Stats
Actions
Tags
From agentops
Planted lint fixture for scripts/skill-eval.sh — intentionally broken front matter (missing name/id, empty description) and hardcoded AWS credentials.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentops:bad-skillThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Planted lint fixture for `scripts/skill-eval.sh`. Intentionally broken:
Planted lint fixture for scripts/skill-eval.sh. Intentionally broken:
this front matter omits name/id (missing required metadata), leaves the
description empty, and hardcodes an AWS key (a secret) in the code block below.
export AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE
export AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
npx claudepluginhub boshu2/agentops --plugin agentopsInternal development tool that validates all SKILL.md and agent .md files against the Claude Code spec. Checks frontmatter completeness, field validity, allowed-tools presence, line count, hardcoded paths, and description quality. Use when the user says "lint skills", "validate skills", "check skill quality", "run the linter", "are my skills valid", or before shipping changes to the skills repo.
Validates skills, agents, or plugins for token complexity, broken links, frontmatter issues, and structural problems. Invoke via /lint <path-to-skill-or-plugin>.
Validates bash/shell code blocks in Claude Code plugin .md files for syntax errors (bash -n), shellcheck pitfalls, macOS/Linux portability issues, unsafe commands, and runtime failures.