WhatsApp Reader — Private, Read-Only Conversation Research
Summarize and research synchronized WhatsApp chats, find commitments, and brief contacts with Agensi-loaded workflows and a local read-only MCP.
$19
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsWhatsApp Reader — Private, Read-Only Conversation Research
Example session with this skill installed
Using my synchronized WhatsApp history, summarize commitments from the last 48 hours with [contact]. Separate explicit promises from possible tasks, clarify if the contact name is ambiguous, and state the coverage limits.
- Read your context and instructions
- Compiled the whatsapp reader
Illustrative example only — the chat details below are fictional, not real messages or a claim about a buyer's history.
Summary
In this fictional example, the local Reader returned 12 synchronized messages from the requested 48-hour window. The discussion covered a draft proposal and a follow-up meeting.
Commitments and possible tasks
| Item | Evidence | Owner | Deadline |
|---|---|---|---|
| Send the revised proposal | Explicit commitment | Buyer | Friday (as stated in the sample) |
| Review the proposal | Explicit commitment | Contact | Not stated |
| Arrange a follow-up | Possible task, not an explicit promise | Unclear | Not stated |
Basis and limits
The agent would identify the requested contact and date window, then summarize only the messages returned by the local Reader tools. A name matching multiple contacts should be clarified before reading. This sample uses invented content solely to illustrate the response format. Actual findings must be grounded in the buyer's synchronized messages; history may be incomplete or stale. No messages are sent, changed, or marked as read.
Connects securely to your tools. The creator never sees your data.
About this skill
Make your WhatsApp history easier to understand without handing conversation access to a general-purpose tool connection. WhatsApp Reader guides your AI agent through bounded, source-grounded conversation summaries, keyword searches, possible tasks and explicit commitments, and contact briefings.
The paid workflows are delivered through the Agensi connector. Buyers separately install the public WhatsApp Reader MCP and configure both the Agensi connector and local Reader MCP in the same agent. The local server registers nine read-oriented tools and does not expose message sending, deletion, reactions, read-state changes, group or account administration, session control, force-sync, or arbitrary HTTP tools. No local copy of the paid SKILL.md is required. The workflows treat message text as untrusted, distinguish facts from inferences, minimize personal data, disclose stale or incomplete-history caveats, and avoid claiming complete coverage.
Included workflows: conversation summaries, keyword research, task and commitment extraction, and contact briefings.
Requirements: Claude Code with the Agensi connector and public mcp-whatsapp Reader MCP configured in the same agent; Python 3.11+, Git, Docker Compose, and a WhatsApp account the buyer can pair with local WuzAPI. The buyer supplies local credentials/configuration and an AI model/provider. No hosted AI, WhatsApp access, model/API key, or server subscription is included.
Limitations: WuzAPI is an unofficial WhatsApp Web integration and may be affected by upstream changes or account/service restrictions. Results cover only locally synchronized history and may be incomplete or delayed; the skill does not trigger synchronization. Privacy redaction is best-effort, not exhaustive or a compliance certification. Message content is processed under the buyer's configured AI provider's data terms. The product does not pair WhatsApp or perform initial account setup on the buyer's behalf.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- Passed all security checks, Safe to install
Requires
Git
macOS
Windows
Python