Runs evaluation of work against user-provided criteria.
npx skills add https://github.com/hafidzlvm/opencode --skill eval-hafidzlvm
Please help me install this Agent Skill. Skill: eval Source: https://github.com/hafidzlvm/opencode/tree/main/.dsh/skills/eval Command: npx skills add https://github.com/hafidzlvm/opencode --skill eval-hafidzlvm
High-intent search queries and answers about installing and using this skill.
Invoke /eval followed by your criteria as text. The skill treats everything you provide after the command as arguments and evaluates the current work against those criteria.
The eval command accepts free-form text arguments representing the evaluation criteria. These arguments are passed into the evaluation instructions defined in the referenced command file.
The evaluation instructions are defined in an external file referenced as commands/eval.md, which is loaded when the skill runs. The SKILL.md file itself only wires the command invocation to that file.
The skill depends on an external commands/eval.md file that is not included in the skill directory, so its detailed behavior is defined elsewhere. It also requires the user to supply criteria explicitly as arguments.
liuminxin45Evaluate AI-driven code changes against acceptance rubrics and report PASS, FAIL, or BLOCKED outcomes.
Ethical-AI-SyndicateEvaluate completed work items against Definition of Done checklists and generate gap reports.
DevMHOneAutomates the creation and execution of LLM benchmark evaluation suites via CLI.
zh667Automate end-to-end verification of code changes across builds, tests, linting, and security checks.
