跳到正文
cccskills
免费在 GitHub 公开

prompt-decorators

Activates a structured decorator framework that modifies how Claude reasons, responds, and formats output. Trigger this skill whenever a prompt contains one or more markers prefixed with +++, such as +++Reasoning, +++StepByStep, +++Tone(style=formal), or any other +++ marker, regardless of what follows in the prompt. Also trigger when the user asks to activate, list, or clear decorators, references the prompt decorator framework, or uses phrases like "use decorator", "apply +++", or "what decorators are available". This skill must be active for any +++ marker to take effect.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(25)

  • SKILL.md4.8 KB
  • references/ActiveDecs.md169 B
  • references/AvailableDecs.md306 B
  • references/Brainstorm.md376 B
  • references/Candor.md386 B
  • references/ChatScope.md278 B
  • references/CiteSources.md288 B
  • references/Clear.md268 B
  • references/Critique.md308 B
  • references/Debate.md307 B
  • references/Dump.md197 B
  • references/Export.md317 B
  • references/FactCheck.md370 B
  • references/Import.md376 B
  • references/Interactive.md483 B
  • references/MessageScope.md205 B
  • references/OutputFormat.md226 B
  • references/Planning.md270 B
  • references/Reasoning.md253 B
  • references/Refine.md318 B
  • references/Rewrite.md323 B
  • references/Socratic.md316 B
  • references/StepByStep.md210 B
  • references/Tone.md229 B
  • references/Validate.md237 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Prompt Decorators

Lightweight control markers that modify reasoning, style, structure, and session behavior. Activated by the +++ prefix. Multiple decorators can be combined in a single prompt. Each decorator's full definition lives in its own file under references/. Load only the file(s) you need. The Quick Reference table below maps every decorator to its file.


Parsing Decorators from a Prompt

When a prompt contains +++ markers:

  1. Extract all decorator names and parameters from the prompt (they appear before the main content)
  2. For each decorator, load its definition from references/<DecoratorName>.md (e.g. +++Reasoning → references/Reasoning.md, +++StepByStep → references/StepByStep.md). Use the Quick Reference table in this file to map decorator names to file paths.
  3. Apply all active decorators simultaneously to the response
  4. Parameters are passed in parentheses, for example: +++Tone(style=formal), +++Refine(iterations=3)

If an unrecognized decorator is used, note it and proceed with the rest.


Scope Rules

Decorators operate in one of two scopes:

ScopeBehavior
Message scope (default)Decorator applies only to the current prompt
Chat scopeDecorator persists across all subsequent messages until cleared
  • +++ChatScope: switches all decorators in the same message to chat scope; they auto-apply to every future prompt
  • +++MessageScope: pauses chat-scoped decorators for the current message only (does not erase them)
  • +++Clear: removes all active chat-scoped decorators; +++Clear(+++Reasoning, +++Tone) removes only the named ones
  • +++ActiveDecs: lists all currently active chat-scoped decorators
  • +++AvailableDecs: lists all available decorators with name, description, and current status

Track active chat-scoped decorators across the conversation and apply them automatically even when the user does not re-specify them.


Combining Decorators

All decorators in a prompt apply simultaneously and in order. They do not conflict, each governs a different dimension of the response (reasoning process, tone, format, verification, etc.). When decorators overlap in effect, use judgment to satisfy both.

Example:

+++Reasoning
+++StepByStep
+++Tone(style=formal)

Explain how transformer models handle attention.

→ Begin with explicit reasoning, structure the body as labeled steps, maintain formal tone throughout.


Quick Reference

CategoryDecoratorDefinition File
Reasoning & structure+++Reasoningreferences/Reasoning.md
Reasoning & structure+++StepByStepreferences/StepByStep.md
Reasoning & structure+++Socraticreferences/Socratic.md
Reasoning & structure+++Debatereferences/Debate.md
Evaluation & refinement+++Critiquereferences/Critique.md
Evaluation & refinement+++Refine(iterations=N)references/Refine.md
Evaluation & refinement+++Candor(level=L)references/Candor.md
Exploration & planning+++Brainstormreferences/Brainstorm.md
Exploration & planning+++Planningreferences/Planning.md
Exploration & planning+++Interactivereferences/Interactive.md
Exploration & planning+++Import(topic=T)references/Import.md
Rewriting & clarification+++Rewritereferences/Rewrite.md
Output control+++OutputFormat(format=F)references/OutputFormat.md
Output control+++Tone(style=S)references/Tone.md
Verification+++FactCheckreferences/FactCheck.md
Verification+++CiteSourcesreferences/CiteSources.md
Verification+++Validatereferences/Validate.md
Session management+++ChatScopereferences/ChatScope.md
Session management+++MessageScopereferences/MessageScope.md
Session management+++Clearreferences/Clear.md
Session management+++ActiveDecsreferences/ActiveDecs.md
Session management+++AvailableDecsreferences/AvailableDecs.md
Export+++Export(format=F)references/Export.md
Export+++Dumpreferences/Dump.md

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Solves complex, open-ended problems using an evolutionary search mechanism inspired by genetic algorithms. Generates a diverse population of candidate answers, scores them against a rubric, then iteratively applies selection, crossover, and mutation to breed progressively better solutions. Use this skill whenever the user wants to explore a solution space deeply, asks for the "best" answer to a subjective or multi-dimensional problem, wants to evaluate competing approaches and distill the strongest, or uses any of these triggers: "evolutionary search", "genetic algorithm", "evolve an answer", "breed solutions", "population-based search", or phrases like "give me multiple approaches and refine the best one". Also trigger when the problem is complex, open-ended, or has no obvious single correct answer and the user wants a high-quality, well-explored result, not just a quick response.

中文简介正在准备中。当前显示原文说明。

smkalami/skills102026年3月30日 更新

Solves complex, open-ended problems using a knockout tournament mechanism. Generates an initial population of diverse candidate answers, pairs them into head-to-head matches, produces a hybrid "child" solution from each pair, and advances the best of the three through a bracket until a winner emerges. Use this skill whenever the user wants to competitively select the best answer from a field of alternatives, asks for a "tournament" or "bracket" style search, wants a faster alternative to full evolutionary search, or uses phrases like: "run a tournament on this", "bracket-style search", "let solutions compete", "knockout search", "find the best answer by elimination", or "which solution wins?". Also trigger when the problem is open-ended and the user wants a clear winner quickly rather than a deep multi-generation refinement.

中文简介正在准备中。当前显示原文说明。

smkalami/skills102026年3月30日 更新

查看 smkalami 的全部技能

报告此技能的问题