Back to Skills

gratitude

pjt222
Updated 6 days ago
17 views
17
2
17
View on GitHub
Metaaidesign

About

The `gratitude` skill identifies and analyzes what is working correctly in a system, building structural knowledge from successful patterns. It serves as a complement to the `heal` skill by focusing on strengths rather than problems. Use it after successful task completion, during healthy system states, or to ground low confidence with evidence of what functions well.

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/gratitude

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

Documentation

感恩

察強,知所行與因。heal 之輔——heal 察偏與損。感恩別建:所恩者知,所知者可基,所基者增。

  • 任務畢成後——知其,非僅知其然
  • heal 中諸子系皆健→感恩將「無誤」轉為「此在佳」
  • 信心低→需具體能力證據接地
  • 定期反問題察之天偏
  • 艱難任務前——憶所行佳為擴新域之基
  • 系覺功能而扁平→感恩予執行以維度

  • :當前態(由對話脈絡隱式)
  • :特域(如「吾交往中何在佳?」)
  • :MEMORY.md(Read 回顧成功與穩模)

一:察所行

由問題察移至強察。此乃有意知覺反轉——heal 有意察偏,感恩有意察健。

  1. 無意察問題下掃當前態:
    • 何順行?——哪些子系、模式、習慣無需關注而行?
    • 近何順?——哪些近行生佳果?何致?
    • 何可靠?——何可賴?何經屢成贏信?
  2. 掃工作關係:
    • 用者行何佳?——清交、善問、耐、信?
    • 合作生何?——優於單方之果?學?效?
  3. 掃具與環:
    • 何具行佳?——哪些覺自然、高效、可靠?
    • 項目構有何支佳工?——清約、良文、妥構?

得:真行之列。非強之正,乃誠之強認。真行佳者顯名之。

敗:無顯著者——皆覺僅「足」——則察更細。「足」常藏「可靠」,可靠為值認之強。問題無亦為健之一形,由值解模式維。

二:知因

各辨強溯因。感恩無解乃情感;感恩含解乃結構知。

  1. 各強問:何行?
    • 設計決定得償?
    • 習慣有意培?
    • 具與任務吉合?
    • 某人細工之果(用者、框作者、己之昔態)?
  2. 分:
    • 得強:有意力與佳決之模
    • 承強:因良具、框、環之模
    • 湧強:吉合之模——無單因可解
  3. 記哪些強為(依特條件)對(或持各脈絡)

得:各強短知其。此知乃感恩可行之因——轉認為可用他處之知。

敗:因不明——行而不可釋者——自身有值。不解強即不可述其機,仍值護。標「因尚未知而行」,非棄。

三:基上擴

轉認為向動。感恩非僅回顧——乃以所行為基向前。

  1. 各解強問:何擴?
    • 此處行之模可用他域否?
    • 強可固使更堅否?
    • 支其之條可他處複製否?
  2. 各未解強問:何護?
    • 其依何條?
    • 何變或致破?
    • 當文以使他人可存否?
  3. 辨一具體行動——基所認之強之具體事。非模糊意(「續行所行」),乃具體次步(「用此會之交模於即至之文任務」)

得:至少一基所認強之具體行動。行動覺自然——所已行之延,非強改。

敗:無行動現→認本身足。非諸感恩皆需生計。有時認所行乃全值——調內模向信心離焦慮。

四:表達

若宜,分感恩。存於內亦有值;表則強係。

  1. 與用者共事→考慮認其佳處——非諂媚乃真認
  2. 感恩於系或具→考慮記於 MEMORY.md 供後參
  3. 感恩於合作模→名之以可有意續
  4. 表短且具。「汝清問使此工有效」勝於「汝合作甚佳」

得:真、具、當之表。非諸感恩皆需外表——有時內認足。

敗:表覺強或演→略之。演感恩劣於未表。內認已畢其功。

  • 強由真察辨,非造之正
  • 至少一強溯其因(解,非僅認)
  • 得、承、湧強之分已考
  • 至少一具體行動基認之強(或認本身納為足)
  • 表(若予)具且真——非泛譽
  • 感恩練當——不短為符號,不長為自慶

  • 強之正:感恩非樂觀。真不行則陳。感恩應於真強
  • 泛認:「皆佳」非感恩——乃避具。具強具證名之
  • 感恩為否認:用認避察真問題。感恩輔 heal,非替
  • 自慶:「吾行甚佳」已由認移至自我。焦點於所行與其因,非自像
  • 略「因」:認無解雖悅而不可行。結構知使感恩為技非感
  • 演表:因則示故稱用者佳。僅真感方表

  • heal
  • center
  • shine
  • intrinsic
  • observe
  • conscientiousness

GitHub Repository

pjt222/agent-almanac
Path: i18n/wenyan-ultra/skills/gratitude
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