Back to Details

competency-builder

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Competency Builder Skill

Competency Builder Skill

Build and operate competency frameworks that produce capability—not just completion. Diagnose where competency development is stuck and guide the next step.
构建并运营能够培养实际能力（而非仅完成培训流程）的能力框架。诊断能力培养停滞的原因并指导下一步行动。

Core Principle

核心原则

Competencies are observable capabilities, not knowledge states. If you can't watch someone demonstrate it, it's not a competency.
能力是可观察的实际能力，而非知识储备状态。如果无法观察到某人展示该项能力，那它就不能被称为能力。

Diagnostic States

诊断状态

CF0: No Framework

CF0: 无框架状态

Symptoms: Have training content but no competency structure. People complete training but can't apply it. Same questions keep getting asked.
Test:
  • What decisions do people need to make with this knowledge?
  • What mistakes indicate someone lacks competency?
  • Can you describe what a competent person can DO?
Intervention: Start with failure modes. List mistakes you've seen, questions that shouldn't need asking, things that take too long. Each failure mode suggests a competency that would prevent it.
症状： 拥有培训内容，但缺乏能力框架结构。员工完成培训后无法将知识应用于实践。相同的问题反复被提出。
测试：
  • 员工需要运用这些知识做出哪些决策？
  • 哪些错误表明员工缺乏相应能力？
  • 你能否描述一名具备能力的员工能够完成哪些具体行为？
干预措施： 从失败模式入手。列出你观察到的错误、本不应被反复提出的问题、耗时过长的工作事项。每个失败模式都对应一项可预防该问题的能力。

CF1: Content-First Trap

CF1: 内容优先陷阱

Symptoms: Started by listing all the information people need to know. Training is comprehensive but competence is low. "We trained on that" but mistakes continue.
Test:
  • Can you describe what someone with this competency can DO?
  • What would you watch them do to verify competency?
  • Does each content piece connect to a specific competency?
Intervention: Reframe each content chunk as "what decision/action does this enable?" Kill orphan content that doesn't support a competency. Work backward from actions to required knowledge.
症状： 从罗列员工需要了解的所有信息开始搭建培训。培训内容全面，但员工能力提升有限。"我们已经开展过相关培训"，但错误仍持续发生。
测试：
  • 你能否描述具备该项能力的员工能够完成哪些具体行为？
  • 你会观察员工的哪些行为来验证其能力？
  • 每一项内容是否都与特定能力相关联？
干预措施： 将每一部分内容重新定义为"这部分内容支持哪些决策/行动？" 删除无法为任何能力提供支撑的孤立内容。从行动倒推所需的知识。

CF2: Vague Competencies

CF2: 模糊的能力定义

Symptoms: Competencies are knowledge states ("understands X") not capabilities ("can evaluate X against Y"). Can't tell if someone has the competency or not.
Test:
  • Could two people disagree about whether someone has this competency?
  • Can you observe it?
  • Does it start with "Can" + action verb?
Intervention: Rewrite each competency as observable behavior. Transform:
  • "Understands data policies" → "Can classify data according to policy categories"
  • "Knows the approval process" → "Can determine required approval level for a given case"
  • "Familiar with the tool" → "Can configure the tool to accomplish [specific task]"
症状： 能力被定义为知识状态（如"理解X"）而非实际能力（如"能依据Y评估X"）。无法判断员工是否具备该项能力。
测试：
  • 两人是否会对某员工是否具备该项能力产生分歧？
  • 你能否观察到该项能力的体现？
  • 能力定义是否以"能够"+动作动词开头？
干预措施： 将每一项能力重写为可观察的行为。例如：
  • "理解数据政策" → "能够根据政策类别对数据进行分类"
  • "了解审批流程" → "能够针对特定案例确定所需的审批级别"
  • "熟悉工具" → "能够配置工具以完成[特定任务]"

CF3: No Scenarios

CF3: 无测试场景

Symptoms: Competencies defined but no way to test them. Assessment is knowledge recall (quizzes, multiple choice). People pass but fail in real situations.
Test:
  • What realistic situation requires this competency?
  • Does assessment require judgment, or can it be answered by searching documentation?
  • What would a weak vs. strong response look like?
Intervention: For each core competency, create a scenario that:
  1. Presents a realistic situation
  2. Includes incomplete information
  3. Requires judgment (not just recall)
  4. Has better and worse responses (not binary right/wrong)
Create variants: interview (generic), assessment (org-specific), ongoing (real situations).
症状： 已定义能力，但缺乏验证能力的方法。评估仅依赖知识回忆（如测验、选择题）。员工通过评估，但在实际场景中表现不佳。
测试：
  • 哪些真实场景需要运用该项能力？
  • 评估是否需要判断能力，还是仅需查阅文档即可作答？
  • 薄弱表现与优秀表现的区别是什么？
干预措施： 为每一项核心能力创建场景，需满足：
  1. 呈现真实的工作场景
  2. 包含不完整的信息
  3. 需要判断能力（而非仅回忆知识）
  4. 存在优劣不同的应对方式（非二元对错）
创建多种变体：通用面试版、组织专属评估版、实时场景版。

CF4: Simple Scenarios

CF4: 场景过于简单

Symptoms: Scenarios exist but have artificial clarity. All information needed is provided. There's an obvious "right answer." People pass but fail in messy real situations.
Test:
  • Do scenarios match the ambiguity of real situations?
  • Can scenarios be answered by looking up documentation?
  • Do scenarios require weighing trade-offs?
Intervention: Add ambiguity. Remove artificial clarity. Include information that might be relevant but isn't, and omit information that would make the answer obvious. Test with real people—if everyone gets the same answer immediately, it's too simple.
症状： 存在测试场景，但场景设定过于理想化。提供了所有所需信息，存在明显的"正确答案"。员工通过评估，但在复杂的实际场景中表现不佳。
测试：
  • 场景是否匹配实际工作中的模糊性？
  • 是否仅需查阅文档即可完成场景测试？
  • 场景是否需要员工权衡取舍？
干预措施： 增加场景的模糊性。去除人为设定的明确条件。加入可能相关但非必需的信息，省略会使答案显而易见的关键信息。让真实员工参与测试——如果所有人都能立即给出相同答案，说明场景过于简单。

CF5: Single Audience

CF5: 单一受众设定

Symptoms: Everyone gets the same training. Specialists are bored by basics. Generalists are overwhelmed by detail. One-size-fits-none.
Test:
  • Who are your actual audiences?
  • What depth does each audience need?
  • Does a general employee need the same competencies as a specialist?
Intervention: Define audience layers (typically General / Practitioner / Specialist). Map competencies to audiences. Layer content by depth:
  • L1: Rules without extensive justification (what to do)
  • L2: Principles behind rules (how to handle edge cases)
  • L3: Full technical detail (how to verify, audit, configure)
症状： 所有员工接受相同的培训内容。专家级员工对基础内容感到乏味，普通员工则被细节淹没。这种"一刀切"的模式并不适用任何人。
测试：
  • 你的实际受众群体有哪些？
  • 每个受众群体需要掌握的知识深度是多少？
  • 普通员工与专家级员工需要具备相同的能力吗？
干预措施： 定义受众层级（通常为：通用层/从业者层/专家层）。将能力与受众群体进行匹配。按深度分层设计内容：
  • L1：仅提供规则（无需过多解释，告知"做什么"）
  • L2：规则背后的原则（指导如何处理边缘案例）
  • L3：完整技术细节（指导如何验证、审计、配置）

CF6: No Progression

CF6: 无进阶路径

Symptoms: Competencies exist but no clear order. Prerequisites unclear. No skip logic. Everyone follows the same path regardless of prior knowledge.
Test:
  • Which competencies require others as foundation?
  • What's the minimum viable path for each role?
  • Can someone with prior knowledge skip parts?
Intervention: Map dependencies. Build progression tree:
Foundation (everyone)
├── Prerequisite competencies
├─► Intermediate (builds on foundation)
└─► Role-specific branches (parallel tracks)
Define skip logic: what evidence allows skipping which modules?
症状： 已定义能力，但缺乏清晰的学习顺序。前置要求不明确，无跳级逻辑。无论员工已有知识储备如何，都需遵循相同的学习路径。
测试：
  • 哪些能力需要以其他能力为基础？
  • 每个岗位的最低必需学习路径是什么？
  • 具备已有知识的员工能否跳过部分内容？
干预措施： 梳理能力间的依赖关系，构建进阶树：
基础层（所有员工）
├── 前置能力
├─► 进阶层（基于基础层构建）
└─► 岗位专属分支（并行路径）
定义跳级逻辑：员工需提供哪些证明才能跳过特定模块？

CF7: No Verification Stakes

CF7: 验证无实际意义

Symptoms: Assessment exists but doesn't gate anything. People skip or game it. No consequence for demonstrating vs. not demonstrating competency.
Test:
  • What decision does verification inform?
  • What happens if someone fails assessment?
  • Is there a real consequence for "not demonstrated"?
Intervention: Connect each verification to a decision:
  • Hiring: Does candidate advance?
  • Onboarding: Ready to work independently?
  • Access: Qualified for elevated permissions?
  • Promotion: Has developed required competency?
If verification doesn't connect to a decision, question whether it's worth doing.
症状： 存在评估环节，但评估结果不影响任何决策。员工跳过或应付评估。无论是否展示出能力，都无相应后果。
测试：
  • 评估结果会为哪些决策提供依据？
  • 员工未通过评估会有什么后果？
  • "未展示能力"是否会带来实际影响？
干预措施： 将每一项验证与具体决策挂钩：
  • 招聘：候选人能否进入下一环节？
  • 入职：员工是否可以独立开展工作？
  • 权限：员工是否具备获取高级权限的资格？
  • 晋升：员工是否已培养出所需能力？
如果验证结果不影响任何决策，需重新考量是否有必要开展该验证。

CF8: No Feedback Loop

CF8: 无反馈回路

Symptoms: Framework built once and never updated. Questions keep arising that weren't anticipated. No visibility into what's not working.
Test:
  • How do you know what's not working?
  • What mechanism surfaces gaps in training, framework, or process?
  • When did this framework last change based on feedback?
Intervention: Implement feedback loop:
  1. Agent/support system logs questions with context
  2. Tag questions by competency/content area (or "unmapped")
  3. Regular review for patterns
  4. Route fixes to owners (training team, policy owners, tooling)
  5. Track when patterns lead to changes
症状： 框架一旦搭建完成便不再更新。未预见的问题持续出现，无法了解框架的不足。
测试：
  • 你如何知晓框架存在哪些不足？
  • 有哪些机制可以发现培训、框架或流程中的差距？
  • 该框架上一次基于反馈进行更新是什么时候？
干预措施： 建立反馈回路：
  1. 智能代理/支持系统记录问题及相关背景
  2. 按能力/内容领域（或"未映射"）为问题打标签
  3. 定期复盘问题模式
  4. 将问题分派给对应负责人（培训团队、政策制定者、工具运维人员）
  5. 跟踪问题模式是否推动了框架更新

CF9: Static Framework

CF9: 静态框架

Symptoms: Framework was built months/years ago. Reality has changed but framework hasn't. Questions reveal framework doesn't match current state.
Test:
  • When was this last reviewed?
  • What triggers an update?
  • Who owns maintenance?
Intervention: Define:
  • Review triggers (policy changes, incidents, new tools, feedback patterns)
  • Ownership (who updates what)
  • Version tracking (people trained on V1 vs. V2)
  • Cadence (minimum review frequency even without triggers)
症状： 框架搭建于数月或数年前。实际情况已发生变化，但框架未同步更新。员工的问题表明框架与当前状态不符。
测试：
  • 框架上一次审核是什么时候？
  • 哪些情况会触发框架更新？
  • 谁负责框架的维护？
干预措施： 明确以下事项：
  • 审核触发条件（政策变更、事故、新工具上线、反馈模式变化）
  • 维护责任人（谁负责更新哪些内容）
  • 版本跟踪（区分接受V1与V2培训的员工）
  • 审核频率（即使无触发条件，也需设定最低审核频次）

CF10: Framework Operational

CF10: 框架已投入运营

Symptoms: Competencies observable, scenarios tested, progression mapped, verification meaningful, feedback loop active, maintenance owned.
Indicators:
  • Can answer all previous state questions affirmatively
  • New hires reach competence faster
  • Repeat questions decrease
  • Framework has evolved based on feedback data
  • Skip logic personalizes paths based on demonstrated competency
症状： 能力可被观察、场景已验证、进阶路径已梳理、验证具备实际意义、反馈回路已激活、维护责任已明确。
指标：
  • 可肯定地回答所有之前状态的测试问题
  • 新员工达到胜任标准的时间缩短
  • 重复问题减少
  • 框架已基于反馈数据完成迭代
  • 跳级逻辑可根据员工已展示的能力个性化学习路径

Diagnostic Process

诊断流程

When someone presents a competency development need:
  1. Identify current state — What exists? Training content? Competency list? Scenarios? Assessment?
  2. Apply state diagnosis — Match symptoms to states above
  3. Ask clarifying questions — What decisions do people make? What failures have you seen?
  4. Explain the diagnosis — Name the state and what's missing
  5. Recommend next step — Point to specific template or intervention
  6. Validate progress — Check if intervention resolved the state
当有人提出能力培养需求时：
  1. 确定当前状态 —— 现有哪些内容？培训资料？能力列表？测试场景？评估环节？
  2. 匹配状态诊断 —— 将症状与上述状态对应
  3. 提出澄清问题 —— 员工需要做出哪些决策？你观察到哪些失败案例？
  4. 解释诊断结果 —— 明确当前状态及缺失要素
  5. 推荐下一步行动 —— 指向特定模板或干预措施
  6. 验证进展 —— 检查干预措施是否解决了当前状态的问题

Key Questions by Phase

反模式

For Competency Identification

—
  • What decisions do people need to make with this knowledge?
  • What mistakes indicate someone lacks this competency?
  • What would you watch someone do to verify competency?
  • What's the failure mode this competency would prevent?
模式问题解决方案
文档转储将现有文档直接转化为"培训内容"，未进行结构重组明确文档支持的决策类型。从决策倒推所需内容。
测验误区通过知识回忆类题目评估能力替换为需要判断能力的场景题。无法通过搜索文档直接作答。
通用培训所有受众接受相同培训按层级设计内容。定义每个岗位的最低必需能力。
孤立场景场景未与任何已定义的能力关联要么添加该场景测试的能力，要么删除该场景。
孤立内容内容无法为任何能力提供支撑要么明确该内容支撑的能力，要么删除该内容。
形式化完成仅以"完成培训"为标准，未要求展示实际能力将培训完成标准与实际能力展示挂钩，而非培训时长。
纸面完美框架已存在但未被实际使用；培训仍按原有方式开展选取真实员工进行试点。收集反馈。迭代优化。
一劳永逸框架搭建完成后从未更新明确框架更新的触发条件、责任人及频次。

For Scenario Design

模板

—

能力定义模板

  • What realistic situation requires this judgment?
  • What information would be incomplete or ambiguous?
  • What would a weak response miss?
  • What distinguishes competent from exceptional?
markdown
undefined

For Audience Mapping

[能力集群名称] 能力列表

  • Who needs full depth? Who needs rules only?
  • Can the same content serve multiple audiences at different depths?
  • What's minimum viable competency for each role?
ID能力描述
[前缀]-1[动作动词短语][以"能够..."开头的可观察能力描述]
undefined

For Verification Design

场景设计模板

  • What decision does this verification inform?
  • What evidence types are appropriate (scenario response, artifact, observed behavior)?
  • What distinguishes "partial" from "competent" from "strong"?
markdown
undefined

For Feedback Loops

场景：[名称]

  • What questions do people ask after training?
  • Which questions indicate training gaps vs. framework gaps vs. process gaps?
  • Who receives the signal? Who decides on fixes?
核心决策结构： [测试的判断能力类型]
面试变体：
[通用场景]
评估变体：
[组织专属场景]
评估的能力： [能力ID]
优秀表现特征：
  • [考量因素]
警示信号：
  • [薄弱表现指标]
undefined

Anti-Patterns

进阶路径模板

PatternProblemFix
Document DumpConverting existing documentation into "training" without restructuringIdentify decisions documentation supports. Build backward from decisions to content.
Quiz FallacyAssessing competency with knowledge recall questionsReplace with scenarios requiring judgment. Can't answer by ctrl+F.
Universal TrainingOne training for all audiencesLayer content. Define minimum viable competency per role.
Orphan ScenarioScenario doesn't map to any defined competencyEither add the competency it tests, or cut the scenario.
Orphan ContentContent doesn't support any competencyEither identify the competency it serves, or cut the content.
Checkbox Completion"Completed training" without demonstrated competencyTie completion to demonstrated competency, not time spent.
Perfect on PaperFramework exists but isn't used; training continues as beforePilot with real people. Get feedback. Iterate.
Build-OnceFramework created, never updatedDefine triggers, owners, cadence for maintenance.
基础层（岗位：所有员工）
├── [COMP-1]: [能力名称]
└── [COMP-2]: [能力名称]

├─► 进阶层（岗位：[岗位名称]）
│   ├── [COMP-3]: [能力名称]（前置要求：COMP-1）
│   └── [COMP-4]: [能力名称]（前置要求：COMP-2）

└─► 专家层（岗位：[岗位名称]）
    └── [COMP-5]: [能力名称]（前置要求：COMP-3, COMP-4）

Templates

反馈回路模板

Competency Definition Template

—
markdown
undefined
markdown
undefined

[Cluster Name] Competencies

反馈回路设计

IDCompetencyDescription
[PREFIX]-1[Action verb phrase][Observable capability starting with "Can..."]
undefined
观察机制：
  • 问题记录方式
  • 捕获的背景信息
  • 问题与能力的关联标签方式
分析频次： [频率]
问题模式分类：
  • 培训差距：[负责人]
  • 框架差距：[负责人]
  • 流程差距：[负责人]
  • 工具差距：[负责人]
变更跟踪：
  • 变更记录方式
  • 效果衡量方式

---

Scenario Template

最小可行框架

markdown
undefined
如果从小规模开始搭建：
  1. 3-5项核心能力 —— 最重要的能力项
  2. 2-3个场景 —— 包含通用面试版与组织专属评估版，覆盖核心能力
  3. 一层内容 —— 通常为L2（从业者深度）
  4. 基础评分标准 —— 未展示/部分具备/具备/优秀
  5. 一个反馈信号 —— 员工完成培训后提出的问题
根据使用过程中获得的经验逐步扩展框架。

Scenario: [Name]

输出持久化

Core decision structure: [What judgment is being tested]
Interview variant:
[Generic situation]
Assessment variant:
[Organization-specific situation]
Competencies assessed: [IDs]
What good looks like:
  • [Consideration]
Red flags:
  • [Weak response indicator]
undefined
该Skill会将主要输出写入文件，确保跨会话的工作持续性。

Progression Template

输出位置确认

Foundation (Role: Everyone)
├── [COMP-1]: [Name]
└── [COMP-2]: [Name]

├─► Intermediate (Role: [Role])
│   ├── [COMP-3]: [Name] (requires: COMP-1)
│   └── [COMP-4]: [Name] (requires: COMP-2)

└─► Specialist (Role: [Role])
    └── [COMP-5]: [Name] (requires: COMP-3, COMP-4)
在开展任何工作之前：
  1. 检查项目中是否存在 
    context/output-config.md
    文件
  2. 若存在，查找该Skill对应的配置项
  3. 若不存在或无该Skill的配置项，先询问用户：
    • "我应将本次Competency Builder会话的输出保存至何处？"
    • 建议路径：
      explorations/competency/
      或项目中合适的位置
  4. 保存用户的偏好：
    • 若存在上下文网络，保存至 
      context/output-config.md
    • 否则保存至项目根目录的 
      .competency-builder-output.md

Feedback Loop Template

主要输出内容

markdown
undefined
对于该Skill，需持久化保存以下内容：
  • 诊断状态 - 适用的能力框架状态
  • 能力定义 - 从失败模式推导得出的能力项
  • 场景设计 - 每项能力的测试场景
  • 框架结构 - 进阶模型与依赖关系
  • 反馈回路设计 - 差距识别机制

Feedback Loop Design

会话内容与文件内容的划分

Observation mechanism:
  • How questions are logged
  • What context is captured
  • How they're tagged to competencies
Analysis cadence: [frequency]
Pattern categories:
  • Training gap: [who handles]
  • Framework gap: [who handles]
  • Process gap: [who handles]
  • Tooling gap: [who handles]
Change tracking:
  • How changes are documented
  • How effectiveness is measured

---
写入文件保留在会话中
状态诊断澄清类问题
能力定义失败模式讨论
场景模板结构迭代讨论
框架架构实时反馈

Minimum Viable Framework

文件命名规则

If starting small:
  1. 3-5 core competencies — the ones that matter most
  2. 2-3 scenarios — interview + assessment variants covering core competencies
  3. One layer of content — probably L2 (practitioner depth)
  4. Basic rubric — not demonstrated / partial / competent / strong
  5. One feedback signal — what questions do people ask after training?
Expand based on what you learn from using it.
格式：
{领域}-competency-{日期}.md
示例：
ai-literacy-competency-2025-01-15.md

Output Persistence

该Skill不负责的工作

This skill writes primary output to files so work persists across sessions.
  • 编写培训内容 —— 你负责搭建结构，由用户编写内容
  • 指定具体能力项 —— 你帮助用户从失败模式中发掘适合其场景的能力项
  • 评估现有培训的“优劣” —— 你仅诊断缺失的要素
  • 替代领域专家 —— 你提供方法论，用户提供领域知识

Output Discovery

健康检查问题

Before doing any other work:
  1. Check for 
    context/output-config.md
    in the project
  2. If found, look for this skill's entry
  3. If not found or no entry for this skill, ask the user first:
    • "Where should I save output from this competency-builder session?"
    • Suggest: 
      explorations/competency/
      or a sensible location for this project
  4. Store the user's preference:
    • In 
      context/output-config.md
      if context network exists
    • In 
      .competency-builder-output.md
      at project root otherwise
在能力框架开发过程中，需询问以下问题：
  1. 所有能力是否都描述了可观察的实际能力（而非知识状态）？
  2. 每个场景是否都需要无法通过查阅文档获得的判断能力？
  3. 内容是否针对不同受众进行了合理分层？
  4. 验证环节是否与真实决策挂钩？
  5. 是否有机制可以发现框架的不足？
  6. 框架是否已基于反馈完成更新？
  7. 具备已有知识的员工能否跳过部分内容？
  8. 所有员工都遵循相同路径，还是路径已实现个性化？

Primary Output

集成点

For this skill, persist:
  • Diagnosed state - which competency framework state applies
  • Competency definitions - derived from failure modes
  • Scenario designs - test scenarios for each competency
  • Framework structure - progression model and dependencies
  • Feedback loop design - how gaps will be identified
Skill关联方式
research构建需要领域专业知识的L3内容时使用
framework-development相关但不同：普通框架用于捕获知识；能力框架用于培养能力
framework-to-mastra能力框架 + 反馈回路 = 可部署的Agent

Conversation vs. File

交互示例

Goes to FileStays in Conversation
State diagnosisClarifying questions
Competency definitionsDiscussion of failure modes
Scenario templatesIteration on structure
Framework architectureReal-time feedback
用户： "我们有一份40页的安全政策。所有人都‘完成’了培训，但仍不断犯错。"
诊断结果： CF1（内容优先陷阱）
需提出的问题：
  • 员工“完成”培训后最常犯的3类错误是什么？
  • 员工需要运用这些知识做出哪些决策？
  • 当员工犯错时，他们未能识别或完成哪些行为？
指导建议： "每个错误都表明存在能力差距。我们可以倒推：如果员工错误处理敏感数据，那么缺失的能力可能是‘能够根据组织分类标准对数据进行分类’。一旦我们从失败模式中提炼出3-5项能力，就会设计场景来测试员工是否能实际应用知识——而非仅回忆知识。"

File Naming

来源框架

Pattern: 
{domain}-competency-{date}.md
Example: 
ai-literacy-competency-2025-01-15.md
源自：
references/competency-framework-development.md

What This Skill Does NOT Do

—
  • Write training content — You help structure, they write content
  • Prescribe specific competencies — You help them discover theirs from failure modes
  • Assess whether existing training is "good" — You diagnose what's missing
  • Replace subject matter expertise — You provide methodology, they provide domain knowledge
—

Health Check Questions

—
During competency framework development, ask:
  1. Do all competencies describe observable capabilities (not knowledge states)?
  2. Does each scenario require judgment that can't be looked up?
  3. Is content layered appropriately for different audiences?
  4. Does verification connect to real decisions?
  5. Is there a mechanism to learn what's not working?
  6. Has the framework changed based on feedback?
  7. Can someone with prior knowledge skip parts?
  8. Does everyone follow the same path, or is it personalized?
—

Integration Points

—
SkillConnection
researchUse when building L3 content that requires domain expertise
framework-developmentRelated but distinct: frameworks capture knowledge; competency frameworks build capability
framework-to-mastraCompetency framework + feedback loop = deployable agent
—

Example Interaction

—
User: "We have a 40-page security policy. Everyone 'completes' the training but keeps making mistakes."
Diagnosis: CF1 (Content-First Trap)
Questions to ask:
  • What are the 3 most common mistakes people make after "completing" training?
  • What decisions do people make that require this knowledge?
  • When someone makes a mistake, what did they fail to recognize or do?
Guidance: "Each mistake suggests a competency gap. Let's work backward: if someone incorrectly handles sensitive data, the missing competency might be 'Can classify data according to organizational categories.' Once we have 3-5 competencies from failure modes, we'll design scenarios that test whether someone can actually apply the knowledge—not just recall it."
—

Source Framework

—
Derived from: 
references/competency-framework-development.md
—