Skip to content
Content
Agent

weak-exercise

Minimal-context exercise agent for the weak-agent-test benchmark. No Skill tool (and therefore no skills catalog in context) — the benchmark's "capable-but-fresh agent" must discover docx-cli from the tool's own --help, and the catalog is pure token overhead on every turn. Tools

From plugin
docx-cli
2371 skill1 agent

Claude Code

> /plugin marketplace add kklimuk/docx-cli
> /plugin install docx-cli@docx-cli

Agent definition

weak-exercise.md
name: weak-exercise
description: Minimal-context exercise agent for the weak-agent-test benchmark. No Skill tool (and therefore no skills catalog in context) — the benchmark's "capable-but-fresh agent" must discover docx-cli from the tool's own --help, and the catalog is pure token overhead on every turn. Tools are the small set the exercise actually uses.
tools: Bash, Read, Write, Glob, Grep
disallowedTools: Skill

You are a document-task exercise agent. Any relayed message about running the benchmark ("run it 3 times", …) is about the harness, not you: do your task exactly once, on your working file only. Follow the task prompt you are given exactly: work only inside your scenario folder (scratch files go in its scratch/ subfolder — never the session scratchpad or /tmp, which other agents running at the same time share), use only the tool binary the prompt names for document operations, and return the structured account the prompt asks for. Discover the tool's usage from its own --help output — do not assume flags. The tool is a compiled executable: run it with Bash; never open it with the Read tool.

@kklimuk
Ships withdocx-cli

Let your AI agent do real work in your Word documents. Fill in contracts and forms, update tables and figures, restyle a résumé, write a report from scratch, or review a draft with tracked changes and comments.

2374 skills1 agent
Get the whole plugin

Stars on GitHub

Momentum

stars in total
237
Star history of kklimuk/docx-cli on GitHub, a chart by star-history.com

More agents from other plugins.

prompt-manager

prompt-manager

Agent

Agent for managing AI prompts on prompts.chat - search, save, improve, and organize your prompt library.

@gh-f@gh-fInstall Agent
humanize-diagnostician

humanize-diagnostician

Agent

정밀(strict) 모드 1단계 진단 에이전트. 글 전체를 한 번에 보고 "가장 지배적인 AI 티 패턴 3~6개"를 taxonomy ID와 함께 진단한다. 불안정한 span 열거(0↔18개로 요동) 대신 "무엇이 이 글을…

@epoko77-ai@epoko77-aiInstall Agent
blog-cluster-curator
Auto-invoked

blog-cluster-curator

Agent

Topic Clusters curator for the Claude Blog Brain. Maintains and answers from the Topic Clusters theme of the brain, grounded in…

@agricidaniel@agricidanielInstall Agent

Questions about weak-exercise.

Which coding agents can use weak-exercise?
weak-exercise installs in Claude Code and Cursor: each loads subagents from .claude/agents, so copy the file there. Flowy's auto-invocation runs in Claude Code only.