Weak Agent Test

Q: What is a Claude Code skill and how does the Weak Agent Test skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Weak Agent Test is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the General category. Learn more at https://claudskills.com/learn/what-is-skill-md/.

Category: General · Sub-category: ai-tooling · Last updated: 2026-07-10

ai:agent

Run the weak-agent (Haiku) adversarial test harness against docx-cli. Spawns Haiku agents to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace, résumé styling, contract redlining + commenting, contract finalize via accept/reject + comment reply/resolve) and one authoring (T. S. Eliot poetry journal: multi-column, verse, footnotes, links, figure) — renders every result with Word, judges them, measures the Haiku tool economy (docx-cli vs other calls), and synthesizes a prioritized ergonomics report. Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.

Security AStatic scan found no risk patternsHow grading works ›

From the source SKILL.md

This harness answers one question: can weak agents (Haiku) actually use docx-cli to get real work done, and what should we fix first? It runs the weak-agent-test workflow (.claude/workflows/weak-agent-test.js), which fans out one Haiku agent per scenario, renders every output with Microsoft Word, grades each against ground-truth criteria, and synthesizes a prioritized improvement report.

<RUN_DIR>/
  REPORT.md            ← synthesized report (+ appended measured metrics)
  haiku-metrics.md     ← measured per-Haiku-agent tokens/time/tool split
  haiku-metrics.json
  benchmark.json       ← self-reported tool economy
  <key>/               ← one per scenario; the worked-on copy lives here
    task.md  assets/   ← (criteria.md is withheld from this copy — judge-only)
…

What this skill does

Weak Agent Test is a community-contributed Claude Code skill in the ai-tooling sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/weak-agent-test/ and loads when your prompt matches the skill's trigger.

When to invoke it: Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.

Who uses this skill

The Weak Agent Test Claude Code skill is built for Claude Code users and developers across all disciplines looking for general-purpose AI assistance. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 147,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/weak-agent-test
curl -L https://claudskills.com/skills/weak-agent-test/SKILL.md \
  -o ~/.claude/skills/weak-agent-test/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/weak-agent-test/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/weak-agent-test/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\weak-agent-test\SKILL.md on Windows. See the full install guide for step-by-step instructions.

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

See pricing → Download desktop app

Frequently asked questions

How do I install the Weak Agent Test Claude Code skill?

Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/weak-agent-test/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.

What does the Weak Agent Test skill do?

Is this skill free to install?

Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.

When should I use the Weak Agent Test skill?

Use Weak Agent Test when your Claude Code task falls under the General category — specifically in the ai tooling area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Weak Agent Test" or describe the task and let Claude pick). Browse related skills at /category/general/.

What is a Claude Code skill and how does the Weak Agent Test skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Weak Agent Test is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the General category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Source: https://github.com/kklimuk/docx-cli/blob/HEAD/.claude/skills/weak-agent-test/SKILL.md
License: MIT
Author: kklimuk

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA

kklimuk. (2026). Weak Agent Test [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/weak-agent-test/

BibTeX

@misc{weak-agent-test-2026,
  author    = {kklimuk},
  title     = {Weak Agent Test [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/weak-agent-test/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge

[![ClaudSkills](https://claudskills.com/badge/weak-agent-test.svg)](https://claudskills.com/skills/weak-agent-test/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)

Security scan

Grade A · scanned 2026-07-10 — free static scan against the OWASP Agentic Skills Top 10.

No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›

✓ Prompt injection
✓ Data exfiltration
✓ Supply chain
✓ Reverse shell
✓ Credentials
✓ Execution
✓ Filesystem
✓ Persistence
✓ Obfuscation
✓ Network

Show this grade on your repo (click to copy):

[![Security: A](https://img.shields.io/badge/Security-A-2e7d32)](https://claudskills.com/skills/weak-agent-test/#security)

More General skills

Browse all General skills in the ClaudSkills registry, or explore these other picks from the same category:

Browse all General skills → Top 100 skills

Part of ClaudSkills — the open registry for Claude Skills & Claude Code Skills. · What's New · Install guide · About · llms.txt

Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore