Linting 216 public Claude Code skills – 69% won't reliably trigger
Source
sgharlow
Author
sgharlow
Date
Key takeaways · AI-distilled
57% of the 87 sampled subagents (50) declare no `tools` list at all, which does not sandboxAn isolated environment where AI-generated code or agent actions run without being able to touch anything real.Full definition → them, it makes them inherit the caller's entire toolbox including Bash, the opposite of least privilege.
Adding subagents that grant bare Bash (16) or a wildcard (8) to the no-list group brings 85% of the 87-multi-agentUsing several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.Full definition → sample to broader-than-needed tool access.
Of 215 public skills scored for triggering reliability, 40% are outright unlikely to fire and another 28% are borderline, so 'my agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → never fires' traces to one frontmatter description line in most cases.
Only 1 of 216 skills and 0 of 87 subagents passed every check in the linter cleanly; 83% of subagents (72 of 87) also omit 'use when...' invocation cues from their description.
Secrets handling was the one area sampled artifacts got mostly right: only 6 of 216 skills tripped the scanner.
Terms in this piece · Glossary
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
Why it matters
Linting 216 public Claude Code skills found 69% have descriptions unlikely to reliably trigger, and 85% of subagents grant broader tool access (often unrestricted Bash) than their task needs, real, fixable failure modes in the skills ecosystem.
articleTowards a Risk Assessment of Malicious Skill Files in Coding AgentsRui Yang, Michael Fu, Kla Tantithamthavorn, Chetan Arora, Joey Chua
articleSkillWorks – every Claude Code skill, scored on whether it loadskyisaiah47
videoSkill issue: Lessons from skilling up coding agents to use Langfuse - Marc Klingen, ClickhouseAI Engineer