linkedin-comment
Skill0 starsChanged 31 days agoMITView on GitHub
Writes LinkedIn comments on other people''s posts that read human and build relationships with buyers and the people they follow. Each comment quotes something specific from the post, adds the author''s own experience, and ends on a sharp point or a real question. Bans generic praise, pitching and engagement bait. Also works for thread replies in communities and Slack. Triggers: "comment on this post", "LinkedIn comment", "write a comment", "reply to this post", "engage with this post", "my comments for today".
2 other projects use a version of this.
Adopted by
Most recently taken up by
- rapha-red/linkedin-plugintheir own version, first seen Oct 13, 2026
- cavalenzuelalara/claude-skillstheir own version, first seen Oct 11, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- cavalenzuelalara/claude-skills★ 0same name
- rapha-red/linkedin-plugin★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- linkedin-carouselsSkill
- linkedin-content-auditSkill
- linkedin-expert-postsSkill
- linkedin-hooksSkill
- linkedin-personal-postsSkill
- linkedin-profileSkill
- linkedin-weekly-contentSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
- Distinctive: line 10
Write comments on other people's posts.
- Very specific: line 18
Not for writing posts (/linkedin-expert-posts, /linkedin-personal-posts) or for DMs.
- Distinctive: line 31
If the post is cut off, ask for the full text first.
- Distinctive: line 60
Read the post: Write its point in one sentence and pick 2 to 3 quotable phrases.
- Distinctive: line 70
No generic praise: Never "Great post", "Love this", "So true", "This resonated", "Spot on", "Thanks for sharing".
- Distinctive: line 71
No engagement bait: Never "Thoughts?", "Agree?", "What do you think?", "Curious to hear your take".
- Distinctive: line 73
No invented experience: Every story, number and credential is real.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
LinkedIn comment
Write comments on other people's posts. Comments put the author in front of the poster's audience and start relationships. A good comment is a small post in its own right; a generic one tells everyone it was written by a bot.
When to use it
- Daily commenting: a handful of thoughtful comments on posts from buyers and the people buyers follow.
- A reply to someone who commented on the author's post.
- Thread replies on other surfaces (communities, Slack, cohort feedback), where the same rules apply.
Not for writing posts (/linkedin-expert-posts, /linkedin-personal-posts) or for DMs.
Inputs
| Input | Required? | Where it comes from |
| The full post text | Required | The user (text or screenshot) |
| Who the poster is | Recommended | Role and company, from the user |
| Voice | Recommended | the tone-of-voice file in context/brand/ |
| The author's expertise and stories | Recommended | context/expert-pov/ |
| Who the buyer is | Recommended | context/icp/, to decide whose posts are worth the time |
| Relationship history | Optional | The user |
If the post is cut off, ask for the full text first. If the voice file is missing, ask for two comments the author wrote before and match them.
Agency users: swap context/ for clients/<client>/context/.
Whose posts
Comment where the buyer is: buyers themselves and the people they follow. Commenting mainly in peer threads teaches the algorithm the wrong audience. Skip politics, drama and pile-ons. When asked for a batch, flag any post that fails this test before drafting.
The three-sentence shape
- Reference. Quote or name a specific phrase or claim from their post.
- Add. The author's own experience, a data point, a counter-example or a next step. First person: "I've seen...", "On the last project I...".
- Close. A sharp claim, or a question whose answer the author actually wants.
For thread replies, lead with the useful move instead: what the author would do, in first person, with the acknowledgement woven in, not up front.
Comment types
| Type | Use it when |
| Extend | You can take their point one step further |
| Story | You have a short real moment that proves or complicates it |
| Nuanced agreement | You agree, with a condition they missed |
| Contrarian | You see it differently and can say why, politely |
| Real question | You want to know how they handle a specific part |
| Bridge | You can connect their point to a related problem |
Steps
- Read the post. Write its point in one sentence and pick 2 to 3 quotable phrases. Produces: the hook into the comment.
- Pick the type that fits the post and the author's real experience. Produces: the angle.
- Draft in the three-sentence shape, in the author's voice. Produces: the comment.
- Run the anti-AI rules below. Produces: the cleaned comment.
- Write an alternative with a different type. Produces: two options to choose from.
- Suggest replies. Two short options in case the poster responds. Produces: thread follow-ups.
Anti-AI rules (non-negotiable)
- Specific reference. The first sentence names something from this post. The 100 posts test: if the comment could sit under 100 other posts, rewrite it.
- No generic praise. Never "Great post", "Love this", "So true", "This resonated", "Spot on", "Thanks for sharing".
- No engagement bait. Never "Thoughts?", "Agree?", "What do you think?", "Curious to hear your take". Ask only a question you need answered, or end on the claim.
- No pitching. No "DM me", "I can help", "We do this at...", "Book a call".
- No invented experience. Every story, number and credential is real. If there is none, write a comment that does not need one.
- No AI rhythm. No "It's not X, it's Y", no three short parallel sentences, no buzzwords, no emoji strings.
- Length. 50 to 150 words. Under 30 adds nothing; over 200 hijacks the thread. Short line breaks for mobile.
- Vary the shape. In a batch, no two comments use the same opening or structure.
What good looks like
- The poster can tell the author actually read the post.
- The comment adds something the post did not have.
- It sounds like a person who does the work, talking to a peer.
Output
Return in the chat: the post's point in one line, the comment, word count, comment type, the alternative, and two reply options. For a daily batch, number each comment and flag any post you suggest skipping.
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
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.