fetch-linkedin-message-history
Fetch read-only LinkedIn message history from the user's logged-in browser for either a LinkedIn messaging thread URL or a LinkedIn profile URL.
Skill by prakhar1114
Chalk Labs
Need help deploying fetch-linkedin-message-history?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/prakhar1114-fetch-linkedin-message-history
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/fetch-linkedin-message-history
What's inside
- Skill name
fetch-linkedin-message-history- Description
- Fetch read-only LinkedIn message history from the user's logged-in browser for either a LinkedIn messaging thread URL or a LinkedIn profile URL. Use when the user wants recent/default LinkedIn chat history, sender names, timestamps, raw structured message data, and Markdown-formatted clickable links without sending messages or opening shared URLs individually.
- License
- MIT
- Instructions
- 80 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (6)
- SKILL.md
- inputs.example.json · inputs/
- inputs.template.json · inputs/
- fallback_plan.md · references/
- run.sh
- run.py · scripts/
SKILL.md (first lines)
## Preconditions
- The user is already logged in to LinkedIn in Chrome.
- The skill uses the AI Mime browser harness through `$AI_MIME_BROWSER_HARNESS_BIN`.
## Inputs
Read JSON from `--inputs-json`. Provide exactly one of:
- `profile_url`: LinkedIn profile URL, or `null`.
- `thread_url`: LinkedIn messaging thread URL, or `null`.
Optional:
- `days`: integer day window, or `null`. When `null`, LinkedIn's latest/default message set is returned, capped by LinkedIn's API/page behavior.
Validation rules:
- Exactly one of `profile_url` or `thread_url` must be non-null.
- `profile_url` is optional; use `thread_url` alone for direct thread fetches.
- Both null is invalid.
- Both filled is invalid.
- `days` must be null or a non-negative integer.
- Validation failures return `success: false` with `validation_message`; they do not launch LinkedIn browser automation.
## Run
Run with:
```bash
./run.sh inputs/inputs.example.json
```
`run.sh` uses the first available interpreter in this order: skill `.venv/bin/python`, workflow `.venv/bin/python`, then required `$AI_MIME_PYTHON_PATH`.
No third-party Python packages are required. If a future change adds `requirements.txt`, install or repair dependencies during skill build or manual repair with:
```bash
"$AI_MIME_UV_PATH" venv .venv --python "$AI_MIME_PYTHON_PATH"
"$AI_MIME_UV_PATH" pip install -r requirements.txt --python .venv/bin/python
```
Runtime does not create or repair `.venv`.
## Outputs
The script prints one stdout JSON object:
```json
{"event":"workflow_done","outputs":{"success":true,"runs":[]}}
```
Validation failures print the same wrapper with `outputs.success` set to `false` and a `validation_message` explaining the invalid input.
Each run includes:
- `messages`: structured records with sender name (`sender` as `You` or the LinkedIn display name), timestamp, text, content type, and direct LinkedIn message metadata.
- `message_history_markdown`: Markdown list with clickable links formatted as `[url](url)`.
- `shared_content`: for LinkedIn shared posts, direct message-payload fields only: host URN, host type, activity id, derived LinkedIn activity URL, and direct `preview_text` if LinkedIn included it in the message payload.
- `possibly_truncated`: true only when the fetched default API page does not reach older than the requested day cutoff.
The skill does not open each shared URL and does not make per-shared-item preview requests.
## Progress logs
Progress logs are written to stderr in clear, short, natural language suitable for an end-user overlay, such as "Opening a neutral LinkedIn page for authenticated API access..." and "Reading messages through LinkedIn's first-party messaging API...".
## Fallback
Read `references/fallback_plan.md` if `run.sh` fails. The fallback describes how to manually use the LinkedIn UI and same-origin browser APIs without sending messages or opening shared URLs individually.
## ask_llm decision points
None.
## References
- `references/fallback_plan.md`From prakhar1114/ai_mime_marketplace, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 27, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get fetch-linkedin-message-history running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
fetch-linkedin-message-history skill. Agent Mart. https://agentmart.dev/skills/prakhar1114-fetch-linkedin-message-history (last updated 2026-10-24)