Is the Weak-Agent Test (docx-cli Harness) skill free?

Yes. The skill itself is free from kklimuk/docx-cli. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Weak-Agent Test (docx-cli Harness) SkillProof Score?

7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Weak-Agent Test (docx-cli Harness)?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Weak-Agent Test (docx-cli Harness) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Weak-Agent Test (docx-cli Harness)

Adversarial Haiku harness that stress-tests docx-cli on 6 real document tasks

by kklimuk · kklimuk/docx-cli

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 73aa534

This is an internal, repo-specific harness (frontmatter metadata internal:true): actually running it needs the full docx-cli checkout, a fresh bun build, the Claude Workflow runtime, six spawned Haiku sub-agents, and Microsoft Word for rendering, so its output could not be exercised and no delta was measured. Copying just the skill folder leaves it non-runnable because the central weak-agent-test.js workflow it invokes lives outside the skill dir under .claude/workflows/. The security scan was clean (the metrics script only reads local run transcripts). The SKILL.md is meticulous and honest about every prerequisite.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Weak-Agent Test (docx-cli Harness) does

Internal QA harness that spawns weak (Haiku) agents to perform six real document tasks with docx-cli, renders each result in Microsoft Word, grades them against ground-truth rubrics, and reports the Haiku tool economy. Triggers on 'weak agent test', 'run the haiku harness', or 'adversarial review'. Built for the kklimuk/docx-cli repo and needs the full checkout, a Workflow runtime, and Word on macOS.

How to install Weak-Agent Test (docx-cli Harness)

git clone https://github.com/kklimuk/docx-cli.git
mkdir -p ~/.claude/skills
cd docx-cli && cp -r .claude/skills/weak-agent-test ~/.claude/skills/weak-agent-test

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Weak-Agent Test (docx-cli Harness)

/weak-agent-test Adversarial Haiku harness that stress-tests docx-cli on 6 real document tasks

It also activates on plain-language prompts like these:

Run the adversarial Haiku harness against the docx-cli document tasks.
Stress-test docx-cli with weak sub-agents and grade the outputs.
Report the Haiku tool-call economy across the six document QA tasks.

Frequently asked questions

Is the Weak-Agent Test (docx-cli Harness) skill free?: Yes. The skill itself is free from kklimuk/docx-cli. SkillProof publishes the install command and an independent test verdict at no cost.
Does Weak-Agent Test (docx-cli Harness) work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. This is an internal, repo-specific harness (frontmatter metadata internal:true): actually running it needs the full docx-cli checkout, a fresh bun build, the Claude Workflow runtime, six spawned Haiku sub-agents, and Microsoft Word for rendering, so its output could not be exercised and no delta was measured. Copying just the skill folder leaves it non-runnable because the central weak-agent-test.js workflow it invokes lives outside the skill dir under .claude/workflows/. The security scan was clean (the metrics script only reads local run transcripts). The SKILL.md is meticulous and honest about every prerequisite.
What is the Weak-Agent Test (docx-cli Harness) SkillProof Score?: 7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Weak-Agent Test (docx-cli Harness)?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Weak-Agent Test (docx-cli Harness) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.