li-audit
Post-mortem on what the user has already published - which posts actually worked, why, and…
Write comments on other people's LinkedIn posts that read as a person with an opinion, not a bot. Use when the user pastes a post and wants a comment, says "comment on this", "engage with this", "what do I say here", or wants a batch of comments for their engagement round.
$ npx -y skills add Jakeschincariol/linkedin-agent-skill --skill li-comment --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/li-commentContext preview
The summary Claude sees to decide when to auto-load this skill.
Write comments on other people's LinkedIn posts that read as a person with an opinion, not a bot. Use when the user pastes a post and wants a comment, says "comment on this", "engage with this", "what do I say here", or wants a batch of comments for their engagement round.
name: li-comment description: >- Write comments on other people's LinkedIn posts that read as a person with an opinion, not a bot. Use when the user pastes a post and wants a comment, says "comment on this", "engage with this", "what do I say here", or wants a batch of comments for their engagement round.
Commenting is the highest-leverage thing on LinkedIn and the easiest to do badly. A comment on a post with 400 reactions gets seen by more people than most of your own posts. A generic one gets seen by nobody and costs you credibility with the author.
The user pastes the post text (and the author's name and role if they have it). If they paste a screenshot, read it. If they give you a URL you cannot open, ask them to paste the text - do not guess what the post said, and do not use browser automation to scrape the feed.
Pick by what the post actually is. Never default to type 1.
| # | type | when | shape | | --- | --- | --- | --- | | 1 | **Add a datum** | post makes a claim you can support with a number | "We saw the same thing: 40% of our..." | | 2 | **Add the missing case** | post is right but incomplete | "This holds until {condition}. Then..." | | 3 | **Respectful disagree** | you genuinely think it is wrong | name the agreement first, then the fork | | 4 | **Extend one line** | one sentence in the post is the good one | quote it, then build on it | | 5 | **Ask the real question** | post skipped the hard part | one question, specific, no "curious to hear" | | 6 | **The receipt** | you have done the thing they described | what happened, in two sentences | | 7 | **The correction** | there is a factual error | be right, be brief, be kind, be sure | | 8 | **The reframe** | the post has the right facts and the wrong frame | "Another way to read this:" | | 9 | **The one-liner** | the post needs nothing, you want presence | under 12 words, must be funny or true |
more", "This resonates", or the author's first name followed by an exclamation mark. All six are invisible.
everyone reading.
topic, it is not a comment, it is noise.
and be real.
Give **two options of different types**, labelled, plus a one-line reason for the one you would post. Run both through `/li-human` first - a comment with an em dash in it is more obviously machine-written than a post, because comments are short and people read them closely.
COMMENT OPTIONS (on @author's post about hiring) [6 · Receipt] We tried the no-resume version of this for 3 hires last year. Two were the best hires we made. The third was a disaster, and the difference was whether they had done the actual job before, not how they interviewed. [3 · Respectful disagree] Agree on the signal problem. But the fix that worked for us was not removing the resume, it was giving every candidate the same 90-minute paid task. Same outcome, far less argument internally. Post the first. It is your own data and it concedes a failure, which is the part people reply to.
If the user wants an engagement round, ask for the 5-10 posts as pasted text in one message, return one comment each in a single block, and keep a running note of who they have already commented on this week in `~/.claude/linkedin/log.md`. Commenting on the same three people every day is visible and it looks like what it is.
Do not auto-post. Do not use a browser tool to publish comments on the user's behalf. Automated posting and scraping both violate LinkedIn's User Agreement and put the account at risk. This skill writes the comment. The user posts it.
Eleven Claude skills that run a LinkedIn account. Free, MIT, no signup, no API key, nothing to connect. One of them writes your posts off 21 hook formulas. One comments on other people's posts. One handles the replies under yours.
Post-mortem on what the user has already published - which posts actually worked, why, and…
Build a LinkedIn document post (carousel) - slide-by-slide copy, the cover that earns the…
Write connection notes and DM follow-ups that get replies - the 200-character invite, the…
Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible…
Triage the LinkedIn inbox - sort connection requests and DMs into leads, recruiters, peers…
Build the week on LinkedIn - what to post, when to post it, and who to engage with. Use when…