Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From harness-eval-lab
Run deterministic static analysis on the full agent setup (CLAUDE.md, skills, commands, hooks, agents, MCP configs). 35 rules + system-level analysis (token budget, trigger overlaps, dependencies, context utilization). No LLM. Use when the user wants a fast lint check, CI gate, or structural health report.
npx claudepluginhub redhat-community-ai-tools/harness-eval-labHow this skill is triggered — by the user, by Claude, or both
Slash command
/harness-eval-lab:eval-setup-lintThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run deterministic static analysis on the user's agent setup. No LLM involved. Fast, reproducible, CI-suitable.
Creates p5.js generative art with seeded randomness, noise fields, and interactive parameter exploration. Use for algorithmic art, flow fields, or particle systems.
Share bugs, ideas, or general feedback.
Run deterministic static analysis on the user's agent setup. No LLM involved. Fast, reproducible, CI-suitable.
/eval-setup-review.Before doing anything else, ask the user:
Where should i present the results?
- Terminal - print the report here in the conversation
- File - write a markdown report to a file (you'll choose the path)
Wait for their answer before proceeding.
Determine the setup path. If the user doesn't specify one, use the current working directory.
uv run python skills/eval-setup-lint/scripts/run_assessment.py <setup-path> recommended
If the user has a ~/.claude/ directory, pass it as the third argument for user-level config discovery:
uv run python skills/eval-setup-lint/scripts/run_assessment.py <setup-path> recommended ~/.claude
Read the JSON output.
Read report-format.md and format the results following that structure.
Include all sections: inventory, token budget, context utilization, trigger analysis, dependencies, findings, and inspection summary.
If the user chose terminal: print the report in the conversation.
If the user chose file: write the report as markdown to the path they specified (or suggest eval-setup-lint-report.md in the current directory). Tell them the file path when done.