- Home
- Skills
- Research & Analysis
- whatsapp ask
whatsapp ask
Local WhatsApp chat indexing and search with SQLite and verifiable [#ID] citations.
Free
Works with the AI Agents you already use
whatsapp ask
Example session with this skill installed
Import my 'Project Alpha' chat from backup.zip, then search for any messages where we discussed the 'deadline' or 'milestones'.
- Read your context and instructions
- Compiled the whatsapp ask
I have imported the 'Project Alpha' chat and performed an IDF-ranked search for the terms "deadline" and "milestones".
Search Results for "deadline", "milestones"
| ID | Date | Sender | Chat | Message Excerpt |
|---|---|---|---|---|
| [#442] | 2024-03-12 | Alice | Project Alpha | "We need to hit the Q1 deadline by Friday." |
| [#445] | 2024-03-12 | Bob | Project Alpha | "Agreed, let's review the milestones on Trello." |
| [#510] | 2024-03-15 | Alice | Project Alpha | "Pushed the final deadline to next Monday." |
| [#512] | 2024-03-15 | Charlie | Project Alpha | "Updated the project milestones in the doc." |
The team initially targeted March 15th for the Q1 deadline [#442], but Alice later confirmed it was pushed to the following Monday [#510]. Bob and Charlie confirmed that milestones were being tracked in Trello and the main project document [#445][#512].
Next steps
- Use
python -m wa.cli context 510to see the messages surrounding the deadline change. - Use
python -m wa.cli export --ids 442,445,510,512 --format mdto save these as a summary report. - Run a follow-up search for "Trello" to find the link mentioned by Bob.
Connects securely to your tools. The creator never sees your data.
About this skill
Privacy-first WhatsApp chat analysis is hard when transcripts exceed context windows or contain sensitive data. This skill provides a local, zero-dependency Python CLI to index WhatsApp exports into SQLite for ranked searching and verifiable analysis.
What it does
- Local Indexing imports
.txtor.zipexports from Android and iPhone into a local SQLite database. - Ranked Search uses IDF-weighting to find relevant message excerpts across massive histories without hitting token limits.
- Context Inspection retrieves the messages immediately preceding or following a specific message ID to verify intent.
- Verifiable Citations forces the agent to cite every claim using specific
[#ID]tags linked to the raw transcript. - Structured Export saves filtered message sets to CSV, Markdown, or TXT formats for external reporting.
How it works
- Import chat files using
wa.cli importto build the local relational index. - List and Filter available chats by date range or sender to narrow the analysis scope.
- Search or Read using keywords for large datasets or full transcripts for smaller date windows.
- Cite and Export relevant findings into formatted reports with full message metadata.
Frameworks & tools
Python 3.11+ using only the standard library. Uses SQLite for local storage and wa.cli for data orchestration.
Why this beats prompting it yourself
Raw chat files are often too large for context windows and lack structure for precise querying. This skill adds a logic layer that ranks messages by rarity and forces the LLM to provide verifiable evidence through mandatory ID citations, preventing hallucinations.
Use cases
- Search years of chat history for specific mentions of contracts or agreements.
- Audit group chat activity for specific topics with chronological context.
- Export selected evidence from a conversation into a clean CSV for legal or personal record-keeping.
- Summarize a month of family or project updates with direct links to original messages.
Known limitations
Requires manual export of WhatsApp chats to .txt or .zip first. Only supports Python 3.11 or newer.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Requires Python 3.11+. User must manually provide WhatsApp .txt or .zip exports. Analysis is limited to the data imported into the local SQLite database.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 2 days ago
- Free with an Agensi account