network-scan
Skill0 starsChanged 2 months agoMITView on GitHub
Find who you know at companies that are hiring - LinkedIn and Xing
3 other projects use a version of this.
Adopted by
Most recently taken up by
- dotlabshq/cruxtheir own version, first seen Oct 8, 2026
- zeljkoobrenovic/sokrates-skillstheir own version, first seen Oct 2, 2026
- proficientlyjobs/proficiently-claude-skillstheir own version, first seen Feb 25, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- proficientlyjobs/proficiently-claude-skills★ 389same name
- dotlabshq/crux★ 4same name
- zeljkoobrenovic/sokrates-skills★ 3same 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- anschreibenSkill
- applySkill
- evaluateSkill
- followupSkill
- interview-prepSkill
- job-searchSkill
- mappeSkill
- patternsSkill
- setupSkill
- tailor-cvSkill
- trackerSkill
- visaSkill
- zeugnisSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Read contacts.csv, preferences.md, resume/*, and tracker.md.
- Distinctive: line 35
Not every contact is worth asking:
- Very specific: line 45
Check Connected On — a contact from eight years ago you have not spoken to since is a different ask from a recent colleague.
- Very specific: line 49
Ask with AskUserQuestion which contacts to write to and what the ask is: a referral, an internal intro, or just context on the company.
≈ “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
Network Scan
Contacts import:
/wingman:setup· Boards:shared/references/de-job-boards.md
In Germany a referral matters at least as much as anywhere else — Germans call the who-you-know factor Vitamin B, and Mittelstand hiring in particular runs on it. A named internal referral routinely beats a cold application to the same posting.
Step 0: Prerequisites
contacts.csv required. Missing → "Run /wingman:setup and export your LinkedIn connections first." CV and preferences also required for the company-fit side.
Step 1: Load
Read contacts.csv, preferences.md, resume/*, and tracker.md.
The LinkedIn export has First Name, Last Name, Company, Position, Connected On. Xing exports vary and are increasingly restricted — handle whatever columns are present rather than assuming a schema.
Step 2: Match
With a company name — find contacts there and check whether the company is hiring.
Without — cross-reference every company in the active pipeline (tracker.md plus recent job-history.md) against the contacts.
Match fuzzily and carefully. Beispiel GmbH should match Beispiel Group, Beispiel Deutschland GmbH, Beispiel SE. German legal suffixes are noise for matching: strip GmbH, AG, SE, KG, GmbH & Co. KG, mbH, e.V. before comparing.
Say when a match is uncertain. A wrong "you know someone here" wastes an outreach and is embarrassing.
Step 3: Rank the contacts
Not every contact is worth asking:
| Contact | Value |
| Same team or function as the role | Highest — can refer directly and speak to the work |
| Hiring manager's peer or manager | High |
| HR / Recruiting at the company | High, and the most direct route in Germany |
| Anywhere else in the company | Moderate — many German employers pay an Empfehlungsbonus for any employee referral |
| Left the company | Low, but can still offer honest context |
Check Connected On — a contact from eight years ago you have not spoken to since is a different ask from a recent colleague. Say which it is; the message should differ.
Step 4: Draft the outreach (interactive)
Ask with AskUserQuestion which contacts to write to and what the ask is: a referral, an internal intro, or just context on the company.
Draft in the language and register that fits the relationship — a former colleague you were on du terms with does not get Sehr geehrter Herr. Register from the relationship, not from language.md.
German norms for this: short, direct, concrete ask, no American-style enthusiasm. Name the specific role and Kennziffer. Make it easy to say no. Under 300 characters for a LinkedIn message.
Never send it. Draft only — the user sends.
Step 5: Also useful without a contact
For companies where the candidate knows nobody, offer:
- The named contact from the posting — a real person to address the Anschreiben to beats
Sehr geehrte Damen und Herren - kununu reviews for what working there is actually like
- Whether the company has a Betriebsrat, and its funding or ownership situation
Step 6: Save
Record contacts found and outreach drafted against the job folder, and note it in tracker.md. Do not re-draft outreach to a contact already approached for the same role.
Response Format
- Matches — contact, position, company, relationship strength, connection age
- Recommended Outreach — who to ask and for what
- Drafts — the messages, ready for the user to send
- No Contact? — named addressee from the posting, kununu signal
Permissions
{ "permissions": { "allow": [
"Read(~/.wingman/**)", "Write(~/.wingman/**)", "Edit(~/.wingman/**)",
"mcp__claude-in-chrome__*"
] } }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.

