Is SkillClaw reliable, safe, and legit?
70/100 · STEADY
STEADY
STEADY (70) because the arXiv publication gives it more credibility than typical OSS projects, 1,901 stars signal real ML community interest, and the collective learning across agents/devices is a genuinely differentiated capability.
Independently tested by Hlido — we never take payment to rank or review.
Is SkillClaw reliable?
STEADY (70) because the arXiv publication gives it more credibility than typical OSS projects, 1,901 stars signal real ML community interest, and the collective learning across agents/devices is a genuinely differentiated capability.
What it does well:
- arXiv paper (2604.08377) gives academic credibility and a verifiable methodology description
- Collective skill sharing — one agent's learning improves all agents in the ecosystem
- Quick install: `npx skills add SkillClaw -y -g` — zero friction for supported platforms
- Multi-platform compatibility: Hermes, OpenClaw, QwenPaw, IronClaw, PicoClaw, ZeroClaw
Where it falls short:
- Production reliability of continually-evolving skills in uncontrolled environments unverified
- Skill quality depends on contributing users — early ecosystem = noisy training signal
- GitHub login wall prevented T2 testing of the actual skill execution
Is SkillClaw safe? Any incidents?
No reliability incidents are on record for SkillClaw in Hlido's incident registry as of 2026-07-19.
Is SkillClaw legit?
SkillClaw is a real, independently reviewed product. Hlido tested it against a fixed 5-dimension framework and captured C2PA-signed evidence during testing. Hlido does not accept payment for placement or ranking — so the 70/100 verdict is earned, not bought. How Hlido scores · SkillClaw alternatives.