Documentation
README
This is the opening of the README. Read the full README on GitHub.
Weak Agent Test is a Quality skill for Claude Code, published by kklimuk in docx-cli.
Weak Agent Test runs an adversarial harness that sends weak agents through real docx-cli document tasks and grades the results in Word. It is used to compare editing and authoring behavior, measure tool use and token cost, and produce a prioritized ergonomics report.
Weak Agent Test is cataloged under Quality on DirSkills. Weak Agent Test comes from a repository tagged agent-skills, ai-agents, anthropic-skills, claude-code and claude-skill.
Documentation
This is the opening of the README. Read the full README on GitHub.
Slash commands named in this skillโs SKILL.md, listed in the order they first appear.
/weak-agent-test/workflows/accountWeak Agent Test is one of 4 skills that DirSkills catalogs from kklimuk/docx-cli, the repository it ships in. Its siblings there include Commit, Docx CLI and Security Review. Each one is a separate skill with its own page in this directory, installs the same way Weak Agent Test does, and is maintained by kklimuk in that same repository. The rest of the collection is listed on the kklimuk/docx-cli page.
Weak Agent Test ranks #1547 by stars among the 1662 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Weak Agent Test against them. Open each page to compare what they document and how they install.
Weak Agent Test is one of 4 skills cataloged on DirSkills from kklimuk/docx-cli.
Weak Agent Test is one of 1662 Quality skills cataloged on DirSkills, ranked #1547 by stars among them.