li-inbox
Skill2 starsChanged 44 days agoMITView on GitHub
Triage the LinkedIn inbox into lead, recruiter, peer, ask, and spam, and say which tell gave each message away. Use when the user pastes messages or asks "triage my inbox", "what needs a reply". Sorts and prioritizes; drafts replies only on request via li-reply or li-dm rules.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- furkanbilalakyuz/linkedin-agent-skill-trtheir own version, first seen Nov 8, 2026
- mubaid/dsh-linkedin-agenttheir own version, first seen Oct 25, 2026
- robbiehaynes/job-searchtheir own version, first seen Oct 20, 2026
- postzen-dev/linkedin-agent-skilltheir own version, first seen Oct 15, 2026
- avi691/linkedin-agent-skilltheir own version, first seen Oct 8, 2026
- nessalazne/linkedin-agent-skilltheir own version, first seen Sep 19, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- Jakeschincariol/linkedin-agent-skill★ 514same name
- avi691/linkedin-agent-skill★ 5same name
- nessalazne/linkedin-agent-skill★ 3same name
- postzen-dev/linkedin-agent-skill★ 3same name
- furkanbilalakyuz/linkedin-agent-skill-tr★ 0same name
- mubaid/dsh-linkedin-agent★ 0same name
- robbiehaynes/job-search★ 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- li-auditSkill
- li-carouselSkill
- li-commentSkill
- li-dmSkill
- li-humanSkill
- li-planSkill
- li-postSkill
- li-profileSkill
- li-replySkill
- li-repurposeSkill
- li-voiceSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 56
Never draft a reply to spam, even a polite decline.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
li-inbox
The inbox, triaged. Every message gets a bucket, a priority, and the tell
that gave it away. This skill sorts; it does not reply. Reply drafts come
from li-reply (for threads) or li-dm (for new outreach), only when the
user asks.
Before you triage
Get the messages: the user pastes them with sender names, or describes them. You need sender + message text for each. Work with what you have.
The buckets
| Bucket | The tell | Action |
| Lead | Asks about the work, pricing, process, availability; mentions a problem you solve | Reply within 24h. Draft via li-dm rules on request. |
| Recruiter | Role pitch, "saw your profile", JD attached or promised | Reply only if looking; template decline otherwise |
| Peer | Industry conversation, no ask, mutual interest | Reply when genuine; these compound |
| Ask | Favor with no relationship: intro, feedback, "pick your brain", promo | Decide the policy once (e.g. "asks get a no or a link"), apply always |
| Spam | Pitch-slap, irrelevant offer, mass template, "just bumping" from a stranger | Archive. No reply. No guilt. |
The loop
1. The triage table. One row per message:
FROM BUCKET TELL
Maya Chen LEAD asks how the audit is priced, mentions her team of 6
Dev R. RECRUITER "exciting Staff SWE role", no company name
growth_hacker_99 SPAM "just bumping this to the top" + lead-gen pitch2. The priority order. What to answer today, in order: leads first, then asks you have decided to honor, then peers. Recruiters and spam get their disposition stated once.
3. The pattern note. End with one line on what the inbox is telling you: "3 of 5 messages this week are pricing questions - your recent posts are working" or "all recruiter, no leads - the profile is signaling job-seeker". The inbox is market data.
Rules
- A maybe is a no with extra steps. If a message is not clearly a lead, it is not a lead. Say so.
- Never draft a reply to spam, even a polite decline. Replies train spammers that the inbox is live.
- The "ask" policy is the user's to set once; your job is to remind them of it consistently, not to re-litigate it per message.
- Time-box it: triage should take the user five minutes to read. If the inbox needs more than that, the buckets are wrong.
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.