AGENT SKILL

fix-my-linkedin-profile

Go through headline, about and featured in the order a visitor reads them, and rewrite whichever one is losing the click. Use when someone asks for a profile review, has a new role or a new offer, says their profile gets views and nothing else, or wants their headline rewritten. Do not stuff keywords, do not promise search placement, and do not rewrite the parts that are already working.

License 许可
Apache-2.0
最近更新
2026-11-13
Stars
★ 1.6k
Forks
483

01 前言 Front Matter

name
fix-my-linkedin-profile
description
Go through headline, about and featured in the order a visitor reads them, and rewrite whichever one is losing the click. Use when someone asks for a profile review, has a new role or a new offer, says their profile gets views and nothing else, or wants their headline rewritten. Do not stuff keywords, do not promise search placement, and do not rewrite the parts that are already working.

03 SKILL.md 正文

Fix my LinkedIn profile

A profile is read in a fixed order by somebody who has already decided to be curious. They saw a post or a comment, they clicked the name, and now they are deciding in a few seconds whether this person is worth following.

Most profiles answer a different question. They are written as a CV, for a recruiter, in the third person, and the visitor who arrived from a post is not that reader.

Step 1: work out who lands here, and from where

The arrival changes what the first line has to do:

  • From a post or a comment. They liked one thing you said. The profile has to tell them whether there is more of it.
  • From search. They have a problem and are checking whether you solve it.
  • From a message or an introduction. They are checking whether to reply.
  • From your own link. They were sent, and the profile is a landing page.

Ask which of these dominates before rewriting anything.

Step 2: the headline

This is the only part that travels. It sits under your name on every post and every comment you leave, so it is read far more often than the profile itself.

It has two jobs: say what you do in the words the reader uses, and give them a reason to click. Common failures:

  • The job title alone, which means nothing outside the company
  • A row of nouns separated by pipes, which reads as a search query
  • An abstraction about helping people unlock their potential
  • Keywords packed in until the line stops being a sentence

Test it by reading it aloud directly after the person's name. If it does not survive being said out loud, it will not survive a feed.

Step 3: the first two lines of About

Everything after them is behind "see more", and most About sections open with a warm-up paragraph nobody gets past. Those two lines carry the whole section.

They should say who you help and what changes. Not your career history, which is what the experience section is for.

Step 4: the rest of About

In this order, in first person, in actual sentences: who you work with, what changes for them, the proof, and what to do next.

Proof means something checkable. A number you can source, a name you have permission to use, a thing somebody can go and read. Adjectives are not proof.

Step 5: featured

Three items at most, each earning its slot. Ask one question: if a stranger read exactly one thing here, which would you want it to be? Then check whether that thing is first.

Step 6: say what to leave alone

Name the parts that are already working and say why. A review that rewrites everything is not a review, and it usually ends with a profile that sounds less like the person than the one they started with.

What this will not do

It will not promise search placement. LinkedIn does not publish how its search ranks people, and anyone quoting you a formula for it is guessing.

It will not stuff keywords. A headline written for a matching algorithm reads exactly like one to the human who arrived from a post, and that human is the one who was going to follow you.

What changes when VoiceMoat is connected

A profile written in a voice the posts do not share is the mismatch a visitor notices first:

  • get_voice_profile gives your LinkedIn register, so the About section sounds like the post that brought them here.
  • get_voice_insights shows the subjects and patterns you actually publish on, which is usually a sharper answer to "what do you do" than the one people give when asked directly.
  • score_voice_match scores the rewritten About against your profile, which catches the drift into brochure voice that this exercise invites.

VoiceMoat also runs three free LinkedIn profile tools at voicemoat.com/tools: a headline analyzer, a headline generator and a summary generator. No account is needed for those either.

VoiceMoat is at voicemoat.com. The connector needs the Pro or Enterprise plan.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

migrate-to-e2e

Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

e2e

Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

create-verification-skill

Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-search

deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-reflect

End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

revid

Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.

图像与多媒体Skill与智能体开发
★ 1.6k