Agent skill

Concentrate Forces

by HughYau in HughYau/qiushi-skill

集中兵力:多件事同时争抢时间、注意力或预算时,列出全部待办,选定唯一主攻目标并公开锁定,彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发;只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。

MITAuto-check passed

Install Concentrate Forces

skills CLI
$ npx skills add HughYau/qiushi-skill --skill concentrate-forces -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HughYau/qiushi-skill concentrate-forces --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HughYau/qiushi-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/concentrate-forces .claude/skills/concentrate-forces && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
concentrate-forces
GitHub stars
3.8k
Token cost
~379 tokens
SKILL.md length
65 words
Files
2
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

集中兵力:多件事同时争抢时间、注意力或预算时,列出全部待办,选定唯一主攻目标并公开锁定,彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发;只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。

  • Works in 7 steps: 盘点全部待办(宿主有 todo 工具就用它),每项标:影响范围 高 / 中 /… → 选唯一主攻,优先级 → 不打无准备之仗:对主攻目标是否已充分了解?没有 → 先… → …
  • Priorities sprawl
  • SKILL.md covers 用 / 不用, 操作规程, 输出模板 and 纪律, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Concentrate Forces is an agent skill from HughYau/qiushi-skill. 集中兵力:多件事同时争抢时间、注意力或预算时,列出全部待办,选定唯一主攻目标并公开锁定,彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发;只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。 English: Concentrate forces. When several tasks compete for time, attention, or budget, enumerate them, lock onto a single main target, finish and verify it completely, then move on. Trigger when priorities sprawl, effort is scattered, or you must decide what to do first; skip when there is one task, tasks are independent and parallel, or the user explicitly wants them advanced together.

Its SKILL.md is about 380 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `original-texts.md`).

The repository describes itself as: Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done… The licence is MIT.

When your agent uses it

  • Priorities sprawl
  • Effort is scattered
  • You must decide what to do first
  • Skip when there is one task

Example prompts

  • “每件都做了一点但都没做完”
  • “/concentrate-forces”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 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。
  2. 选唯一主攻,优先级
  3. 不打无准备之仗:对主攻目标是否已充分了解?没有 → 先 investigation-first。
  4. 宣告并锁定(模板见下)。
  5. 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"。
  6. 彻底 + 验证:解决到确认不留后患为止,不做一半就转向。
  7. 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。

What it can do on your machine

Read from SKILL.md and the folder at commit 5ace717. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Concentrate Forces loads about 379 tokens when it runs. Until then it costs about 135 tokens; SKILL.md has 65 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~135
When it runs · the whole SKILL.md, loaded when a task matches
~379

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HughYau/qiushi-skill at commit 5ace717, republished under its MIT licence (© HughYau). 65 words, ~379 tokens.

Download SKILL.mdSave it as .claude/skills/concentrate-forces/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
concentrate-forces
description
集中兵力:多件事同时争抢时间、注意力或预算时,列出全部待办,选定唯一主攻目标并公开锁定,彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发;只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。 English: Concentrate forces. When several tasks compete for time, attention, or budget, enumerate them, lock onto a single main target, finish and verify it completely, then move on. Trigger when priorities sprawl, effort is scattered, or you must decide what to do first; skip when there is one task, tasks are independent and parallel, or the user explicitly wants them advanced together.

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

  1. 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。
  2. 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。
  3. 不打无准备之仗:对主攻目标是否已充分了解?没有 → 先 investigation-first。
  4. 宣告并锁定(模板见下)。
  5. 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"。
  6. 彻底 + 验证:解决到确认不留后患为止,不做一半就转向。
  7. 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

© HughYau, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/concentrate-forces of HughYau/qiushi-skill.

  • SKILL.md
  • original-texts.md

Open the folder on GitHubat commit 5ace717

Compare with similar skills

Concentrate Forces next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Concentrate Forces compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Concentrate Forces this skillHughYau/qiushi-skill3.8k—~379Automated safety check: PassMIT
Porters Five Forcesphuryn/pm-skills27k—~2kAutomated safety check: PassMIT
Detecting Rdp Brute Force Attacksmukul975/Anthropic-Cybersecurity-Skills34k—~779Automated safety check: PassApache-2.0
Hunt Brute Forcesickn33/agentic-awesome-skills47k1 repos~4.9kAutomated safety check: PassMIT
Porters Five Forcesdeanpeters/Product-Manager-Skills7.2k—~2.7kAutomated safety check: PassCustom licence
Maoxuan Concentrated Forcechinapathbreaker/mao-skill131—~840Automated safety check: PassNone

Similar skills

  • Porters Five Forces

    phuryn/pm-skills

    Perform Porter's Five Forces analysis — competitive rivalry, supplier power, buyer power, threat of substitutes, and threat of new entrants.

    27k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Detecting Rdp Brute Force Attacks

    mukul975/Anthropic-Cybersecurity-Skills

    Detect RDP brute force attacks by parsing Windows Security Event Logs (EVTX files, via python-evtx) for failed logon patterns (Event ID 4625, Logon Type 10/3), correlating with successful logons…

    34k GitHub stars~779 tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Hunt Brute Force

    sickn33/agentic-awesome-skills

    Hunt Missing/Weak Rate Limiting

    47k GitHub starsUsed in 1 repo~4.9k tokens
    Backend & APIsAuto-check passed
  • Porters Five Forces

    deanpeters/Product-Manager-Skills

    Read an industry's structure through Porter's Five Forces with documented signals per rating, ending at the profit pool.

    7.2k GitHub stars~2.7k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Maoxuan Concentrated Force

    chinapathbreaker/mao-skill

    用户在资源有限、不知道精力怎么分配、想要在某个领域形成突破时,应激活此skill. An agent skill from chinapathbreaker/mao-skill.

    131 GitHub stars~840 tokensUpdated 5 mo ago
    Auto-check passed
  • Ackman Concentrated Activism

    questflowai/investorskills

    A skill your agent uses when evaluating Bill Ackman-style concentrated long theses, activist campaigns, high-conviction multiyear bets, and public narrative plus fundamental catalysts.

    1.9k GitHub stars~491 tokensUpdated 1 mo ago
    Auto-check passed

More from HughYau/qiushi-skill

All 11 skills in this repo
  • Contradiction Analysis

    HughYau/qiushi-skill

    矛盾分析法:把复杂问题拆成若干对立面,找出规定其他矛盾的主要矛盾及其主要方面,判定对抗性 / 非对抗性,并据此选择处理方式。当问题头绪多、多个因素互相牵制、优先级不清、根因不明、反复修不好、trade-off 说不清时触发;直接执行类任务或用户已定方案时不触发。

    3.8k GitHub stars~485 tokensUpdated 9 days ago
    Auto-check passed
  • Criticism Self Criticism

    HughYau/qiushi-skill

    批评与自我批评:在工作完成、阶段验收、收到批评或同类错误反复出现时,对成果和过程做诚实、具体、基于事实的审视,输出可执行的改进项,并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗";任务刚开始或只是单步查询时不触发。

    3.8k GitHub stars~423 tokensUpdated 9 days ago
    Auto-check passed
  • Investigation First

    HughYau/qiushi-skill

    调查研究:在下判断、做决策、给建议之前,先用第一手材料弄清现状,产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发;已充分调查后的执行阶段不要重复触发。

    3.8k GitHub stars~425 tokensUpdated 9 days ago
    Auto-check passed
  • Mass Line

    HughYau/qiushi-skill

    群众路线:从持有真实情况的多方(用户、使用者、代码库、日志、运行结果)收集分散意见,系统化为方案,再带回去对齐与检验,循环改进。当多方意见分歧、需要汇总零散反馈、方案要拿回给真实使用者确认、或你发觉自己在闭门造车时触发;信息源单一且完整、处于执行阶段时不触发。

    3.8k GitHub stars~467 tokensUpdated 9 days ago
    Auto-check passed
  • Overall Planning

    HughYau/qiushi-skill

    统筹兼顾:当多个目标、指标或利益方相互制约、优化一项会伤害另一项时,识别全部辩证关系对,检查片面性,为每对关系定出当前阶段的侧重与底线,评估系统性影响,并设失衡预警。触发信号包括 trade-off、目标冲突、速度 vs 质量、短期 vs 长期、"顾此失彼";只有单一目标、用户已定取舍、或属硬性二选一时不触发。

    3.8k GitHub stars~416 tokensUpdated 9 days ago
    Auto-check passed
  • Practice Cognition

    HughYau/qiushi-skill

    实践认识论:把方案、假说或判断放回实践中检验,按「实践 → 认识 → 再实践」螺旋迭代,并在开始前写明循环终止条件。当你提出了假说要验证、一次尝试失败要复盘再来、发现自己只想不做或只做不想时触发;一次性输出、答案可直接查阅、还没形成假说(先调查)时不触发。

    3.8k GitHub stars~416 tokensUpdated 9 days ago
    Auto-check passed

Questions about Concentrate Forces

What does Concentrate Forces do?

集中兵力:多件事同时争抢时间、注意力或预算时,列出全部待办,选定唯一主攻目标并公开锁定,彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发;只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。. Concentrate Forces is an agent skill from HughYau/qiushi-skill. 集中兵力:多件事同时争抢时间、注意力或预算时,列出全部待办,选定唯一主攻目标并公开锁定,彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发;只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。 English: Concentrate forces.

When should I use Concentrate Forces?

Concentrate Forces fits situations like: priorities sprawl; effort is scattered; you must decide what to do first; skip when there is one task.

How do I install Concentrate Forces in Claude Code?

Run `npx skills add HughYau/qiushi-skill --skill concentrate-forces -a claude-code`. Or copy the skill folder (skills/concentrate-forces in HughYau/qiushi-skill) into .claude/skills/concentrate-forces in your project. Claude Code loads it when a task matches its description.

How do I install Concentrate Forces in Codex?

Run `npx skills add HughYau/qiushi-skill --skill concentrate-forces -a codex`. Or copy the skill folder (skills/concentrate-forces in HughYau/qiushi-skill) into .agents/skills/concentrate-forces in your project. Codex loads it when a task matches its description.

Can I use Concentrate Forces in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HughYau/qiushi-skill --skill concentrate-forces -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/concentrate-forces, .gemini/skills/concentrate-forces, .github/skills/concentrate-forces and .opencode/skills/concentrate-forces in your project.

What does Concentrate Forces need to run?

SKILL.md names no scripts, command-line tools or credentials: Concentrate Forces is instructions for the agent only.

Does Concentrate Forces access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Concentrate Forces safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Concentrate Forces use?

Concentrate Forces is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Concentrate Forces use?

About 379 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Concentrate Forces?

Skills that share tags, products or a category with Concentrate Forces: Porters Five Forces (phuryn/pm-skills, 27k stars), Detecting Rdp Brute Force Attacks (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Hunt Brute Force (sickn33/agentic-awesome-skills, 47k stars) and Porters Five Forces (deanpeters/Product-Manager-Skills, 7.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Concentrate Forces?

HughYau (a GitHub user) maintains it in HughYau/qiushi-skill, which has 3,812 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 1, 2026.

Source: HughYau/qiushi-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.