RonanCodes/linkedin
skills/linkedin/SKILL.md
Manage your LinkedIn via the official API — create posts, fetch your profile, and draft copy for bio/experience edits. Use when user wants to post to LinkedIn, share an update, check their LinkedIn identity, or revise their profile/headline/about.
development
Updated May 1, 2026
$ install --global
skillsauthnpx skillsauth add RonanCodes/ronan-skills linkedinInstall 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, 2:29 AM289.9s7 files scanned
SKILL.md
- name:
- description:
- Manage your LinkedIn via the official API — create posts, fetch your profile, and draft copy for bio/experience edits. Use when user wants to post to LinkedIn, share an update, check their LinkedIn identity, or revise their profile/headline/about.
- category:
- social
- argument-hint:
- <auth | post <text> | me | draft <about|headline|experience|education|skills> [text]>
- allowed-tools:
- Bash(curl *) Bash(python3 *) Bash(open *) Bash(pbcopy) Read Write Edit
- - pipeline:
- distribution
- - platform:
- - role:
- adapter
Official LinkedIn API (OAuth 2.0) for creating posts from your personal profile. Profile-section edits (bio, experience, jobs) have no public write API — handled in draft-only mode: the skill generates the copy, copies it to clipboard, and opens the LinkedIn edit UI for you to paste + save.
Usage
/ro:linkedin auth # one-time OAuth (token lasts ~60 days)
/ro:linkedin post "Hello LinkedIn 👋" # publish a text post to your feed
/ro:linkedin me # show profile identity (userinfo)
/ro:linkedin draft about "New about-section copy..." # draft-edit mode: clipboard + open editor
/ro:linkedin draft headline "Staff Engineer @ ..."
/ro:linkedin draft experience # just open the add-position form
Dispatch
| Arg | Script |
|-----|--------|
| auth | scripts/auth.py |
| post <text> | scripts/post.sh |
| me | scripts/me.sh |
| draft <section> [text] | scripts/draft-edit.sh |
Pass all trailing args through verbatim.
First-time setup
- LinkedIn developer app — https://www.linkedin.com/developers/apps
- Products tab → request "Sign In with LinkedIn using OpenID Connect" and "Share on LinkedIn" (both usually auto-approve)
- Auth tab → Authorized redirect URLs → add
http://localhost:8765/callback
- Credentials — write to
~/.claude/.env:
ThenLINKEDIN_CLIENT_ID=... LINKEDIN_CLIENT_SECRET=...chmod 600 ~/.claude/.env. - Run OAuth:
/ro:linkedin auth— browser opens, you approve, token is written back to~/.claude/.env.
The access token lasts ~60 days. post / me warn when <7 days remain and fail hard when expired — re-run auth to refresh.
What this skill does NOT do
- Read bio / experience / about text — OIDC only returns name/email/picture. For the actual text use
/ro:linkedin-voyager profile <slug>(ToS-grey). - Bio / experience / headline / about edits — LinkedIn's Profile Edit API is partner-only.
draftmode is the answer: the skill generates the copy,pbcopys it, andopens the right LinkedIn form URL. You paste + save. - Company-page posts — would need
w_organization_socialscope + an org URN. Not wired. Ask to extend. - Messaging, connections, comments, reactions — not in the
w_member_socialscope. LinkedIn restricts these to partners. Use the paidlinkedin-cli(Linked API) if you need them. - Analytics beyond basic profile info — needs additional scopes / products not requested here.
Security
- Client secret and access token live only in
~/.claude/.env(mode 0600). Never committed. auth.pyonly binds tolocalhostand validates the OAuthstateparameter.- The skill never echoes the secret or the full token in output (only the last 4 chars for debugging).
Details
See reference.md for: OAuth flow internals, /rest/posts request shape, error codes, scope reference, and how to extend for company pages.
See also
ro:linkedin-scan— read-only LinkedIn scraper (light, public-facing HTML).ro:linkedin-voyager— ToS-grey sibling: reads bio/experience/full profile via the unofficial Voyager API using browser cookies. Use when the official API can't give you what you need. Ban risk — see its SKILL.md.ro:browser-cookies— shared cookie extractor used by scan + voyager.ro:write-copy— apply style rules before drafting a post or about section.
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