Skip to content

kklimuk/docx-cli / .claude/skills/weak-agent-test

weak-agent-test

Verified

Run the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) 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, has opus judge them against ground-truth rubrics, measures each exercise's tool economy, token cost, wall-clock, and correctness (from transcripts for Claude, the exercise.json ledger for the local harness), 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.

scenarios/eliot-journal/assets/frontispiece.svg

View on GitHub
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 360 280" width="360" height="280">
	<title>Frontispiece</title>
	<rect x="0" y="0" width="360" height="280" fill="#f7f3ea"/>
	<!-- double art-deco border -->
	<rect x="16" y="16" width="328" height="248" fill="none" stroke="#2f3b3a" stroke-width="3"/>
	<rect x="24" y="24" width="312" height="232" fill="none" stroke="#2f3b3a" stroke-width="1"/>
	<!-- corner squares -->
	<g fill="#2f3b3a">
		<rect x="20" y="20" width="6" height="6"/>
		<rect x="334" y="20" width="6" height="6"/>
		<rect x="20" y="254" width="6" height="6"/>
		<rect x="334" y="254" width="6" height="6"/>
	</g>
	<!-- art-deco sunburst rising from the horizon -->
	<g stroke="#2f3b3a" stroke-width="2">
		<line x1="180" y1="210" x2="180" y2="70"/>
		<line x1="180" y1="210" x2="140" y2="84"/>
		<line x1="180" y1="210" x2="220" y2="84"/>
		<line x1="180" y1="210" x2="104" y2="110"/>
		<line x1="180" y1="210" x2="256" y2="110"/>
		<line x1="180" y1="210" x2="76" y2="146"/>
		<line x1="180" y1="210" x2="284" y2="146"/>
	</g>
	<!-- horizon arcs -->
	<g fill="none" stroke="#2f3b3a" stroke-width="1.5">
		<path d="M96 210 A 84 84 0 0 1 264 210"/>
		<path d="M120 210 A 60 60 0 0 1 240 210"/>
	</g>
	<line x1="60" y1="210" x2="300" y2="210" stroke="#2f3b3a" stroke-width="2"/>
	<!-- monogram -->
	<text x="180" y="245" text-anchor="middle" font-family="Georgia, serif" font-size="18" fill="#2f3b3a" letter-spacing="3">T · S · E</text>
</svg>
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall