Wacrawl
- 2 installs
- 167 repo stars
- Updated August 3, 2026
- steipete/wacrawl
Helps with ai & agent building tasks during AI-assisted development.
About
wacrawl is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.
- wacrawl
- AI & Agent Building
- AI-coding skill
Wacrawl by the numbers
- 2 all-time installs (skills.sh)
- Ranked #13,957 of 16,556 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/steipete/wacrawl --skill wacrawlAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 2 |
|---|---|
| repo stars | ★ 167 |
| Last updated | August 3, 2026 |
| Repository | steipete/wacrawl ↗ |
What it does
Helps with ai & agent building tasks during AI-assisted development.
Files
Wacrawl
Use this for WhatsApp Desktop archive questions. wacrawl is read-only against WhatsApp data and writes only its own archive.
Sources
- DB:
~/.wacrawl/wacrawl.db - Source:
~/Library/Group Containers/group.net.whatsapp.WhatsApp.shared - Repo:
~/Projects/wacrawl - CLI:
wacrawl
Refresh
Check source/archive health:
wacrawl doctorImport a fresh local snapshot:
wacrawl importInspect counts:
wacrawl statusEncrypted Git backup:
wacrawl backup status
wacrawl backup pushQuery Workflow
1. Refresh/import if the question depends on recent WhatsApp state. 2. Resolve chat, sender, date range, media needs, and keyword. 3. Use CLI for chats/messages/search; use JSON for scripts. 4. Report exact date spans, counts, chat names/JIDs, and import freshness.
Common commands:
wacrawl chats --limit 20
wacrawl messages --after 2026-01-01 --limit 50
wacrawl --json search "query" --from-themSafety
Do not write into the WhatsApp app container. Do not send messages; this tool is archive/read-only.
Verification
For repo edits:
go test ./...
make testThen smoke:
wacrawl doctor
wacrawl statusRelated skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10