RonanCodes/linkedin-voyager
skills/linkedin-voyager/SKILL.md
Read LinkedIn profile data (bio, headline, experience, education, skills, contacts) via the unofficial Voyager API. Uses your browser session cookies — NO password. Sibling to the official-API `linkedin` skill. Use when user wants to see or export their own (or a public) profile content not available in the official API.
development
Updated May 1, 2026
$ install --global
skillsauthnpx skillsauth add RonanCodes/ronan-skills linkedin-voyagerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 1, 2026, 2:27 AM189.1s2 files scanned
SKILL.md
- name:
- linkedin-voyager
- description:
- Read LinkedIn profile data (bio, headline, experience, education, skills, contacts) via the unofficial Voyager API. Uses your browser session cookies — NO password. Sibling to the official-API `linkedin` skill. Use when user wants to see or export their own (or a public) profile content not available in the official API.
- category:
- social
- argument-hint:
- <profile <slug> | contact <slug> | search <keywords> | connections>
- allowed-tools:
- Bash(uv *) Bash(python3 *) Read
- - pipeline:
- scan
- - platform:
- - role:
- scanner
LinkedIn Voyager (unofficial)
Read-side sibling to ro:linkedin. Hits LinkedIn's internal Voyager API (same API the linkedin.com web app uses) via the linkedin-api Python library (tomquirk). Gives access to profile sections the official OAuth API doesn't expose: About, Headline, Experience, Education, Skills, Certifications, Contact info, Connections, etc.
⚠️ Terms of service + ban risk
This skill uses an undocumented internal API and authenticates with your session cookies. Per LinkedIn's User Agreement §8.2, automated access that is not through their public API is prohibited. Aggressive or high-volume usage has resulted in account restrictions or bans. Use sparingly:
- Prefer
/ro:linkedin(official API) for anything it covers. - Keep request rate low. One profile fetch per minute is fine; a scripted crawl is not.
- The skill is model-invocable, but treat it as a deliberate operation — don't auto-fire it on tangential LinkedIn-related questions. Prefer
/ro:linkedin(official API) when possible.
Usage
/ro:linkedin-voyager profile ronanconnolly # your own profile (bio/headline/experience/skills)
/ro:linkedin-voyager profile satyanadella # any public profile slug
/ro:linkedin-voyager contact ronanconnolly # email/phone/twitter if the viewer can see them
/ro:linkedin-voyager search "staff engineer" # people search (limited)
/ro:linkedin-voyager connections # the viewer's own 1st-degree connections
Auth — session cookies, no password
On every run, scripts/voyager.py extracts li_at + JSESSIONID from the browser set by ROBROWSER in ~/.config/ro/defaults.env (or --browser <name>), using browser_cookie3. No password is ever prompted or stored. Cookies stay in memory.
If the library rejects the cookies (LinkedIn sometimes requires challenges), log into linkedin.com once in the browser and retry.
Output
Profile output (default — compact human-readable):
# <Full Name> — <Headline>
<location> · <industry>
linkedin.com/in/<slug>
## About
<bio text>
## Experience
- <Title> @ <Company> (<start> – <end or Present>) <location>
<description if any>
- ...
## Education
- <School> — <Degree> <Field> (<years>)
## Skills
skill1, skill2, skill3, ...
Add --json for raw Voyager JSON (huge — useful for wiki ingest or diffs).
Dispatch
| Arg | Function |
|-----|----------|
| profile <slug> | get_profile(public_id=slug) + pretty-printer |
| contact <slug> | get_profile_contact_info(public_id=slug) |
| search <terms> | search_people(keywords=terms, limit=10) |
| connections | get_profile_connections(<viewer>) |
Execution
uv run --with 'linkedin-api>=2.3' --with browser-cookie3 python3 \
/path/to/skills/linkedin-voyager/scripts/voyager.py <cmd> <args...>
uv provisions the deps on first run; subsequent runs are fast.
TODO / known limits of profile
- Current implementation uses dash endpoint
FullProfile-138which returns the top card only: name, headline, summary (About/bio), location, profile picture. - Experience, education, skills, certifications, languages live on separate dash sub-endpoints (e.g.
/identity/dash/profilePositions?viewee=<urn>&...). Not yet wired. Add as a second call chained after the top card if the caller wants the full profile. - Library's own
get_profile()hits/identity/profiles/<slug>/profileViewwhich returns 410 Gone as of 2026-Q1. Don't use it — this skill'scmd_profilecalls the dash endpoint directly.
Limits & failure modes
- Rate limit / challenge — LinkedIn may serve a CAPTCHA. Log into linkedin.com in the browser, solve it, retry.
- Fields missing — Voyager returns what the authenticated viewer can see. Private profiles return a stub.
- Library drift — LinkedIn rotates internal endpoints;
linkedin-apiis usually patched within weeks.uvauto-picks the latest compatible version per run. - Account flag — heavy usage = temp restriction. Don't loop this skill. If responses start returning
Set-Cookie: li_at=delete me+ infinite 302 loops to the same URL, LinkedIn has invalidated the session server-side. Log back into the browser and wait ~30 min before retrying. - Cookie quirk (fixed in scripts/voyager.py) — Chromium stores LinkedIn cookies with domain
.www.linkedin.comand quoted JSESSIONID values like"ajax:...". requests' cookiejar won't send.www.linkedin.com-scoped cookies to hostwww.linkedin.com, and the quoted JSESSIONID won't match thecsrf-tokenheader (which is set unquoted). Both caused 403 "CSRF check failed" untilget_cookies()rebuilt the jar with.linkedin.comdomain + stripped JSESSIONID quotes.
See also
/ro:linkedin— official OAuth API: posts + draft-mode profile edits. Start there./ro:linkedin-scan— light scraping of the public-facing HTML (even safer, less structured)./ro:browser-cookies— the underlying cookie path this skill uses.- Upstream: https://github.com/tomquirk/linkedin-api
Related Skills
RonanCodes/skills/linear-pipeline
testing
VerifiedTrustedCommunity
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
SKILL.mdUpdated Jul 5, 2026
RonanCodes/skills/in-your-face
development
VerifiedTrustedCommunity
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
SKILL.mdUpdated Jul 5, 2026
RonanCodes/codex
tools
VerifiedTrustedCommunity
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
SKILL.mdUpdated Jul 5, 2026
RonanCodes/warranty-check
research
VerifiedTrustedCommunity
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".
SKILL.mdUpdated Jul 4, 2026