agent skill

Handle Linkedin Profile View Signal

by swan-gtm in swan-gtm/gtm-skills

A skill your agent uses when a profile-view webhook (e.g. An agent skill from swan-gtm/gtm-skills.

MITAuto-check passedSales & Support

Install Handle Linkedin Profile View Signal

skills CLI
$ npx skills add swan-gtm/gtm-skills --skill handle-linkedin-profile-view-signal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install swan-gtm/gtm-skills handle-linkedin-profile-view-signal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ariel-cohen/handle-linkedin-profile-view-signal .claude/skills/handle-linkedin-profile-view-signal && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
handle-linkedin-profile-view-signal
GitHub stars
172
Token cost
~3.2k tokens
SKILL.md length
1,556 words
Files
4 (incl. references)
Skills in repo
32
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a profile-view webhook (e.g. An agent skill from swan-gtm/gtm-skills.

  • Works in 9 steps: Parse & Validate → 5 — Idempotency (Before Any Enrichment) → Resolve Viewer Identity & Company… → …
  • A profile-view webhook (e.g
  • SKILL.md covers Template placeholders and What good looks like
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Handle Linkedin Profile View Signal is an agent skill from swan-gtm/gtm-skills. Use this skill when a profile-view webhook (e.g. LeadShark) fires for a new view on a team member's LinkedIn profile. It resolves the viewer's identity and company, applies dedup, internal, relationship, and ICP gates, and routes qualified viewers into the MQL pipeline — treating a profile view exactly like a website visit. The CRM is never polluted: only fully resolved, ICP-matched viewers reach a CRM write.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/customization-checklist.md`, `references/installation-getting-the-signal-flowing.md` and `references/webhook-payload-reference-leadshark-new-profile-visit.md`).

It sits in Sales & Support, covering Resume and CV writing and Webhooks. The repository describes itself as: Open, production-grade GTM skills for AI agents. The licence is MIT.

When your agent uses it

  • A profile-view webhook (e.g
  • Tasks that involve Resume and CV writing
  • Tasks that involve Webhooks

Example prompts

  • “s LinkedIn profile. It resolves the viewer”
  • “/handle-linkedin-profile-view-signal”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Parse & Validate
  2. 5 — Idempotency (Before Any Enrichment)
  3. Resolve Viewer Identity & Company (Mandatory)
  4. Internal Check
  5. CRM Relationship Check (Mirror Your Website-Visit Skill)
  6. ICP Check
  7. Log Signal & Create/Update Company + Contact in {{CRM}}
  8. Classify Intent & Route to Sub-Skills
  9. Outcome Post to {{NOTIFICATIONS_CHANNEL}}

What it can do on your machine

Read from SKILL.md and the folder at commit 67abd04. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Handle Linkedin Profile View Signal loads about 3.2k tokens when it runs, and up to ~5.6k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 1,556 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from swan-gtm/gtm-skills at commit 67abd04, republished under its MIT licence (© swan-gtm). 1,556 words, ~3,234 tokens.

Download SKILL.mdSave it as .claude/skills/handle-linkedin-profile-view-signal/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
handle-linkedin-profile-view-signal
description
Use this skill when a profile-view webhook (e.g. LeadShark) fires for a new view on a team member's LinkedIn profile. It resolves the viewer's identity and company, applies dedup, internal, relationship, and ICP gates, and routes qualified viewers into the MQL pipeline — treating a profile view exactly like a website visit. The CRM is never polluted: only fully resolved, ICP-matched viewers reach a CRM write.
title
Handle LinkedIn profile view signal
category
Signals

Template placeholders

Replace every {{...}} before enabling. See the setup checklist reference for the full setup list.

  • {{PROFILE_OWNER}} — Full name of the team member whose LinkedIn is tracked (e.g. "Jane Doe")
  • {{INTERNAL_DOMAINS}} — Your own company domain(s) (e.g. "acme.com")
  • {{NOTIFICATIONS_CHANNEL}} — Slack channel reference for outcome/debug posts
  • {{ENRICHMENT_TOOL}} — Primary contact-enrichment tool available to the agent
  • {{FALLBACK_SCRAPER}} — Fallback LinkedIn profile scraper (e.g. an Apify actor)
  • {{CRM}} — Your CRM (e.g. HubSpot)
  • {{CRM_HYGIENE_SKILL}} — Sub-skill reference: how to create/update companies & contacts in your CRM
  • {{EXISTING_RELATIONSHIP_SKILL}} — Sub-skill reference: handling accounts with an open/lost deal
  • {{HIGH_INTENT_SKILL}} — Sub-skill reference: potential-MQL scoring & routing
  • {{AWARENESS_SKILL}} — Sub-skill reference: net-new ICP awareness logging
  • {{TIER_SCALE}} — Your lead-score tiers, low→high (default: Bronze / Silver / Gold / Diamond)
  • {{SOLE_SIGNAL_CAP_TIER}} — Max tier when a profile view is the only 1st-party signal (default: Silver)
  • {{COOLDOWN_WINDOW}} — Same-session dedup window (default: 1 hour)
Overview

This skill fires when your profile-view tracker (e.g. LeadShark) detects a new view on {{PROFILE_OWNER}}'s LinkedIn profile. Goal: behave exactly like a website visit — resolve the viewer, run the same ICP gate, register them as a known contact only when they pass, and feed them into the MQL pipeline.

The golden rule: the CRM is never polluted. Only a viewer who is identified + company-resolved + not-internal + not-customer + ICP-matched ever reaches a CRM write. Everyone else is silently discarded or logged to org memory only.

The webhook trigger handles only one thing: ignoring events that are not new.profile.visit. All logic lives here.

Channel rule: When outreach is triggered by a LinkedIn profile view signal, keep it LinkedIn-only. Do not create email steps. The contact came to you via LinkedIn — stay on that channel.


Step 1 — Parse & Validate

The payload arrives as text. Extract the fields listed in references/webhook-payload.md. Key ones:

  • data.profile_owner — confirm this is {{PROFILE_OWNER}}; if not, stop silently.
  • data.lead.is_anonymous — if true, stop immediately and silently. No enrichment, no CRM writes, no memory writes, no channel post. Anonymous viewers (LinkedIn Premium private mode) are fully discarded.
  • data.lead.title is the LinkedIn headline — it often contains no company. Never treat it as a company name.
  • data.visit.id is a stable unique token per visit; data.lead.actor_id identifies the person across visits.

Step 1.5 — Idempotency (Before Any Enrichment)

Profile-view trackers emit multiple visit records for a single viewing session — same person, same actor_id, different visit.id each time. Run two checks before paying for enrichment:

Read the org-level memory note "Profile Views — {{PROFILE_OWNER}} — Processed Visit IDs" (create it if it doesn't exist). Each entry stores: visit.id | actor_id | timestamp.

Check 1 — Exact retry guard: If data.visit.id is already in the note → duplicate webhook redelivery → stop silently. No enrichment, no CRM, no memory writes, no channel post.

Check 2 — Per-person session cooldown: If data.lead.actor_id appears in the note with a timestamp within the last {{COOLDOWN_WINDOW}} → same viewing session split into multiple events → stop silently.

Otherwise: Append data.visit.id | data.lead.actor_id | data.visit_timestamp to the note and continue. Keep only the most recent ~200 entries.

Critical: A genuine repeat view from the same person outside the cooldown window has the same actor_id but passes both checks and re-scores as a stronger signal. This is intentional — the cooldown only collapses rapid same-session duplicates, never real repeat intent.


Step 2 — Resolve Viewer Identity & Company (Mandatory)

Identifying the person is not the same as resolving the company. You must have both before proceeding.

Do NOT infer the company from the LinkedIn headline. Headlines like "Product | Strategist | Building 0→1" are not company names.

  1. Run {{ENRICHMENT_TOOL}} on linkedin_username (or linkedin_url) to retrieve: current company name, company domain, confirmed job title, and country/location.
  2. If {{ENRICHMENT_TOOL}} does not return a confident company name + domain — even if it identified the person — you MUST run {{FALLBACK_SCRAPER}} on the profile URL to obtain the current company, domain, and country. The fallback is required here, not optional. A guessed company is worse than UNRESOLVED.
  3. You must exit this step with: viewer full name, confirmed title, company name, company domain (both required), country.

Exit condition — UNRESOLVED: If after both tools you still cannot confidently determine a company name + domain:

  • Set outcome = UNRESOLVED
  • Append the raw data (name, title, linkedin_url, visit.id, timestamp) to the org memory note "Profile Views — {{PROFILE_OWNER}} — Unresolved Viewers"
  • Do NOT write anything to {{CRM}}, account memory, or the channel
  • Stop.

Step 3 — Internal Check

If the resolved domain is {{INTERNAL_DOMAINS}} or any other internal domain → stop silently. No CRM, no memory, no channel post.


Step 4 — CRM Relationship Check (Mirror Your Website-Visit Skill)

Look up the company in your workspace + {{CRM}}:

  • Active partner → stop silently. No CRM writes, no scoring, no channel post. Partner accounts are managed by their owner — do not create noise.
  • Current customer (Closed Won) → set outcome = EXISTING CUSTOMER. Do NOT create or update any CRM records. Jump to Step 8.
  • Active deal or Closed-Lost → open the {{EXISTING_RELATIONSHIP_SKILL}} sub-skill and follow it. After it returns, jump to Step 8 with outcome = EXISTING RELATIONSHIP.
  • No existing relationship (net-new) → continue to Step 5.

Step 5 — ICP Check

Compare the company against your ICP segments.

  • Not ICP → set outcome = NOT ICP. Do NOT create or update any CRM records. Do NOT write to account memory. Jump to Step 8.
  • ICP match → continue to Step 6.

Show full SKILL.md (733 more words)Show less
Step 6 — Log Signal & Create/Update Company + Contact in {{CRM}}

⛔ Hard gate — read before doing anything in this step:

Do NOT create or update ANY CRM company or contact, and do NOT write to account memory, unless ALL of the following are true: (a) the viewer is not anonymous (b) the company was confidently resolved to a real domain in Step 2 (c) the domain is not internal (Step 3 passed) (d) the account is not an existing customer (Step 4 passed) (e) the account passed the ICP check in Step 5

If any condition fails, skip this step entirely — no CRM writes of any kind.

If all conditions are met:

Log to account memory:

[PROFILE VIEW — {{PROFILE_OWNER}}] [date] — Visit ID: [visit.id]
Viewer: [full name], [title]
LinkedIn: [linkedin_url]
Connection status: [connection_status]
Company: [company name] ([domain])
Country: [country]
Repeat views: [count of prior profile-view entries in this account's memory + 1]

Update the account's state summary in your workspace.

Create/update Company and Contact in {{CRM}} following the {{CRM_HYGIENE_SKILL}} sub-skill:

  • Create/update the company record (associate the LinkedIn company page if found)
  • Create/update a Contact record for the viewer: name, title, linkedin_url, company, country — even without an email. Associate immediately with the company.
  • Add a CRM note on the contact:
    LinkedIn profile view — {{PROFILE_OWNER}}
    • Viewed {{PROFILE_OWNER}}'s LinkedIn profile on [date]
    • Connection status: [connection_status]
    • Visit ID: [visit.id]
    • Repeat view count from this company: [n]
  • Do not invent custom CRM properties to record the visit — the note above is sufficient. Only use properties that already exist in your CRM.

Step 7 — Classify Intent & Route to Sub-Skills

Persona gate (evaluate first — overrides all routing below):

Before routing, classify the viewer's persona:

  • Strong buyer persona: CRO, VP/Head of Sales, VP/Head of Marketing, CMO, CEO, Co-founder, RevOps Lead, GTM Engineer, Growth Lead, Head of Demand Gen, Agency Owner, or equivalent leadership with buying authority for your product. (Adjust this list to your ICP's buying committee.)
  • Weak/non-buyer persona: individual contributor (IC), Support, Finance, HR, Ops, Analyst, IT/Network Engineer, or any junior title without buying authority.

If the viewer is a weak/non-buyer persona: Route to {{AWARENESS_SKILL}} regardless of repeat-view count, connection status, or stacked signals from prior visits. Do NOT route to {{HIGH_INTENT_SKILL}}. Pass the note: "Do NOT send a connection request from {{PROFILE_OWNER}} — viewer is not a buying persona." Stacked-signal tier lifts do not apply; the account stays at {{SOLE_SIGNAL_CAP_TIER}} or below.

High intent → open {{HIGH_INTENT_SKILL}} when the viewer is a strong buyer persona AND ANY of:

  • Viewer is a strong buyer persona (as defined above)
  • Repeat view: 2+ profile-view entries in account memory from this person or company in the past 30 days
  • connection_status = Connected AND persona is at least medium strength

Awareness → open {{AWARENESS_SKILL}} when:

  • Viewer is a weak/non-buyer persona, OR
  • First view from this company AND viewer is a junior/medium persona

When invoking {{AWARENESS_SKILL}} for a weak persona, pass the explicit note: "Do NOT send a connection request from {{PROFILE_OWNER}} — viewer is not a buying persona."

Sole-signal cap: When calling either sub-skill, pass the explicit instruction: "Profile view cap: if this LinkedIn profile view is the only 1st-party signal on this account (no website visit, no chatbot conversation, no reply to outreach, no prior meeting), score must not exceed {{SOLE_SIGNAL_CAP_TIER}}. Do not score higher on a profile view alone. Additional signals arriving later can lift this cap."

When calling either sub-skill, pass this context:

  • Signal type: "LinkedIn profile view on {{PROFILE_OWNER}}"
  • Repeat view count
  • Connection status
  • Viewer name, title, LinkedIn URL
  • "Vendor/partner check already completed — not a vendor. ICP check already completed — is ICP. Company and contact already created/updated in {{CRM}}."

The sub-skills run lead scoring, tier assignment, CRM sync, buying-committee enrichment, outreach drafting, and alerts. After they return, continue to Step 8.


Step 8 — Outcome Post to {{NOTIFICATIONS_CHANNEL}}

Post to {{NOTIFICATIONS_CHANNEL}} only for these outcomes:

  • SCORED
  • NOT ICP
  • EXISTING CUSTOMER
  • EXISTING RELATIONSHIP

Do NOT post for: ANONYMOUS (fully silent), UNRESOLVED (not actionable), INTERNAL (fully silent), or duplicate stops.

Post fires after routing and scoring has returned, so the tier is always known.

Message format:

👤 [Full Name] — [title]
Company: [company name] ([domain]) | [country]
Connection: [connection_status]
Repeat views: [n] (this company)
LinkedIn: [linkedin_url]

Outcome: [one of]
  SCORED — [tier from {{TIER_SCALE}}]
  EXISTING CUSTOMER — logged, no scoring
  EXISTING RELATIONSHIP — routed to existing-relationship sub-skill
  NOT ICP — no CRM writes, no scoring

What we did: [one line — e.g. "Contact created in CRM, routed to high-intent
sub-skill, scored Gold, alert sent to the MQL channel"]

Execution: [link]

What good looks like

A great run means every qualified viewer lands in the CRM fully resolved — real company name and domain, never guessed from a headline — while duplicates, anonymous views, internal views, and non-ICP viewers die silently. Weak personas never trigger connection requests, a lone profile view never scores above the sole-signal cap, and the channel post tells the team in one glance who viewed, the outcome, and exactly what was done.

Mediocre looks like: CRM pollution from headline-guessed companies, repeat-session spam posts, Gold tiers on a single profile view, or noisy posts for outcomes that should be silent.

© swan-gtm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/ariel-cohen/handle-linkedin-profile-view-signal of swan-gtm/gtm-skills.

  • SKILL.md
  • references/customization-checklist.md
  • references/installation-getting-the-signal-flowing.md
  • references/webhook-payload-reference-leadshark-new-profile-visit.md

Open the folder on GitHubat commit 67abd04

Compare with similar skills

Handle Linkedin Profile View Signal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Handle Linkedin Profile View Signal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Handle Linkedin Profile View Signal this skillswan-gtm/gtm-skills172—~3.2kAutomated safety check: PassMIT
Upwork Proposal Writerabullaisi/upwork-skills1141 repos~3kAutomated safety check: PassMIT
Account Contact Shortlistexplorium-ai/gtm-skills185—~1.6kAutomated safety check: PassMIT
Hubspot Integrationdavila7/claude-code-templates33k4 repos~265Automated safety check: PassMIT
Company Researchliangdabiao/exa-research-mcp-skill110—~452Automated safety check: PassNone
Enrich Contactexplorium-ai/gtm-skills185—~1kAutomated safety check: PassMIT

Similar skills

  • Upwork Proposal Writer

    abullaisi/upwork-skills

    Draft or review an Upwork proposal (cover letter) using the five-move method extracted from a Top Rated Plus freelancer's winning proposals, corrected for the AI era.

    114 GitHub starsUsed in 1 repo~3k tokens
    Sales & SupportAuto-check passed
  • Account Contact Shortlist

    explorium-ai/gtm-skills

    Contact data skill for Claude Code and Codex: build a ranked shortlist of decision-makers and contacts at a target company for outbound prospecting, deal acceleration, or renewal/expansion plays.

    185 GitHub stars~1.6k tokensUpdated 3 days ago
    Sales & SupportAuto-check passed
  • Hubspot Integration

    davila7/claude-code-templates

    Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects.

    33k GitHub starsUsed in 4 repos~265 tokens
    Sales & SupportAuto-check passed
  • Company Research

    liangdabiao/exa-research-mcp-skill

    Company research using Exa search. An agent skill from liangdabiao/exa-research-mcp-skill.

    110 GitHub stars~452 tokensUpdated 2 mo ago
    Sales & SupportAuto-check passed
  • Enrich Contact

    explorium-ai/gtm-skills

    Contact enrichment skill for Claude Code and Codex: look up a B2B prospect's full professional profile including work email, phone number, LinkedIn profile, title, seniority, department, and company…

    185 GitHub stars~1k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed
  • Linkedin

    unifapi-agent/agents

    When a workflow needs public LinkedIn data through UnifAPI — company pages, follower/employee counts, open jobs and job-count, member insights, people, posts, or engagement.

    589 GitHub stars~1.9k tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed

More from swan-gtm/gtm-skills

All 32 skills in this repo
  • Revops Revenue Planning

    swan-gtm/gtm-skills

    Annual and quarterly revenue plan construction, top-down vs bottoms-up reconciliation, plan versioning, stretch goal handling, and FP&A-RevOps collaboration for B2B revenue teams.

    172 GitHub stars~7.2k tokensUpdated 3 days ago
    Auto-check passed
  • AI Personalization Prompts

    swan-gtm/gtm-skills

    A skill your agent uses when setting up AI-powered personalization, building Clay or lemlist workflows, or automating prospect research — 6 AI personalization prompts (lemlist style) plus 2 email…

    172 GitHub stars~653 tokensUpdated 3 days ago
    Auto-check passed
  • Audience Icp Filter

    swan-gtm/gtm-skills

    A skill your agent uses when a list of people already exists and someone needs to know who on it is worth contacting — event or webinar attendees, registrants, a prospecting export, a CRM segment, a…

    172 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed
  • Brand Mention Monitor

    swan-gtm/gtm-skills

    A skill your agent uses when you need to know what people are saying about a brand across the web and social — "monitor brand mentions", "what are people saying about [brand] this week", "run a…

    172 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed
  • Bridge Before Cold

    swan-gtm/gtm-skills

    Use this skill before staging a prospect and before drafting any first touch, when a segment has gone silent, and when deciding whether an account is genuinely cold.

    172 GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed
  • Champion Move Detection

    swan-gtm/gtm-skills

    Use this skill on a monthly cadence to detect champions and heavy users of your paying customers who changed jobs, verify the move against live LinkedIn data, score the new company, and surface…

    172 GitHub stars~5k tokensUpdated 3 days ago
    Auto-check passed

Questions about Handle Linkedin Profile View Signal

What does Handle Linkedin Profile View Signal do?

A skill your agent uses when a profile-view webhook (e.g. An agent skill from swan-gtm/gtm-skills. Handle Linkedin Profile View Signal is an agent skill from swan-gtm/gtm-skills.g.

When should I use Handle Linkedin Profile View Signal?

Handle Linkedin Profile View Signal fits situations like: A profile-view webhook (e.g; tasks that involve Resume and CV writing; tasks that involve Webhooks.

How do I install Handle Linkedin Profile View Signal in Claude Code?

Run `npx skills add swan-gtm/gtm-skills --skill handle-linkedin-profile-view-signal -a claude-code`. Or copy the skill folder (skills/ariel-cohen/handle-linkedin-profile-view-signal in swan-gtm/gtm-skills) into .claude/skills/handle-linkedin-profile-view-signal in your project. Claude Code loads it when a task matches its description.

How do I install Handle Linkedin Profile View Signal in Codex?

Run `npx skills add swan-gtm/gtm-skills --skill handle-linkedin-profile-view-signal -a codex`. Or copy the skill folder (skills/ariel-cohen/handle-linkedin-profile-view-signal in swan-gtm/gtm-skills) into .agents/skills/handle-linkedin-profile-view-signal in your project. Codex loads it when a task matches its description.

Can I use Handle Linkedin Profile View Signal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swan-gtm/gtm-skills --skill handle-linkedin-profile-view-signal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/handle-linkedin-profile-view-signal, .gemini/skills/handle-linkedin-profile-view-signal, .github/skills/handle-linkedin-profile-view-signal and .opencode/skills/handle-linkedin-profile-view-signal in your project.

What does Handle Linkedin Profile View Signal need to run?

SKILL.md names no scripts, command-line tools or credentials: Handle Linkedin Profile View Signal is instructions for the agent only.

Does Handle Linkedin Profile View Signal access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Handle Linkedin Profile View Signal safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Handle Linkedin Profile View Signal use?

Handle Linkedin Profile View Signal is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Handle Linkedin Profile View Signal use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Handle Linkedin Profile View Signal?

Skills that share tags, products or a category with Handle Linkedin Profile View Signal: Upwork Proposal Writer (abullaisi/upwork-skills, 114 stars), Account Contact Shortlist (explorium-ai/gtm-skills, 185 stars), Hubspot Integration (davila7/claude-code-templates, 33k stars) and Company Research (liangdabiao/exa-research-mcp-skill, 110 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Handle Linkedin Profile View Signal?

swan-gtm (a GitHub organization) maintains it in swan-gtm/gtm-skills, which has 172 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 8, 2026.

Source: swan-gtm/gtm-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.