Qiushi-Skill is a collection of agent skills that turn dialectical materialist and practical philosophy into methods for investigating problems, identifying their central contradiction, testing conclusions, and continuing work. It is intended to guide AI agents through analysis and task execution. The catalogue entries are its skills, commands, hook, plugin, and agent components.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HughYau/qiushi-skill --skill concentrate-forcesgit clone --depth 1 https://github.com/HughYau/qiushi-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hughyau/qiushi-skill/concentrate-forces)<a href="https://agentmods.dev/skills/hughyau/qiushi-skill/concentrate-forces"><img src="https://agentmods.dev/badge/skills/hughyau/qiushi-skill/concentrate-forces/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hughyau/qiushi-skill/concentrate-forces"><img src="https://agentmods.dev/badge/skills/hughyau/qiushi-skill/concentrate-forces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00187 | $0.00800 |
| Opus 5 | $0.00093 | $0.00400 |
| Sonnet 5 | $0.00037 | $0.00160 |
| Haiku 4.5 | $0.00019 | $0.00080 |
Grade A, and why
concentrate-forces scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
集中兵力
"伤其十指不如断其一指。" —— 《中国革命战争的战略问题》
用 / 不用
用：
- 多个任务或问题同时摆在面前
- 正在同时推进多件事，但哪件都没做好
- 面对一个大问题，要决定从哪部分突破
不用：
- 只有一个任务
- 任务彼此独立、无资源竞争，可以并行
- 用户明确要求同时推进（用户指令优先）
- 已在执行选定的主攻，不需要重新决策
操作规程
- 盘点全部待办（宿主有 todo 工具就用它），每项标：影响范围 高 / 中 / 低、难度 高 / 中 / 低、是否被其他任务依赖。
- 选唯一主攻，优先级：
- 首选：影响高 + 被依赖（解锁阻塞）
- 次选：影响高 + 难度中（性价比最高）
- 末选：难度低（先易后难，积累势能）
主攻目标最好就是主要矛盾；不确定时先
contradiction-analysis。
- 不打无准备之仗：对主攻目标是否已充分了解？没有 → 先
investigation-first。 - 宣告并锁定（模板见下）。
- 执行期规则：新需求进来先问"属于当前主攻范围吗？"是 → 纳入；否 → 记入待办并告知"当前集中处理 X，完成后立即处理"。
- 彻底 + 验证：解决到确认不留后患为止，不做一半就转向。
- 战役间隙：完成后短暂总结，重估剩余任务（第一个的解决可能改变了格局），再选下一个。
输出模板
🎯 当前主攻目标：……
原因：……
完成信号：……（可观测）
暂缓（主攻完成后处理）：
- ……：为何暂缓
- ……
纪律
- 同一时间只有一个主攻目标。
- 击溃十个不如歼灭一个：解决一半就转向等于没解决。
- 先打分散孤立之敌，后打集中强大之敌。
交接
- 主攻完成 →
criticism-self-criticism短复盘 → 回到第 1 步选下一个 - 主攻方向本身拿不准 →
contradiction-analysis
原著依据：original-texts.md
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · -93 lines · +82 tokens per session a0a1b973bfa7
- 11d ago First seen · 156 lines · 105 tokens per session scan A 3193bf1e295a
concentrate-forces is a skill published in the GitHub repository HughYau/qiushi-skill (3,772 stars, last pushed 4d ago), licensed MIT. It adds 187 tokens to every session and 800 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
listenhub-tts
A text-to-speech tool that uses the ListenHub service to turn written text into audio, including short recordings, multi-speaker scripts, and long-form streamed speech.
article-icons
A tool that adds static inline SVG icons from itshover.com to Markdown, HTML, and similar articles.
ship-it
A GitHub workflow for finishing an implemented issue: commit the relevant changes, push a branch, create a pull request, merge it, and close the issue. GitHub is a service for hosting code and reviewing changes, and a pull request is a proposed change for review.
fix-pr-review-loop
Use when the user asks to fix a PR review and drive it to approval autonomously — "fix the PR review and loop until approved", "fix-pr-review-loop", "keep addressing review comments until this PR is approved". Takes an optional PR number/URL (defaults to the current branch's PR). Repeatedly calls fix-pr-review, waits…