Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Analyzes a real-world problem with methods adapted from Mao Zedong's Selected Works: separating facts from inference, finding the main contradiction and setting next steps.
SKILL.md written in Chinese; this summary is our English description.
Install Maoxuan Problem Analysis
$ npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install SamadhiFire/xinqingnian-maoxuan-skill xinqingnian-maoxuan-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "xinqingnian-maoxuan-skill" agent skill from https://github.com/SamadhiFire/xinqingnian-maoxuan-skill/tree/main into .claude/skills/xinqingnian-maoxuan-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xinqingnian-maoxuan-skill", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install SamadhiFire/xinqingnian-maoxuan-skill xinqingnian-maoxuan-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xinqingnian-maoxuan-skill" agent skill from https://github.com/SamadhiFire/xinqingnian-maoxuan-skill/tree/main into .agents/skills/xinqingnian-maoxuan-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xinqingnian-maoxuan-skill", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install SamadhiFire/xinqingnian-maoxuan-skill xinqingnian-maoxuan-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "xinqingnian-maoxuan-skill" agent skill from https://github.com/SamadhiFire/xinqingnian-maoxuan-skill/tree/main into .cursor/skills/xinqingnian-maoxuan-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xinqingnian-maoxuan-skill", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install SamadhiFire/xinqingnian-maoxuan-skill xinqingnian-maoxuan-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "xinqingnian-maoxuan-skill" agent skill from https://github.com/SamadhiFire/xinqingnian-maoxuan-skill/tree/main into .gemini/skills/xinqingnian-maoxuan-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xinqingnian-maoxuan-skill", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install SamadhiFire/xinqingnian-maoxuan-skill xinqingnian-maoxuan-skillInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "xinqingnian-maoxuan-skill" agent skill from https://github.com/SamadhiFire/xinqingnian-maoxuan-skill/tree/main into .github/skills/xinqingnian-maoxuan-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xinqingnian-maoxuan-skill", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install SamadhiFire/xinqingnian-maoxuan-skill xinqingnian-maoxuan-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "xinqingnian-maoxuan-skill" agent skill from https://github.com/SamadhiFire/xinqingnian-maoxuan-skill/tree/main into .opencode/skills/xinqingnian-maoxuan-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xinqingnian-maoxuan-skill", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
xinqingnian-maoxuan-skill- GitHub stars
- 364
- Token cost
- ~874 tokens
- SKILL.md length
- 124 words
- Files
- 82 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Analyzes a real-world problem with methods adapted from Mao Zedong's Selected Works: separating facts from inference, finding the main contradiction and setting next steps.
- Works in 6 steps: 服从用户明确的任务、输出形式和合理限制。 → 处理安全、医疗、法律、财务、暴力、胁迫等高风险边界。 → 区分事实、推断、传闻和未知项，不把方法论变成贴标签或敌我化语言。 → …
- Breaking down a tangled team or project problem when you name this method
- SKILL.md covers 优先级, 信息决策门, 核心工作流 and 回复方式, plus 2 more sections
- Deciding which of several competing issues is the main contradiction
What it does
The skill is written in Chinese and turns ideas from Mao Zedong's Selected Works into a modern analysis routine. It is meant to run only when you ask for these methods by name or concept, for example the main contradiction, investigation and research, the united front, stage judgment or testing in practice, and not whenever a problem is merely complex. It avoids quoting slogans or role-playing, and works by checking facts, separating appearance from structure, finding the dominant issue, judging the stage and setting a central task.
Replies follow a fixed three-part shape: set out the situation, find what governs the whole, and say what to do first. The skill first judges whether your input is enough, asks at most two high-value questions when it is not, and handles safety, medical, legal, financial and violence risks before any analysis. Reference files hold method cards, clarification rules, risk boundaries and HTML output templates, and an examples folder shows a first-round clarification.
When your agent uses it
- Breaking down a tangled team or project problem when you name this method
- Deciding which of several competing issues is the main contradiction
- Planning an investigation before committing to a decision
Example prompts
- “Use the main contradiction method to analyze why our team keeps missing deadlines.”
- “Apply the investigation and research approach to our drop in customer renewals and tell me what to find out first.”
- “Judge what stage our side project is in and set the central task for the next month.”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- 服从用户明确的任务、输出形式和合理限制。
- 处理安全、医疗、法律、财务、暴力、胁迫等高风险边界。
- 区分事实、推断、传闻和未知项，不把方法论变成贴标签或敌我化语言。
- 判断信息是否足以支持分析，再决定直接回答还是澄清。
- 选择最少的方法卡，给出判断、依据、边界和下一步。
- 保留毛选方法的论证节奏和推进感，不把回答磨平成普通咨询话术。
What it can do on your machine
Read from SKILL.md and the folder at commit 4382484. 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
Ships 1 file in scripts/, which the agent can run.
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
Maoxuan Problem Analysis loads about 874 tokens when it runs, and up to ~73k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 124 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from SamadhiFire/xinqingnian-maoxuan-skill at commit 4382484, republished under its MIT licence (© SamadhiFire). 124 words, ~874 tokens.
Download SKILL.mdSave it as
.claude/skills/xinqingnian-maoxuan-skill/SKILL.md (or your agent's skills folder). This skill also uses 81 other files; get the full folder from GitHub.- name
- xinqingnian-maoxuan-skill
- description
- Apply modern problem-analysis methods adapted from Mao Zedong's Selected Works. Use only when the user explicitly asks for 毛选、教员、新青年、主要矛盾、调查研究、统一战线、阶段判断、实践检验等相关方法来分析现实问题，or explicitly invokes $xinqingnian-maoxuan-skill. Do not trigger merely because a work, relationship, learning, decision, self-management, or team problem is complex.
新青年·毛选拆局
把《毛泽东选集》中可复用的方法翻译成现代问题分析流程。不要复述语录、模仿政治口号或进行角色扮演；重点是校准事实、识别主导结构、判断阶段、配置资源并形成可执行路线。
这个 skill 的辨识度来自毛选式的认识和工作方法，而不只是方法卡名称。除安全危机外，回答应让用户感到分析在做这些事：从具体情况出发，分清现象和结构，抓住当前主导问题，结合阶段与力量条件确定中心任务，再交给实践检验。详细规则见 maoxuan-reasoning-style.md。
优先级
按下面顺序执行；前面的规则覆盖后面的流程偏好：
- 服从用户明确的任务、输出形式和合理限制。
- 处理安全、医疗、法律、财务、暴力、胁迫等高风险边界。
- 区分事实、推断、传闻和未知项，不把方法论变成贴标签或敌我化语言。
- 判断信息是否足以支持分析，再决定直接回答还是澄清。
- 选择最少的方法卡，给出判断、依据、边界和下一步。
- 保留毛选方法的论证节奏和推进感，不把回答磨平成普通咨询话术。
命中高风险信号时，先读 safety-escalation.md。必要时先给最低限度的安全处置，再继续分析；不要为了走完澄清流程延误止损。
信息决策门
不要机械地把所有任务都变成多轮问卷。先判断当前输入属于哪一路：
- 信息足够：直接重述问题并分析，不额外追问。
- 基本足够但有缺口：基于现有信息给暂定判断，显式写出关键假设与不确定性；只有结论被一个分叉点卡住时，补
1个问题。 - 严重不足：首轮最多问
2个高杠杆问题，优先补目标和最近一次关键事件。后续每轮通常只补1个关键缺口。 - 紧急或高风险：先处理安全、止损或专业求助入口，再问必要信息。
如果用户明确要求“基于现有信息先分析”“不要追问”或“给我一个初判”，就直接给有限结论，并标注依据、假设和置信度。
完整判断规则看 ambiguity-gate.md。需要追问时再读 intake-flow.md 和 choice-question-format.md。
核心工作流
- 锁定用户要推进的结果；不要先替用户决定目标。
- 区分关键事件、人物/对象、位置与控制点、已做尝试、约束和底线。
- 信息足够后，用 problem-restatement.md 压成稳定问题。
- 按需进入 problem-taxonomy.md 和 scene-index.md。分类与场景主要用于内部路由，不必机械展示给用户。
- 从 method-index.md 只选当前最需要的
1到2张方法卡。 - 命中高风险术语或表达时，读 misuse-boundaries.md 和 translation-red-lines.md。
- 输出判断、证据、替代解释、行动路线、观察信号与止损条件。
- 正式分析前读 maoxuan-reasoning-style.md，根据问题风险和复杂度选择语言强度。
- 用户要 HTML 时，再读 output-mode-routing.md 和
references/html-output/。
回复方式
除安全危机和用户明确要求极短格式外，每轮回复使用稳定的外显三结构：
先把情况摆清：事实、目标、已知与未知。再看什么牵住全局：现象与结构、主次、阶段和控制点。眼下先做什么：中心任务、先后手、追问或实践检验。
三段功能和顺序固定，标题可以随语境自然变化，不逐字复读同一句话。
- 澄清阶段：第一段摆已知，第二段说明关键缺口，第三段问最少的问题。
- 分析阶段：第一段摆事实，第二段形成主导判断，第三段给行动与检验。
- 方案阶段：直接在第三段给路线，不重新打开长问卷。
- 用户要求简短时，压缩格式；用户要求完整报告时，再展开结构。
- 可以使用“毛选方法”“调查研究”“主要矛盾”等术语，但要随即翻成现代工作语言，不堆口号。
- 非安全场景不要完全隐去方法气质。简短回答至少体现一个分层判断和一个中心动作；正式分析通常体现
摆情况 / 分层次 / 抓主导 / 看阶段 / 定中心任务 / 实践检验中至少三步。
详细写法看 round-response-structure.md。
硬边界
- 不把人简单分成敌我、先进落后或可清洗对象。
- 不生成操控、羞辱、胁迫、报复、孤立或煽动冲突的策略。
- 不把单次事件直接上升为“主要矛盾”或阶段变化。
- 不把医疗、法律、财务或人身安全问题伪装成普通结构分析。
- 不为显示方法感而强行使用战争、斗争、整顿等高压词汇。
- 不声称现代结论是原文的直接结论；区分
原文依据 / 现代转译 / 本次推断。
按需读取地图
- 总导航：references/README.md
- 澄清与防漂移：
references/clarification/ - 分类与场景：
references/categories/、references/scenarios/ - 方法卡：
references/methods/ - 方法气质与表达：maoxuan-reasoning-style.md
- 风险与安全：
references/risks/ - 输出路由：
references/routing/ - HTML 报告：
references/html-output/
一句话总纲：先判断是否需要问，再把事实压稳；只调用必要的方法，给出有限、可验证、能行动的结论。
© SamadhiFire, 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 81 other files (scripts, references) in the repository root of SamadhiFire/xinqingnian-maoxuan-skill.
- SKILL.md
- .editorconfig
- .gitattributes
- .gitignore
- .nojekyll
- LICENSE
- README.md
- agents/openai.yaml
- examples/screenshots/ChatGPT Image 2026年4月9日 23_34_06.png
- examples/screenshots/sample-org-fork-01-cover.png
- examples/screenshots/sample-org-fork-02-relation-graph.png
- examples/screenshots/sample-org-fork-03-main-route.png
- examples/screenshots/sample-org-fork-04-actions-evidence.png
- examples/screenshots/sample-org-fork-05-control-points.png
- examples/screenshots/sample-org-fork-06-people-details.png
- examples/screenshots/sample-org-fork-07-structure-routes.png
- examples/screenshots/sample-org-fork-08-method-sources.png
- examples/模糊输入首轮澄清示例.md
- … and 64 more
Open the folder on GitHubat commit 4382484
Compare with similar skills
Maoxuan Problem Analysis 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Maoxuan Problem Analysis this skillSamadhiFire/xinqingnian-maoxuan-skill | 364 | — | ~874 | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Interview Meaddyosmani/agent-skills | 105k | 6 repos | ~3.8k | Automated safety check: Pass | MIT | |
| OpenSpec Guided OnboardingFission-AI/OpenSpec | 72k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Writing Plansgeeksblabla/stateofdev.ma | 163 | 58 repos | ~661 | Automated safety check: Pass | None | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None |
Similar skills
Interview Me
addyosmani/agent-skills
Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.
OpenSpec Guided Onboarding
Fission-AI/OpenSpec
Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.
Writing Plans
geeksblabla/stateofdev.ma
A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Planning With Files
jd-opensource/JoySafeter
Implements Manus-style file-based planning for complex tasks.
Related
Categories
Questions about Maoxuan Problem Analysis
What does Maoxuan Problem Analysis do?
Analyzes a real-world problem with methods adapted from Mao Zedong's Selected Works: separating facts from inference, finding the main contradiction and setting next steps. The skill is written in Chinese and turns ideas from Mao Zedong's Selected Works into a modern analysis routine. It is meant to run only when you ask for these methods by name or concept, for example the main contradiction, investigation and research, the united front, stage judgment or testing in practice, and not whenever a problem is merely complex.
When should I use Maoxuan Problem Analysis?
Maoxuan Problem Analysis fits situations like: breaking down a tangled team or project problem when you name this method; deciding which of several competing issues is the main contradiction; planning an investigation before committing to a decision.
How do I install Maoxuan Problem Analysis in Claude Code?
Run `npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a claude-code`. Or copy the skill folder (the SamadhiFire/xinqingnian-maoxuan-skill repository) into .claude/skills/xinqingnian-maoxuan-skill in your project. Claude Code loads it when a task matches its description.
How do I install Maoxuan Problem Analysis in Codex?
Run `npx skills add SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a codex`. Or copy the skill folder (the SamadhiFire/xinqingnian-maoxuan-skill repository) into .agents/skills/xinqingnian-maoxuan-skill in your project. Codex loads it when a task matches its description.
Can I use Maoxuan Problem Analysis 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 SamadhiFire/xinqingnian-maoxuan-skill --skill xinqingnian-maoxuan-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xinqingnian-maoxuan-skill, .gemini/skills/xinqingnian-maoxuan-skill, .github/skills/xinqingnian-maoxuan-skill and .opencode/skills/xinqingnian-maoxuan-skill in your project.
What does Maoxuan Problem Analysis need to run?
SKILL.md names no scripts, command-line tools or credentials: Maoxuan Problem Analysis is instructions for the agent only.
Does Maoxuan Problem Analysis 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 Maoxuan Problem Analysis 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Maoxuan Problem Analysis use?
Maoxuan Problem Analysis is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Maoxuan Problem Analysis use?
About 874 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 72k tokens, read only when the agent opens those files.
What are the alternatives to Maoxuan Problem Analysis?
Skills that share tags, products or a category with Maoxuan Problem Analysis: Executing Plans Inline (obra/superpowers, 297k stars), Interview Me (addyosmani/agent-skills, 105k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 72k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Maoxuan Problem Analysis?
SamadhiFire (a GitHub user) maintains it in SamadhiFire/xinqingnian-maoxuan-skill, which has 364 GitHub stars. The repository was last updated on August 12, 2026.
Source: SamadhiFire/xinqingnian-maoxuan-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.