use-whatsapp
use-whatsapp is a Messaging & communication channels skill for AI agents, published by envhaven in the envhaven repository on GitHub. Skillspace rates use-whatsapp D (62/100) and it passed the safety scan; the rating is based on static analysis only.
Stand up a personal WhatsApp ↔ Claude Code bridge. The user messages a WhatsApp number from their phone and Claude Code (with full agent loop, file tools, bash) replies. Uses Anthropic subscription auth (no per-token charges). Per-chat session continuity, daily 5am session resets with pre-flush memory extraction, two-role LID whitelist (owner / read-only guest), group chat support with privacy mode (auto-allowed when the owner adds the bot), reply-to-message support, user-defined cron jobs scheduled in natural language, no slash commands. Optional auto-start (`/custom-cont-init.d/` on LinuxServer.io/EnvHaven, s6-rc, systemd-user, or launchd) so the bridge survives reboots. This skill builds a standalone Claude Code bridge.
- Grade
- D
- Quality
- 62 / 100
- Safety
- Passed
- GitHub stars
- 23
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 73 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.