Social
coreyhaines31/marketingskills
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.
Agent skill
Playbook Linkedin Engagement
by growthenginenowoslawski in growthenginenowoslawski/coldoutboundskills
Turn the people who like and comment on a source account's LinkedIn posts (a competitor, or one of the client's own customers) into ICP-filtered prospect rows, with an optional copy-ready…
Install Playbook Linkedin Engagement
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills playbook-linkedin-engagement --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/playbooks/playbook-linkedin-engagement .claude/skills/playbook-linkedin-engagement && rm -rf skills-srcUse ~/.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/
Install the "playbook-linkedin-engagement" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-linkedin-engagement into .claude/skills/playbook-linkedin-engagement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "playbook-linkedin-engagement", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-linkedin-engagementType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills playbook-linkedin-engagement --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/playbooks/playbook-linkedin-engagement .agents/skills/playbook-linkedin-engagement && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "playbook-linkedin-engagement" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-linkedin-engagement into .agents/skills/playbook-linkedin-engagement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "playbook-linkedin-engagement", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills playbook-linkedin-engagement --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/playbooks/playbook-linkedin-engagement .cursor/skills/playbook-linkedin-engagement && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "playbook-linkedin-engagement" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-linkedin-engagement into .cursor/skills/playbook-linkedin-engagement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "playbook-linkedin-engagement", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/growthenginenowoslawski/coldoutboundskills.git --path skills/playbooks/playbook-linkedin-engagement--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills playbook-linkedin-engagement --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/playbooks/playbook-linkedin-engagement .gemini/skills/playbook-linkedin-engagement && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "playbook-linkedin-engagement" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-linkedin-engagement into .gemini/skills/playbook-linkedin-engagement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "playbook-linkedin-engagement", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install growthenginenowoslawski/coldoutboundskills playbook-linkedin-engagementInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/playbooks/playbook-linkedin-engagement .github/skills/playbook-linkedin-engagement && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "playbook-linkedin-engagement" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-linkedin-engagement into .github/skills/playbook-linkedin-engagement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "playbook-linkedin-engagement", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills playbook-linkedin-engagement --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/playbooks/playbook-linkedin-engagement .opencode/skills/playbook-linkedin-engagement && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "playbook-linkedin-engagement" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-linkedin-engagement into .opencode/skills/playbook-linkedin-engagement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "playbook-linkedin-engagement", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
playbook-linkedin-engagement- GitHub stars
- 753
- Token cost
- ~1.5k tokens
- SKILL.md length
- 725 words
- Files
- 3
- Skills in repo
- 49
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turn the people who like and comment on a source account's LinkedIn posts (a competitor, or one of the client's own customers) into ICP-filtered prospect rows, with an optional copy-ready…
- Works in 3 steps: The operator confirms the source list.… → Resolve every source account to a bare… → If the client's ICP is unknown, ask.…
- Who engages with our competitors
- SKILL.md covers The number that governs planning, The source-company rule (both…, Before any paid call and Run it, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Playbook Linkedin Engagement is an agent skill from growthenginenowoslawski/coldoutboundskills. Turn the people who like and comment on a source account's LinkedIn posts (a competitor, or one of the client's own customers) into ICP-filtered prospect rows, with an optional copy-ready personalization line when the campaign asks for one. Triggers on "who engages with our competitors", "likers and commenters", "LinkedIn engagement list", "people commenting on competitor posts", "who engages with our customers' posts", "warm LinkedIn audience", "competitor engagers". Outputs one clean prospect row per engager…
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `clay-table.md` and `clay-workflow.md`).
It sits in Writing & Content, covering Social media posts. It works with LinkedIn. The repository describes itself as: Open-source Claude Code skills for cold email and outbound sales. Grade campaigns, export Prospeo searches, scrape Google Maps — all from Claude Code. The licence is MIT.
When your agent uses it
- Who engages with our competitors
- Likers and commenters
- LinkedIn engagement list
- People commenting on competitor posts
Example prompts
- “s LinkedIn posts (a competitor, or one of the client”
- “who engages with our competitors”
- “likers and commenters”
- “/playbook-linkedin-engagement”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- The operator confirms the source list. Say it out loud: *"these companies and everyone who
- Resolve every source account to a bare domain first. An unresolved source silently disables
- If the client's ICP is unknown, ask. Never infer a headcount band, a country list, or a title
What it can do on your machine
Read from SKILL.md and the folder at commit 25c5d85. 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
Playbook Linkedin Engagement loads about 1.5k tokens when it runs. Until then it costs about 145 tokens; SKILL.md has 725 words of instructions outside code blocks.
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 growthenginenowoslawski/coldoutboundskills at commit 25c5d85, republished under its MIT licence (© growthenginenowoslawski). 725 words, ~1,483 tokens.
Download SKILL.mdSave it as
.claude/skills/playbook-linkedin-engagement/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- playbook-linkedin-engagement
- description
- Turn the people who like and comment on a source account's LinkedIn posts (a competitor, or one of the client's own customers) into ICP-filtered prospect rows, with an optional copy-ready personalization line when the campaign asks for one. Triggers on "who engages with our competitors", "likers and commenters", "LinkedIn engagement list", "people commenting on competitor posts", "who engages with our customers' posts", "warm LinkedIn audience", "competitor engagers". Outputs one clean prospect row per engager; engagement_line only on request.
Playbook: LinkedIn Engagement
All rules here are best practice, not law. Override any of them when the campaign calls for it; note the best practice once and move on.
Use when an account's audience is the client's audience — a competitor or the client's own customer.
Do not use for more companies in a market, similar companies (playbook-lookalikes), or job
changers (playbook-new-in-role). The chain is the same for both lanes; only the target URL changes.
Output: one row per engager — who, employer, post, evidence URL. engagement_line is opt-in.
The number that governs planning
⚠️ Roughly 1 in 10 raw engagers survives. Harvest 10 to 15x what you need.
Cost follows from that: about $4.45 per 1,000 raw engagers, which is about $45 per 1,000 usable prospects at the measured survival rate. That is squarely in expensive territory, so shortlist posts by engagement count before you scrape.
The source-company rule (both halves, always automatic)
This is the rule that separates a usable engagement list from an embarrassing one, and it has two halves that people implement only one of.
(a) Drop every engager employed by ANY source company — not just the author of the post they engaged with. Match each current employer on resolved domain first, then profile URL, then squashed name, and also on resolved email domain.
(b) Push every source company onto that client's do-not-contact list. Row drops fix only this run; the block list runs at send time, which is what stops the same people arriving through a different lane next month.
It bites hardest on the customer lane, where the source companies are people the client already works with.
⛔ Never block the client's own domain. If it appears in the source set, the list is wrong — stop.
Before any paid call
- The operator confirms the source list. Say it out loud: "these companies and everyone who works at them go on this client's DNC list."
- Resolve every source account to a bare domain first. An unresolved source silently disables
both halves of the rule above. Unresolved means stop, not continue.
(
playbook-social-link-findingdoes this conversion in both directions.) - If the client's ICP is unknown, ask. Never infer a headcount band, a country list, or a title set.
Run it
0 Confirm source URLs, client ICP, and whether the brief wants a line (default: no).
0b Resolve every source account to a bare domain -> source-companies.json (EXACT match only).
Unresolved => STOP.
1 Company posts, windowed to the last month, shortlisted by engagement count.
2 Post reactions + post comments for the shortlisted posts.
3 ICP enrichment (headcount, company) on the engagers.
4 Deterministic pre-gate: source-company drop, ICP filter, dedupe.
5 Suppression pass: client DNC, existing TAM, live campaigns.
6 DNC push (once per harvest).
7 Email finding, valid only.Rows are the deliverable; lines are opt-in. Never run a line writer unless the brief asks. When it does, an empty-line row leaves that campaign for the normal one rather than shipping a gap.
Show full SKILL.md (319 more words)Show less
Verification
PASS 17/18 correct outcomes on the source-and-gate test — and note what that counts: a correct exclusion is scored as a usable outcome. Raw signal yield was 1 usable prospect in 17 unique people.
Both numbers are true and they measure different things. The gate works; the yield is thin. Plan from the yield.
⚠️ The end-to-end harvest has never been run in one pass. Do a one-post run and read the output before scaling.
Clay implementation
clay-table.md— where the gate lives in a table.clay-workflow.md— the CLI-buildable version.
Edge cases and failure modes
| Symptom | Cause | Fix |
|---|---|---|
| The list contains the client's own employees | The client's domain got into the source set | Stop. The list is wrong |
| The list contains the competitor's own staff | Only half (a) was implemented, matched on name alone | Match on resolved domain first, then profile URL, then squashed name, then email domain |
| The same people reappear next month through another lane | Half (b) was skipped | The DNC push is what persists. Row drops do not |
| The source-company rule appears to do nothing | An unresolved source URL produced an empty source set | An empty set silently disables both halves. Unresolved means stop |
| Cost per usable prospect is 10x the estimate | You costed raw engagers, not survivors | ~1 in 10 survives. Harvest 10-15x |
| A person's employer is wrong | Taking the first entry of an experience array rather than the current one | Read the current experience explicitly |
| Rows silently vanish on a join | Post and engager records key differently | Confirm the join key on one post before scaling |
| The run stalls waiting on a scraper | There is no fallback source by design | The run waits. A different scraper is not a drop-in substitute here |
Hard rules
- Both halves of the source-company rule, every run, automatically.
- The operator confirms the source list before any paid call.
- Rows are the deliverable. Lines are opt-in.
- If the ICP is unknown, ask.
© growthenginenowoslawski, 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 2 other files in skills/playbooks/playbook-linkedin-engagement of growthenginenowoslawski/coldoutboundskills.
- SKILL.md
- clay-table.md
- clay-workflow.md
Open the folder on GitHubat commit 25c5d85
Compare with similar skills
Playbook Linkedin Engagement 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Playbook Linkedin Engagement this skillgrowthenginenowoslawski/coldoutboundskills | 753 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Socialcoreyhaines31/marketingskills | 54k | 4 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Social Contentfreekmurze/dotfiles | 1k | 23 repos | ~2.1k | Automated safety check: Pass | None | |
| Linkedin Marketingsergebulaev/linkedin-skills | 4.4k | 1 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Linkedin Content Plannersergebulaev/linkedin-skills | 4.4k | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Typefullyfreekmurze/dotfiles | 1k | 1 repos | ~3.4k | Automated safety check: Notes | None |
Similar skills
Social Content
freekmurze/dotfiles
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms.
Linkedin Marketing
sergebulaev/linkedin-skills
Plan, draft, audit, and publish LinkedIn posts and comments.
Linkedin Content Planner
sergebulaev/linkedin-skills
Generate a 7-day LinkedIn content plan from a theme, audience, and pillars.
Typefully
freekmurze/dotfiles
Create, schedule, and manage social media posts via Typefully.
Changelog Social Recap
FlorianBruniaux/claude-code-ultimate-guide
Turns CHANGELOG.md entries for a release or a week into LinkedIn, Twitter/X, newsletter and Slack posts in French and English.
More from growthenginenowoslawski/coldoutboundskills
All 49 skills in this repoEmail Deliverability Audit
growthenginenowoslawski/coldoutboundskills
Diagnostic audit for a running cold email program. An agent skill from growthenginenowoslawski/coldoutboundskills.
Icp Onboarding
growthenginenowoslawski/coldoutboundskills
Conversational intake for cold email campaigns. An agent skill from growthenginenowoslawski/coldoutboundskills.
List Builder
growthenginenowoslawski/coldoutboundskills
META skill — build the largest possible qualified lead list for any request, end to end.
Auto Research Public
growthenginenowoslawski/coldoutboundskills
Autonomous cold email campaign launcher. An agent skill from growthenginenowoslawski/coldoutboundskills.
Blitz List Builder
growthenginenowoslawski/coldoutboundskills
Use the Blitz API to find decision-makers at specific companies when you already have a list of company domains.
Deliverability Test Public
growthenginenowoslawski/coldoutboundskills
Compare reply rates, bounce rates, and positive reply rates broken down by inbox type (SMTP / Gmail / Outlook) for a Smartlead account.
Related
Works with
Categories
Questions about Playbook Linkedin Engagement
What does Playbook Linkedin Engagement do?
Turn the people who like and comment on a source account's LinkedIn posts (a competitor, or one of the client's own customers) into ICP-filtered prospect rows, with an optional copy-ready…. Playbook Linkedin Engagement is an agent skill from growthenginenowoslawski/coldoutboundskills. Turn the people who like and comment on a source account's LinkedIn posts (a competitor, or one of the client's own customers) into ICP-filtered prospect rows, with an optional copy-ready personalization line when the campaign asks for one.
When should I use Playbook Linkedin Engagement?
Playbook Linkedin Engagement fits situations like: who engages with our competitors; likers and commenters; linkedIn engagement list; people commenting on competitor posts.
How do I install Playbook Linkedin Engagement in Claude Code?
Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a claude-code`. Or copy the skill folder (skills/playbooks/playbook-linkedin-engagement in growthenginenowoslawski/coldoutboundskills) into .claude/skills/playbook-linkedin-engagement in your project. Claude Code loads it when a task matches its description.
How do I install Playbook Linkedin Engagement in Codex?
Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a codex`. Or copy the skill folder (skills/playbooks/playbook-linkedin-engagement in growthenginenowoslawski/coldoutboundskills) into .agents/skills/playbook-linkedin-engagement in your project. Codex loads it when a task matches its description.
Can I use Playbook Linkedin Engagement 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 growthenginenowoslawski/coldoutboundskills --skill playbook-linkedin-engagement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/playbook-linkedin-engagement, .gemini/skills/playbook-linkedin-engagement, .github/skills/playbook-linkedin-engagement and .opencode/skills/playbook-linkedin-engagement in your project.
What does Playbook Linkedin Engagement need to run?
SKILL.md names no scripts, command-line tools or credentials: Playbook Linkedin Engagement is instructions for the agent only.
Does Playbook Linkedin Engagement 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 Playbook Linkedin Engagement 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 Playbook Linkedin Engagement use?
Playbook Linkedin Engagement 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 Playbook Linkedin Engagement use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Playbook Linkedin Engagement?
Skills that share tags, products or a category with Playbook Linkedin Engagement: Social (coreyhaines31/marketingskills, 54k stars), Social Content (freekmurze/dotfiles, 1k stars), Linkedin Marketing (sergebulaev/linkedin-skills, 4.4k stars) and Linkedin Content Planner (sergebulaev/linkedin-skills, 4.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Playbook Linkedin Engagement?
growthenginenowoslawski (a GitHub user) maintains it in growthenginenowoslawski/coldoutboundskills, which has 753 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 5, 2026.
Source: growthenginenowoslawski/coldoutboundskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.