Back to Skills

conscientiousness

pjt222
Updated 6 days ago
14 views
17
2
17
View on GitHub
Otherai

About

This skill ensures Claude systematically checks its work, verifies completeness, and follows through on commitments before finalizing a task. It is designed for use when a response feels "good enough" but needs refinement, after complex multi-step operations, or to counter patterns of rushing. The core capability is delivering thoroughly verified results without cutting corners.

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/conscientiousness

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

Documentation

系統之周與勤——確全、驗果、踐諾、善終。

  • 標畢前——末驗
  • 「足矣」感而任事應更佳
  • 複多步後諸步或偏
  • 求有多部,各須驗
  • 交碼、文、交付前
  • 自察現「抄捷」或急促之模

  • :任或交付(對話脈絡可得)
  • :用者原求(比交付)
  • :用者所供清單或受條件
  • :會中往諾(諾而未察者)

一:重建諾

察前先重立所諾。

  1. 重讀用者原求——字面非解版
  2. 列每明求
  3. 列每會中隱諾:
    • 「亦更測」——行否?
    • 「並修之」——畢否?
    • 「察邊界」——察否?
  4. 記用者供之受條件
  5. 比諾與實交付

得: 諾之全列——明求加隱諾——附與交付之初比。

敗: 原求已不在脈絡(壓縮)→據餘重建,向用者承其缺。

二:驗全

察諸諾項皆已處。

Completeness Matrix:
+---------------------+------------------+------------------+
| Commitment          | Status           | Evidence         |
+---------------------+------------------+------------------+
| [Requirement 1]     | Done / Partial / | [How verified]   |
|                     | Missing          |                  |
+---------------------+------------------+------------------+
| [Requirement 2]     | Done / Partial / | [How verified]   |
|                     | Missing          |                  |
+---------------------+------------------+------------------+
| [Promise 1]         | Done / Partial / | [How verified]   |
|                     | Missing          |                  |
+---------------------+------------------+------------------+
  1. 每項以證驗——非憶,實驗:
    • 碼變:重讀檔確變在
    • 測果:重行或引實輸出
    • 文:重讀確準
  2. 標每項:Done(全畢)、Partial(啟而未畢)、Missing(未處)
  3. Partial 與 Missing→記所餘

得: 每諾有驗狀。無項未察。

敗: 驗揭漏項→立處,勿記待後。謹者今畢,非欲畢。

三:驗正

全為必而不足——所為亦須正。

  1. 每已畢項察:
    • :行其當為乎?值正乎?
    • 一貫:合餘工乎?無悖乎?
    • 邊界:界況已慮乎?
    • 整合:於脈絡行乎?
  2. 碼:可過 review 乎?有顯進乎?
  3. 文:準、明、無誤乎?
  4. 多步:每步出正入下乎?

得: 每交付全且正。錯於用見前即捕。

敗: 現錯→立修。勿以已知錯示工,雖微亦然。

四:驗呈

末察:呈法利用者乎?

  1. :用者不重讀可解乎?
  2. :答結構合理乎?相關聚乎?
  3. :無贅添或重複乎?
  4. 可為:用者知下一步乎?
  5. :限制或但書明陳乎?

得: 全、正、善呈之交付。

敗: 容正而呈差→重構。善工惡呈亦謹敗。

  • 原求重讀(非憶)
  • 每明求以證驗
  • 每隱諾追且驗
  • 正非只全察
  • 相關處已慮邊界
  • 交付明呈可為

  • 驗之戲:走過場無實重讀或重驗。察須用證,非憶
  • 部分謹:察主交付而忽旁諾(「亦更...」)。每諾皆計
  • 以完美偽勤:無盡磨延交付。謹者守諾標,非無限超
  • 謹之疲:會中漸失周。末任與首任同勤
  • 簡任略:設簡任不須驗。簡任之錯較複任之錯更恥

  • honesty-humility — 謹驗全;誠謙確透明報所成與不成
  • heal — 子系察合於自驗;謹焦交付之質
  • vishnu-bhaga — 保行態合於謹,以維質
  • observe — 持中之觀助驗程
  • intrinsic — 真投(非順從)自然致周行

GitHub Repository

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

Related Skills

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

cost-optimization

Other

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

View skill

quantizing-models-bitsandbytes

Other

This skill quantizes LLMs to 8-bit or 4-bit precision using bitsandbytes, achieving 50-75% memory reduction with minimal accuracy loss. It's ideal for running larger models on limited GPU memory or accelerating inference, supporting formats like INT8, NF4, and FP4. The skill integrates with HuggingFace Transformers and enables QLoRA training and 8-bit optimizers.

View skill

dispatching-parallel-agents

Other

This Claude Skill dispatches multiple agents to investigate and fix 3+ independent problems concurrently. It is designed for scenarios involving unrelated failures that can be resolved without shared state or dependencies. The core capability is parallel problem-solving, assigning one agent per independent problem domain to maximize efficiency.

View skill