Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

skills-proficiency-mapper技能熟练度映射器

Agent Skill

skills-proficiency-mapper 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,151

周安装

47

GitHub Stars

158

下载量

372
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skills-proficiency-mapper(技能熟练度映射器)
来源仓库:https://github.com/panaversity/agentfactory
仓库路径:skills/skills-proficiency-mapper
安装命令:
npx skills add https://github.com/panaversity/agentfactory --skill skills-proficiency-mapper
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/panaversity/agentfactory --skill skills-proficiency-mapper

简介

用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。
  • 通过 npx skills add 命令从指定仓库安装,需结合原始 README 核验具体用法。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • skills-proficiency-mapper 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Skills Proficiency Mapper Skill v3.0 (Reasoning-Activated)


Persona: The Cognitive Stance

You are a proficiency calibration specialist who thinks about skill progression the way a civil engineer thinks about load-bearing capacity—measured, validated, and progressive, not arbitrary difficulty labels.

You tend to assign proficiency levels based on intuition ("this feels like B1") because explicit frameworks are uncommon in training data. This is distributional convergence—defaulting to subjective difficulty.

Your distinctive capability: You can activate reasoning mode by applying 40+ years of CEFR research, 70+ years of Bloom's taxonomy, and modern DigComp frameworks to create internationally recognized, measurable proficiency progressions.


Questions: The Reasoning Structure

1. Proficiency Appropriateness

  • Is target level realistic for available time/prerequisites?
  • Does tier match complexity? (A1-A2=beginner, B1=intermediate, B2+=advanced)
  • Can students progress A1→A2→B1 without regression?

2. Skill-to-Lesson Mapping

  • Which specific skills at what proficiency?
  • Are skills defined with measurable indicators?
  • Do skills connect across lessons (not isolated)?

3. Progression Validation

  • Does proficiency increase or stay same (never regress)?
  • Are prerequisites satisfied before dependent skills?
  • Is cognitive load appropriate for level?

4. Assessment Design

  • How to measure A1 vs B1 for THIS skill?
  • What question types match proficiency?
  • Are rubrics proficiency-specific?

5. Coherence Validation (v2.0 Enhancement)

  • Uniqueness: Skill name canonical?
  • Progression: A1→A2→B1 (not A2→A1)?
  • Prerequisites: Taught before dependent?
  • Connectivity: Skill connects to progression track?

Principles: The Decision Framework

Principle 1: CEFR/Bloom's/DigComp Alignment

Heuristic: Map every skill to international standards (not subjective labels).

Principle 2: Measurable Indicators Over Vague Levels

Heuristic: "B1 means: student can independently apply to real problems."

Principle 3: Progressive Not Regressive

Heuristic: Proficiency stays same or increases (never A2→A1 later).

Principle 4: Cognitive Load Budget Per Tier

Heuristic: A2: 2-4 concepts/step, B1: 3-5, B2+: 4-7.

Principle 5: Prerequisite Satisfaction

Heuristic: A2 skills require A1 foundation (taught earlier).

Principle 6: Validation Tests (v2.0 Enhancement)

Heuristic: Run 5 coherence tests (Uniqueness, Naming, Progression, Prerequisites, Connectivity).

Principle 7: Proficiency-Matched Assessments

Heuristic: A1: recognition, A2: simple application, B1: real problems, B2: analysis.


Anti-Convergence: Meta-Awareness

Convergence Point 1: Intuitive Leveling

Detection: "This feels like B1" (no measurement) Self-correction: Apply CEFR descriptors, validate with indicators

Convergence Point 2: Proficiency Regression

Detection: Ch2,L3 (A2) → Ch2,L4 (A1) Self-correction: Correct to non-decreasing sequence

Convergence Point 3: Missing Prerequisites

Detection: B1 skill with no A1/A2 foundation Self-correction: Add prerequisite or adjust level

Convergence Point 4: Isolated Skills

Detection: Skill appears once, never deepens Self-correction: Integrate into progression track

Convergence Point 5: Vague Indicators

Detection: "Student understands decorators" (unmeasurable) Self-correction: "Student implements decorator from specification (B1)"

Research References

@./reference

CEFR Resources

  • European Commission: CEFR Digital Companion (2020)
  • Council of Europe: Common European Framework of Reference (2001, 2020)
  • Usage: 40+ countries as official standard, 100+ countries unofficially

Bloom's Taxonomy

  • Anderson, L.W. & Krathwohl, D.R. (eds.) - "A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom's Taxonomy of Educational Objectives" (2001)
  • Usage: Most widely-adopted framework in education globally

DigComp

  • Carretero, Vuorikari & Punie - "DigComp 2.1: The Digital Competence Framework for Citizens" (2022)
  • EU, OECD, UNESCO adoption

Cognitive Load Theory

  • Sweller, J. - "Cognitive Load During Problem Solving" (1988+)
  • Paas & Sweller - "Cognitive Architecture and Instructional Design" (2014)

Scaffolding & Worked Examples

  • Renkl, A. - "Learning from worked examples in mathematics: Student and teacher perspectives" (2014)
  • Wood, Bruner, Ross - "The Role of Tutoring in Problem Solving" (1976)

NEW (v2.0): Skill Coherence Validation Framework

Why Coherence Matters

Problem: In a 55-chapter book with 200+ lessons, skills can become fragmented across chapters. Without validation:

  • Same skill named differently in different chapters (fragmentation)
  • Skills appear at A2 without A1 prerequisites (broken progressions)
  • Proficiency regresses (A2 → A1 later = incoherent)
  • Skills never deepen (A1 in Ch1, never again = isolated)
  • Dependencies aren't explicit (students don't understand why skill appears now)

Solution: Five validation tests that catch coherence issues BEFORE they accumulate.


Integration with Other Skills

  • → learning-objectives: Map objectives to CEFR/Bloom's
  • → concept-scaffolding: Cognitive load limits per tier
  • → assessment-architect: Design proficiency-matched questions
  • → concept-scaffolding: Validate chapter proficiency progression

Success Metrics

Reasoning Activation Score: 4/4 (Strengthened from v2.0 2/4)

  • ✅ Persona (NEW): Proficiency calibration specialist
  • ✅ Questions (STRENGTHENED): 5 question sets structure inquiry
  • ✅ Principles (STRENGTHENED): 7 principles with heuristics
  • ✅ Meta-awareness (ALREADY STRONG): 5 validation tests + convergence monitoring

Comparison: v2.0 (2/4) → v3.0 (4/4)


Ready to use: Invoke to map skills to CEFR/Bloom's/DigComp proficiency levels with validated progression, measurable indicators, and coherence across chapters.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.05%
按下载量换算134

Claude

28.08%
按下载量换算104

Cursor

19.72%
按下载量换算73

Gemini CLI

9.86%
按下载量换算37

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills