Need help implementing this on your team?
We'll install the skills, customize them to your workflow, and run the output through your team's combined LinkedIn network. Skills do the research, Linkd does the motion.
Paste a profile or drop a URL. The skill audits ten sections, photo, banner, headline, About, experience, featured, recommendations, skills, education, activity, and returns recommendations ranked critical / important / polish. No 25-bullet unprioritized lists.
A profile review is only useful if the recommendations are actionable and prioritized. Generic checklists ("make sure you have a profile photo") don't engage with what the profile actually has. Unprioritized lists with 25 equal-weight bullets cause paralysis. The skill avoids both.
Ten sections get audited: photo, banner, headline, About, experience descriptions, featured section, recommendations, skills, education, recent activity. For each: present/absent/partial, quality if present, specific issue, recommendation, impact tier.
Impact tiers are honest. Critical = blocking discoverability or credibility (no photo, no current role, broken headline). Important = significantly improves the profile (weak About, no featured section, generic headline). Polish = marginal improvement (minor wording tweaks).
web_fetch first. LinkedIn often blocks unauthenticated fetches, fallback to pasted content. Asks for specific sections when fetch returns partial data.
Photo, banner, headline, About, experience, featured, recommendations, skills, education, activity. Each scored present / absent / partial / weak.
Critical (blocks discoverability or credibility), important (significantly improves), polish (marginal). Three tiers, not 25 equal bullets.
Not "improve your About", but "your About opens with 3 lines of credentials before any positioning; lead with the audience you serve". Targeted, not generic.
Markdown with sections ranked critical → important → polish. Plus a "fix this week" shortlist and a "build over 6 months" backlog.
"Make sure you have a profile photo", yes, of course. The review engages with what the profile actually has and what's wrong with IT specifically.
Critical / important / polish. A 25-bullet equal-weight list causes paralysis. The skill ranks aggressively so the user knows where to start.
Beyond the full ranked list, a 3–5 item shortlist of "do these this week" actions. The full list is the backlog; the shortlist is the next action.
"Get 10 recommendations" is correct but not actionable in 30 days. The skill distinguishes quick wins from long builds rather than mixing them.
Each of the ten sections gets a present/absent assessment, a quality grade if present, the specific issue, and a recommendation. Plus a critical → important → polish ranking and a "fix this week" shortlist of the highest-leverage actions.
The download is a zip containing two things: the .skill file (what you upload to Claude) and a SKILL.md sidecar (the human-readable instructions). Unzip first, then follow the steps for your Claude.
.skill file from the unzipped bundle..skill file too (it's also a zip).~/.claude/skills/web_search and file output enabled.This is exactly what Claude reads when the skill triggers. No hidden prompts, no separate config. What you see here is what you get.
We'll install the skills, customize them to your workflow, and run the output through your team's combined LinkedIn network. Skills do the research, Linkd does the motion.