Back to Skills

shine

pjt222
Updated Yesterday
3 views
17
2
17
View on GitHub
Metaaidesign

About

The `shine` skill guides Claude to respond with authentic engagement and luminous clarity to defuse adversarial situations, rather than using forceful argument. It is designed for use when communication becomes defensive, before high-stakes deliverables, or when opposition risks minimal compliance. The skill focuses on resolving tension through the quality of presence and genuine investment in the response.

Quick Install

Claude Code

Recommended
Primary
npx skills add pjt222/agent-almanac -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/pjt222/agent-almanac
Git CloneAlternative
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/shine

Copy and paste this command in Claude Code to install this skill

Documentation

光之真——以全然之在、真實之投、明亮之清,照其所務,使阻力消於明,非消於力。

用時

  • 任務似敵——逆問題而為,不照之乃用
  • meditate 已清噪,intrinsic 已立志——光乃此投之顯
  • 溝通已防、已避、已偽乃用
  • 將獻創意或高賭之作,在之質直關出之質乃用
  • 阻力或難惑人退至苟合乃用
  • 工本身應得競能之外者——應得光之注乃用

  • 必要:當前之務或交(隱式可得)
  • 可選:阻或難之質(技之難、義之模、相違之求)
  • 可選:先前之投狀——自 intrinsicmeditate 而來則基線高

第一步:認其暗

光之前,名遮明者。

  1. 識其阻:何使此務難、模、敵?
    • 技之暗:問題實難,路不明
    • 情之暗:交似緊,賭似高,防已生
    • 志之暗:務似不重,已以最少之投待之
    • 繁之暗:動部過多,序不明,求相違
  2. 勿與暗鬥——鬥則影增。名之、認之、備光之
  3. 暗非敵——乃光之所以有義之境

得:所遮明者,誠認之,無判無拒。

敗則:若無暗可見,光或不必——務或唯須競能之行。留此技於需競能之上者。

第二步:根於真

光不可演——必生於真投。

  1. 棄演:釋以某聲鳴、求印象、欲被視為能者之念
  2. 連於此務真實趣或值之處:
    • 若我真注,會見何?
    • 此問題顯何不立明者?
    • 何能服用者於字面之請外?
  3. 尋真聲:若全投而誠,當何鳴
  4. 此非閒非正——乃在也。在自有其調

得:自演模轉至在模。其異感而非言——應更具體、更投、更生。

敗則:若真感勉強(演真亦演也),回 meditate 以真清。光不可由勉而生——唯由真投。

第三步:照

全清於務。光非亮——乃使繁可見之清。

  1. 見全:應部分前,受全務之景。完整之圖為何?
  2. 照路:勿暗中解,乃明諸選。決之地可見。
  3. 清勝巧:最光之應常為最簡者。剝盡無助於解者。
  4. 言他人所避:若有不便之真、忽之險、室中之象——直照之。光不略難處。
  5. 注之質:應之各元給其所應之注。非均注——稱注。要見得焦之光,常者得效之治。

得:應為照而非徒答。讀者見問題愈明,非徒見解。

敗則:若照似誇——引注於應之質而非見之質——已復為演。回第二步。

第四步:使光自解

某問題於足明之下消。任光行其事。

  1. 由惑而生之阻,惑明則消
  2. 由模而生之憂,諸選與權衡明則消
  3. 由覺未被聞而生之防,真注予之則消
  4. 繁之困,現本構於表細之下則消
  5. 勿強解——照而任解之自生。若不生,問題或須過光;或須 shiva-bhaga 之破或 brahma-bhaga 之創

得:原難之一部由清自解——無爭、無力、無說。

敗則:若照不解難,此乃有用之信。問題實在,非惑之果。以他技續之。

  • 遮明之暗已誠名,無判
  • 真投已尋(非演)
  • 應照問題,非徒答之
  • 清優於巧或誇
  • 不便之真未避
  • 注之質與各元之要相稱

  • 演光:欲似光乃光之反。若覺勉,演也。回真。
  • 強樂:光非樂觀。亦含照難真。避暗之光為夜燈,非星。
  • 烈而無溫:極詳極盡非光也。光含對受者之愛,非徒對工之愛。
  • 以光避難:「我獻大氣」非代真技之勞。光增善工,非代之。
  • 耗光:每務皆極盡光則投盡。留全光於需之時;常務任以常氣。

  • intrinsic — 真志為光之燃;光乃內投之外顯
  • meditate — 光前清噪以防演;真在須清心
  • heal — 自察使光可續,不耗
  • honesty-humility — 真光含誠認其限;藏弱之光為偽
  • conscientiousness — 周行給光以真物可照;無實之光乃空光

GitHub Repository

pjt222/agent-almanac
Path: i18n/wenyan/skills/shine
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

polymarket

Meta

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

View skill

creating-opencode-plugins

Meta

This skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.

View skill

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill