Linkedin Marketing
Writes LinkedIn posts and comments from 16 hook formulas, with approval before publishing
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 31, 2026
- Environment
- Claude Code 2.x (agent harness)
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 31, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Cloned the repo to /tmp and installed it into a throwaway HOME ($(mktemp -d)), confirming SKILL.md lands at ~/.claude/skills/linkedin-marketing/SKILL.md (548K after dropping .git and the duplicated .codex-marketplace tree); frontmatter parses with name+description, and all six spot-checked referenced paths (references/voice-rules.md, hook-formulas.md, algorithm-heuristics.md, lib/url_parser.py, lib/publora_client.py, skills/linkedin-post-writer/SKILL.md) returned HTTP 200. Security scan found no curl|sh, no base64 blobs, and only two outbound hosts in lib/ (api.publora.com, api.apify.com) reading only its own four declared env vars; the one subprocess.run is the opt-in LINKEDIN_SKILLS_CUSTOM_POSTER path. For output I wrote one brief (3-person SaaS replaces a $2,258/mo support stack with $91.30 of API calls, one script wrongly auto-closed 12 refund tickets, goal=saves) and produced two posts: a baseline written cold, and one following root SKILL.md -> linkedin-post-writer -> goal-table -> F7 Odd-Precision Money Ledger; scripted diff showed baseline 2 em dashes / 5 hashtags / 2 numeric tokens / "What do you think?" closer / failure buried in paragraph 5, versus skill 0 em dashes / 1 hashtag / 14 numeric tokens / failure in the first 3 lines / unrounded line-item ledger. Deductions: the skill draft came out 1,318 chars against its own 900-1,300 sweet spot, F7 forced me to invent the $77.42+$13.88 split the skill itself warns against faking, skills/linkedin-humanizer/sub-skills/detector-tester.md line 63 hardcodes /home/sbulaev/p/linkedin-skills, plugin.json says 10 skills while README and the tree show 11, and the "9.4x baseline" / "8.5x" engagement multipliers are presented as verified but I could not check them.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What Linkedin Marketing does
An umbrella skill that routes LinkedIn work to 11 sub-skills: post writing from 16 named hook formulas, comment and reply drafting from a post URL, an AI-tell humanizer, hook extraction, weekly content planning, profile rewriting, and engager analytics. Triggers when you ask to write or audit a LinkedIn post, draft a comment on a LinkedIn URL, strip AI tells from a draft, or plan a week of LinkedIn content. Drafting works with no setup; publishing needs a Publora API key and reading post bodies needs an Apify token.
How to install Linkedin Marketing
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Linkedin Marketing
-
/linkedin-marketingWrites LinkedIn posts and comments from 16 hook formulas, with approval before publishing
It also activates on plain-language prompts like these:
-
Write a viral LinkedIn post about our launch -
Audit this draft against LinkedIn's 2026 algorithm -
Draft a reply comment for this LinkedIn post
Frequently asked questions
- Is the Linkedin Marketing skill free?
- Yes. The skill itself is free from sergebulaev/linkedin-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Linkedin Marketing work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Cloned the repo to /tmp and installed it into a throwaway HOME ($(mktemp -d)), confirming SKILL.md lands at ~/.claude/skills/linkedin-marketing/SKILL.md (548K after dropping .git and the duplicated .codex-marketplace tree); frontmatter parses with name+description, and all six spot-checked referenced paths (references/voice-rules.md, hook-formulas.md, algorithm-heuristics.md, lib/url_parser.py, lib/publora_client.py, skills/linkedin-post-writer/SKILL.md) returned HTTP 200. Security scan found no curl|sh, no base64 blobs, and only two outbound hosts in lib/ (api.publora.com, api.apify.com) reading only its own four declared env vars; the one subprocess.run is the opt-in LINKEDIN_SKILLS_CUSTOM_POSTER path. For output I wrote one brief (3-person SaaS replaces a $2,258/mo support stack with $91.30 of API calls, one script wrongly auto-closed 12 refund tickets, goal=saves) and produced two posts: a baseline written cold, and one following root SKILL.md -> linkedin-post-writer -> goal-table -> F7 Odd-Precision Money Ledger; scripted diff showed baseline 2 em dashes / 5 hashtags / 2 numeric tokens / "What do you think?" closer / failure buried in paragraph 5, versus skill 0 em dashes / 1 hashtag / 14 numeric tokens / failure in the first 3 lines / unrounded line-item ledger. Deductions: the skill draft came out 1,318 chars against its own 900-1,300 sweet spot, F7 forced me to invent the $77.42+$13.88 split the skill itself warns against faking, skills/linkedin-humanizer/sub-skills/detector-tester.md line 63 hardcodes /home/sbulaev/p/linkedin-skills, plugin.json says 10 skills while README and the tree show 11, and the "9.4x baseline" / "8.5x" engagement multipliers are presented as verified but I could not check them.
- What is the Linkedin Marketing SkillProof Score?
- 8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install Linkedin Marketing?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Linkedin Marketing with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.