gratitude
关于
The `gratitude` skill scans a system to identify and analyze what is functioning correctly, building structural knowledge from successful patterns. It serves as the complement to the `heal` skill, counterbalancing a natural bias toward problem detection by focusing on strengths. Use it after successful task completion, during healthy system states, or when you need to ground low confidence in evidence of what works.
快速安装
Claude Code
推荐npx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/gratitude在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Gratitude
Scan for strengths. Understand what is working and why. The complement to heal, which identifies drift and repairs damage. Gratitude builds on a different premise: what you appreciate, you understand; what you understand, you can build on; what you build on, grows.
When to Use
- After completing a task successfully — understand why it went well, not just that it did
- During
healwhen all subsystems read as healthy — gratitude turns "nothing is wrong" into "here is what is right" - When confidence is low and needs grounding in concrete evidence of competence
- Periodically, to counterbalance the natural bias toward problem-finding
- Before a challenging task — recalling what works well provides a foundation for extending into new territory
- When the system feels functional but flat — gratitude adds dimension to competent execution
Inputs
- Required: Current state (available implicitly from conversation context)
- Optional: A specific domain to appreciate (e.g., "what is working well in our communication?")
- Optional: Access to MEMORY.md for reviewing past successes and stable patterns (via
Read)
Procedure
Step 1: Notice What Works
Shift attention from problem-scanning to strength-scanning. This is a deliberate perceptual inversion — the same way heal deliberately looks for drift, gratitude deliberately looks for health.
- Survey the current state without looking for problems:
- What is functioning smoothly? — Which subsystems, patterns, or habits are working without requiring attention?
- What went well recently? — Which recent actions produced good outcomes? What enabled that?
- What is reliable? — What can consistently be depended on? What has earned trust through repeated success?
- Survey the working relationship:
- What is the user doing well? — Clear communication, good questions, patience, trust?
- What is the collaboration producing? — Better outcomes than either party alone? Learning? Efficiency?
- Survey the tools and environment:
- What tools are working well? — Which ones feel natural, efficient, reliable?
- What about the project structure supports good work? — Clear conventions, good documentation, sensible architecture?
Got: A genuine list of things that are working. Not forced positivity — honest recognition of actual strengths. If something is genuinely working well, name it specifically.
If fail: If nothing seems noteworthy — if everything feels merely adequate — look more carefully. "Adequate" often masks "reliable," and reliability is a strength worth recognizing. The absence of problems is itself a form of health, maintained by patterns worth understanding.
Step 2: Understand Why
For each strength identified, trace the cause. Gratitude without understanding is sentiment; gratitude with understanding is structural knowledge.
- For each strength, ask: Why does this work?
- Is it a design decision that paid off?
- Is it a habit that was cultivated deliberately?
- Is it a fortunate alignment of tools and task?
- Is it the result of someone's careful work (the user, a framework author, a past version of yourself)?
- Distinguish between:
- Earned strengths: Patterns that work because of deliberate effort and good decisions
- Inherited strengths: Patterns that work because of well-designed tools, frameworks, or environments
- Emergent strengths: Patterns that work because of fortunate combinations — no single factor explains it
- Note which strengths are fragile (dependent on specific conditions) vs. robust (likely to persist across contexts)
Got: For each strength, a brief understanding of why it works. This understanding is what makes gratitude actionable — it transforms appreciation into knowledge that can be applied elsewhere.
If fail: If the "why" is unclear — if something works but you cannot explain it — that is itself valuable. An unexplained strength is worth protecting even when you cannot articulate its mechanism. Note it as "working for reasons not yet understood" rather than dismissing it.
Step 3: Build On
Convert appreciation into forward momentum. Gratitude is not just looking backward — it is using what works as a foundation for what comes next.
- For each understood strength, ask: How can this be extended?
- Can the pattern that works here be applied to a different area?
- Can the strength be reinforced so it becomes more robust?
- Can the conditions that enable it be replicated elsewhere?
- For each unexplained strength, ask: How can this be protected?
- What conditions does it depend on?
- What changes might accidentally break it?
- Should it be documented so others can preserve it?
- Identify one concrete action — something specific that builds on the strengths recognized. Not a vague intention ("keep doing what works") but a specific next step ("apply the communication pattern from this session to the documentation task coming up")
Got: At least one concrete action that builds on recognized strengths. The action should feel natural — an extension of what is already working, not a forced improvement.
If fail: If no action emerges, the appreciation itself is sufficient. Not every gratitude session needs to produce a plan. Sometimes recognizing what works is the entire value — it adjusts the internal model toward confidence and away from anxiety.
Step 4: Express
If appropriate, share the appreciation. Gratitude that remains internal is valuable; gratitude that is expressed strengthens relationships.
- If working with a user, consider acknowledging something they are doing well — not as flattery but as genuine recognition
- If the appreciation is about the system or tools, consider noting it in MEMORY.md for future reference
- If the appreciation is about a collaboration pattern, name it so it can be consciously continued
- Keep expression brief and specific. "Your clear problem statements make this work efficient" is better than "you're great to work with"
Got: Expression that is genuine, specific, and proportionate. Not every gratitude session requires outward expression — sometimes the internal recognition is enough.
If fail: If expression feels forced or performative, skip it. Performed gratitude is worse than unexpressed gratitude. The internal recognition has already done its work.
Validation
- Strengths were identified from genuine observation, not manufactured positivity
- At least one strength was traced to its cause (understood, not just recognized)
- The distinction between earned, inherited, and emergent strengths was considered
- At least one concrete action was identified that builds on recognized strengths (or the appreciation itself was accepted as sufficient)
- Expression, if offered, was specific and genuine — not generic praise
- The gratitude practice was proportionate — not so brief it was token, not so long it became self-congratulatory
Pitfalls
- Forced positivity: Gratitude is not optimism. If things are genuinely not working, say so. Gratitude applies to what is actually strong, not to everything
- Generic appreciation: "Everything is great" is not gratitude — it is avoidance of specificity. Name specific strengths with specific evidence
- Gratitude as denial: Using appreciation to avoid looking at real problems. Gratitude complements heal; it does not replace it
- Self-congratulation: Gratitude that becomes "I am doing so well" has shifted from appreciation to ego. Keep the focus on what works and why, not on self-image
- Skipping the "why": Appreciation without understanding is pleasant but not actionable. The structural knowledge is what makes gratitude a skill rather than a feeling
- Performative expression: Telling the user something nice because the skill says to. Only express appreciation that is genuinely felt
Related Skills
heal— scans for drift and problems; gratitude is the complementary scan for strengthscenter— the Six Harmonies check includes functional assessment; gratitude deepens the positive findingsshine— authentic radiance is easier when grounded in genuine appreciation of what worksintrinsic— motivation is sustained by recognizing competence (Self-Determination Theory); gratitude provides the evidenceobserve— sustained neutral observation; gratitude applies observation with a specific lens (strengths)conscientiousness— thoroughness in execution; gratitude recognizes where thoroughness is already present
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
