원클릭으로 Manus에서 모든 스킬 실행

minimize-change-router

스타7

포크1

업데이트2026년 4월 19일 21:55

Dispatcher that routes to one of two sub-skills whenever a change-related concern surfaces. Load this skill whenever the user pushes back on a rule/code change with phrases like "这不通用" / "不是 general" / "修修补补" / "又在打补丁" / "抽象层不对" / "patching" / "补丁" / "画蛇添足" / "改得太多" / "别动其他东西" / "最小修改" / "我没让你做那个" / "顺手改" / "minimum modification" / "scope creep", AND self-trigger internally whenever the AI is about to (a) add a sibling rule to an existing rule system or (b) touch more than ~5 lines of code or docs. This router does no work itself; it only selects the correct sub-skill. Trigger aggressively — undertriggering leaves the AI to patch-and-sprawl without guardrails.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

gyy0592

gyy0592/claude-config

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

minimize-change-router

Purpose

Dispatcher. Holds no content of its own. Picks exactly one of two sub-skills and hands off.

Dispatch table

Trigger class A (abstraction-level complaint about rules/docs):

User phrases: "不通用" / "不是 general" / "修修补补" / "又在打补丁" / "抽象层不对" / "patching" / "补丁" / "这条规则是 X 的特例" / "sibling rule smell"
Self-trigger: AI about to add a new rule to an existing rule list
Action: stop. Read /home/yguo173/.claude/skills/general-rule-vs-patch/SKILL.md. Follow its definitions before proposing any rule change.

Trigger class B (scope/diff-size complaint about code/doc edits):

User phrases: "最小修改" / "别动其他东西" / "改得太多" / "画蛇添足" / "我没让你做那个" / "顺手改" / "minimum modification" / "scope creep" / "only fix X"
Self-trigger: AI about to modify more than about 5 lines, or touch files outside the literal target of the user's ask
Action: stop. Read /home/yguo173/.claude/skills/minimum-modification/SKILL.md. Follow its 3-round self-review loop before any edit.

Ambiguity rule

If both trigger classes apply (e.g. user complains about both abstraction and scope in one turn), load sub-skill 1 first, then sub-skill 2. Rule-level concerns subsume code-level concerns because a wrong rule produces many wrong diffs.

What this skill does NOT do

Does not argue, does not defend the prior output, does not produce a fix. The only output of this router is a decision: which sub-skill to load next.

이 저장소의 다른 Skills

같은 저장소

submit-task

gyy0592/claude-config

Guides AI through the end-to-end task submission workflow for the claude-config repo: (1) initializing a task workspace with new_task.sh, (2) committing and pushing to v2 and main branches, (3) deploying to the remote GPU server via ssh. Trigger when user says 'submit', 'push', 'deploy', 'version bump', 'push to main', or asks to commit and push changes to this repo.

2026-05-177

plain-language

gyy0592/claude-config

Enforces just-in-time term definition in technical writing — every name / file path / acronym / black-box term gets explained the moment it first appears (one line, parenthetical, inline), and re-explained whenever it reappears after a long gap. **NEVER** front-load a glossary at the top of a document; **NEVER** assume the reader has already read 100 turns of context. Trigger this skill aggressively whenever (1) the user complains 'I don't understand / 听不懂 / 说人话 / 给我说人话 / 你在说啥 / 这是啥 / 黑话 / 别用术语 / 操你妈的看不懂', (2) the user pushes back on a previous reply with 'what is X' / 'what does X mean' / '这个 X 是什么', (3) you're writing any technical report / diagnosis / plan / postmortem / architecture doc that mentions internal file paths, scripts, hooks, FSM states, variable names, or any term that wasn't in the user's original prompt verbatim, (4) you're about to write a 'Glossary' or 'Definitions' section at the top of a document — STOP, this skill says don't. Over-trigger rather than under-trigger; the cost of one extra

2026-05-177

efficiency-audit

gyy0592/claude-config

Audits whether the current code is already running at maximum speed by checking GPU/CPU/IO bottleneck saturation. Red-alarms if NONE of GPU/CPU/IO is bottlenecked — that proves speedup is mathematically possible and the code is wasting compute. Loads 5 sub-skills progressively. Trigger this skill aggressively whenever the user asks about speed, performance, throughput, latency, "why is this slow", "is my code optimal", "can I make this faster", "find the bottleneck", profiling, optimization, GPU utilization, dataloader speed, training speed, inference speed, 性能, 加速, 瓶颈, 慢, 优化, 训练慢, 推理慢, even when the user doesn't explicitly use the word "audit". Also trigger when reviewing training scripts, inference scripts, or any data-processing pipeline for efficiency. Skip only if the user clearly asks about correctness, not speed.

2026-05-127

no-undefined

gyy0592/claude-config

Document-level rigour auditor. Enforces that every term, symbol, abbreviation, experimental label, and formula appears with its definition adjacent to its first occurrence — and re-states it on distant reuse. Also enforces no-step-skipping in math derivations. Invoke whenever writing or reviewing a technical report, paper explanation, or derivation where a reader could encounter an undefined token. Pairs with math-explain (single-formula checklist) and zero-jump-check (inter-step seam auditor) as the outer document-level layer of the rigorous-writing stack.

2026-05-127

code-tree

gyy0592/claude-config

Generate a structured, navigable code documentation document for a Python codebase — the 'code tree'. Use this skill whenever the user asks to document a codebase, explain how the code works end-to-end, generate a code tree, write code documentation, understand call chains, or map out how functions relate to each other. Trigger on: '生成代码树', '代码树', '给我写代码文档', '解释代码结构', '画一个调用树', 'generate a code tree', 'document the codebase', 'write code docs', 'explain how the code works', 'map out the call chains', 'code documentation'. The output is a single Markdown file with: (1) directory tree, (2) ASCII call trees per functional area, (3) per-function docs with always-visible input/output descriptions and collapsed technical details. After generating, the skill runs ask-claude to verify format quality and fixes issues.

2026-04-297

gen-draft-simplify

gyy0592/claude-config

Generate a project-specific draft_simplify.md for a code repository — a high-level plan for an upcoming maintainability refactor that preserves runtime behavior bit-for-bit. Use this skill whenever the user wants to PLAN a code-cleanup / refactor / maintainability pass on a whole repository, before any code is changed. Trigger aggressively on phrases like '生成simplify draft', '写一下化简方案', '重构方案', '生成可维护性化简的draft', '帮我规划一下重构', 'plan a refactor', 'draft a simplify plan', 'generate a refactor plan for this repo'. The skill does NOT execute the refactor — it only produces the planning document. The output is a single instantiated draft_simplify.md at the repo root, with all placeholders filled from a mandatory AskUserQuestion intake. Do NOT trigger for: single-PR review (use /simplify), one-shot small edits, or when the user explicitly asks to start refactoring immediately. Do NOT confuse with /gen-draft (which is the generic draft generator) — this skill is specialized: the output draft already contains the full si

2026-04-287

name

minimize-change-router

description

minimize-change-router

Purpose

Dispatcher. Holds no content of its own. Picks exactly one of two sub-skills and hands off.

Dispatch table

Trigger class A (abstraction-level complaint about rules/docs):

User phrases: "不通用" / "不是 general" / "修修补补" / "又在打补丁" / "抽象层不对" / "patching" / "补丁" / "这条规则是 X 的特例" / "sibling rule smell"
Self-trigger: AI about to add a new rule to an existing rule list
Action: stop. Read /home/yguo173/.claude/skills/general-rule-vs-patch/SKILL.md. Follow its definitions before proposing any rule change.

Trigger class B (scope/diff-size complaint about code/doc edits):

User phrases: "最小修改" / "别动其他东西" / "改得太多" / "画蛇添足" / "我没让你做那个" / "顺手改" / "minimum modification" / "scope creep" / "only fix X"
Self-trigger: AI about to modify more than about 5 lines, or touch files outside the literal target of the user's ask
Action: stop. Read /home/yguo173/.claude/skills/minimum-modification/SKILL.md. Follow its 3-round self-review loop before any edit.

Ambiguity rule

What this skill does NOT do

Does not argue, does not defend the prior output, does not produce a fix. The only output of this router is a decision: which sub-skill to load next.