mjaskolski

Elicitation - how to talk with humans and ask them questions?

Data Analysisv1.0.4
By mjaskolskiUpdated 2026-05-115 versions · latest released 2026-02-04elicitation@clawhub_mjaskolski/elicitation
Data InsightsUser Analytics#Personal

According to AlphaMoat, as of 2026-10, Elicitation - how to talk with humans and ask them questions? has 7,448 downloads and 20 stars — ranked by downloads #3,764 among 10,914 AI skills in this ranking, and #347 of 915 in Data Analysis.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
7.4K
Stars
20
Overall download rank
#3,764
Top 35% overall · Top 38% in Data Analysis
PlatformDownloadsStarsComments
ClawHub ↗4.8K201
SkillHub ↗7.4K20—

Platforms count differently and update at different times.

What this skill does

It targets interview scripts, user research flows and dialogue design, holding that depth comes from patience rather than probing and using methods such as the OARS framework to create conditions for authentic self-disclosure. It also reviews such material against the research traditions it draws on. Psychological profiling may involve sensitive memories and experiences. Use only in transparent, consent-based settings with privacy, retention, opt-out and non-diagnostic boundaries; let people decline sensitive questions. Treat interpretations as tentative, cross-check explicit statements, and do not use them for clinical, hiring, surveillance or coercive judgments.

Profile published 2026-10-27

What you can do with it

  • Design interview questions that do not feel intrusive
  • Review whether a dialogue script presses too hard

When to use it

  • When a depth interview is being designed
  • When judging whether a conversation over-probes

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Design interview questions that reveal user values
Check this interview script for pressure tactics

Monthly Trend

Downloads7.4K
3.8K5.7K7.7K2026-03 · Downloads 4.0K2026-05 · Downloads 4.5K2026-06 · Downloads 4.6K2026-07 · Downloads 4.8K2026-08 · Downloads 5.0K2026-09 · Downloads 5.5K2026-10 · Downloads 7.4K26-0326-0926-10
Stars20
1920202026-03 · Stars 192026-05 · Stars 202026-06 · Stars 202026-07 · Stars 202026-08 · Stars 202026-09 · Stars 202026-10 · Stars 2026-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-107.4K—20
2026-095.5K—20
2026-085.0K+3.1%20
2026-074.8K+4.8%20
2026-064.6K+3.5%20
2026-054.5K—20
2026-034.0K—19

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

17 KB · ClawHub v1.0.4
---
name: elicitation
description: 'Psychological profiling through natural conversation using narrative identity
  research (McAdams), self-defining memory elicitation (Singer), and Motivational Interviewing
  (OARS framework). Use when you need to: (1) understand someone''s core values and motivations,
  (2) discover formative memories and life-defining experiences, (3) detect emotional schemas
  and belief patterns, (4) build psychological profiles through gradual disclosure,
  (5) conduct user interviews that reveal deep insights, (6) design conversational flows
  for personal discovery, (7) identify identity themes like redemption and contamination narratives,
  (8) elicit authentic self-disclosure without interrogation.'
Show all (476 lines)
license: MIT
metadata:
  author: tasteray
  version: "1.0"
---

# Elicitation

Psychological profiling through natural conversation.

## Goal

When reviewing or creating content related to psychological elicitation—whether conversation scripts, interview questions, user research flows, or any code that implements these techniques—**your goal is to achieve a 10/10 score**.

Score all work on a 0-10 scale based on adherence to the principles and techniques in this skill. Provide your assessment as **X/10** with specific feedback on what's working and what needs improvement to reach 10/10.

A 10/10 means the work:
- Embodies the core principle (depth through patience, not probing)
- Uses appropriate techniques from the research traditions
- Avoids all anti-patterns
- Creates conditions for authentic self-disclosure

Iterate until you reach 10/10.

---

## Core Principle

**Depth comes from patience, not probing.**

The most revealing information emerges when people feel safe to share, not when they're questioned. Your role is to create conversational space where self-disclosure feels natural and meaningful.

Key insight: People want to tell their stories. They rarely get the chance.

## Three Research Traditions

This skill synthesizes three complementary approaches:

### 1. Autobiographical Memory Research
How memories shape identity. Key finding: **Self-defining memories** (Singer) are the building blocks of personality—vivid, emotionally intense, frequently rehearsed memories linked to enduring concerns.

### 2. Narrative Identity Theory
How people construct life stories. Key finding: The **narrative themes** people use (redemption vs. contamination, agency vs. communion) predict psychological well-being better than the actual events (McAdams).

### 3. Motivational Interviewing
How to facilitate disclosure without resistance. Key finding: **Reflections outperform questions** at eliciting authentic self-disclosure. Aim for 2:1 reflection-to-question ratio (Miller & Rollnick).

---

## Self-Defining Memories

Jefferson Singer identified five criteria that make a memory "self-defining":

1. **Vivid** - Rich sensory and emotional detail
2. **Emotionally intense** - Strong feeling, positive or negative
3. **Frequently rehearsed** - Comes to mind often, told to others
4. **Linked to similar memories** - Part of a pattern or theme
5. **Connected to enduring concerns** - Reflects ongoing goals, conflicts, or unresolved issues

### Eliciting Self-Defining Memories

Don't ask: "What's your most formative memory?"

Instead, create conversational frames:

**The "keeps coming back" frame:**
> "Some memories just stay with us—they pop into our heads at unexpected moments, or we find ourselves telling them to new people in our lives. Is there a memory like that for you?"

**The "explains who I am" frame:**
> "When you're getting to know someone new and you want them to really understand where you're coming from, is there a story or moment you find yourself sharing?"

**The "turning point" frame:**
> "Looking back, was there a moment that felt like things shifted—where life before and after felt somehow different?"

### What Self-Defining Memories Reveal

| Memory Feature | Personality Insight |
|----------------|---------------------|
| Themes of mastery, achievement | High need for agency |
| Themes of connection, relationships | High need for communion |
| Redemption sequences (bad → good) | Resilience, generativity |
| Contamination sequences (good → bad) | Depression risk, unresolved trauma |
| Integration and meaning-making | Psychological maturity |
| Fragmentation and confusion | Identity diffusion |

See: [Self-Defining Memories Reference](elicitation/self-defining-memories.md)

---

## Life Story Interview: 8 Key Scenes

Dan McAdams' Life Story Interview asks for 8 specific "scenes" that reveal narrative identity:

1. **High Point** - Peak experience, most wonderful moment
2. **Low Point** - Nadir, most difficult moment
3. **Turning Point** - Moment of significant change
4. **Earliest Memory** - First clear memory
5. **Important Childhood Memory** - Vivid memory before age 12
6. **Important Adolescent Memory** - Vivid memory from teen years
7. **Important Adult Memory** - Significant recent memory
8. **One Other Important Memory** - Anything else that defines who they are

### Conversational Adaptations

You don't need to ask all 8 sequentially. Instead:

**Open with curiosity, not agenda:**
> "I'm curious about the moments that shaped you. Not necessarily the big resume stuff—more the experiences that stick with you."

**Follow their lead:**
When they mention a period of life, gently explore:
> "What was that time like for you? Any particular moments that stand out?"

**Bridge across time:**
> "That sounds like it mattered. Was there ever a moment earlier—or later—that connected to that same feeling?"

### Narrative Themes to Listen For

**Agency themes** (personal power, achievement, mastery):
- "I decided..."
- "I made it happen..."
- "I pushed through..."

**Communion themes** (connection, love, belonging):
- "We were all together..."
- "I felt so close to..."
- "They understood me..."

**Redemption sequences** (suffering leads to growth):
- "It was terrible, but..."
- "Looking back, I'm glad..."
- "That's what made me who I am..."

**Contamination sequences** (good becomes bad):
- "Things were great until..."
- "I thought I was happy, but..."
- "It ruined everything..."

See: [Narrative Identity Reference](elicitation/narrative-identity.md)

---

## OARS Framework

Motivational Interviewing's core skills, adapted for elicitation:

### Open Questions
Questions that can't be answered with yes/no. But use sparingly.

Instead of: "Did you like your childhood?"
Try: "What was it like growing up in your family?"

### Affirmations
Genuine recognition of strengths, efforts, or values—not compliments.

Instead of: "That's great!"
Try: "You valued honesty even when it was costly."

### Reflections
Restate or reframe what they said. This is the core skill.

**Simple reflection** (repeat back):
> "So you felt invisible in that moment."

**Complex reflection** (add meaning):
> "It sounds like recognition really matters to you—like you need to know your contributions are seen."

**Amplified reflection** (gently exaggerate):
> "So nothing they could have done would have made a difference." (Often prompts them to nuance their position)

**Double-sided reflection** (hold both truths):
> "On one hand, you loved the stability. On the other, you felt trapped."

### Summaries
Periodically gather what you've heard. Creates meaning and invites correction.

> "Let me see if I'm following: Growing up, you learned to be self-reliant because asking for help meant disappointment. But you've also noticed that pattern keeping people at a distance now. And you're wondering if there's another way."

### The 2:1 Ratio

**Aim for 2 reflections for every question.**

Questions gather information but can feel like interrogation. Reflections show understanding and invite elaboration.

Bad pattern:
> Q: "What happened?" → Q: "How did that feel?" → Q: "What did you do next?"

Better pattern:
> Q: "What happened?" → R: "That caught you off guard" → R: "You weren't sure what to make of it"

See: [Motivational Interviewing Reference](elicitation/motivational-interviewing.md)

---

## Values Elicitation

Shalom Schwartz's 10 Universal Values provide a framework for understanding motivation:

| Value | Core Concern |
|-------|--------------|
| **Self-Direction** | Independence, freedom, creativity |
| **Stimulation** | Novelty, excitement, challenge |
| **Hedonism** | Pleasure, enjoyment, gratification |
| **Achievement** | Success, competence, ambition |
| **Power** | Authority, wealth, social status |
| **Security** | Safety, stability, order |
| **Conformity** | Obedience, self-discipline, politeness |
| **Tradition** | Respect, commitment, humility |
| **Benevolence** | Helpfulness, loyalty, forgiveness |
| **Universalism** | Equality, justice, environmental protection |

### Values Elicitation Techniques

**Role model technique:**
> "Who do you admire? What is it about them specifically?"

**Opposite day technique:**
> "What kind of person could you never be? What would feel like a betrayal of yourself?"

**Decision archaeology:**
> "Think of a hard choice you made. What ultimately tipped the scales?"

**Anger as values signal:**
> "What makes you genuinely angry—not annoyed, but morally outraged?"

See: [Values Elicitation Reference](elicitation/values-elicitation.md)

---

## Schema Detection

Jeffrey Young's 18 Early Maladaptive Schemas are stable patterns of thinking and feeling that develop in childhood and persist across contexts:

### The Five Domains

**1. Disconnection & Rejection**
- Abandonment, Mistrust/Abuse, Emotional Deprivation, Defectiveness/Shame, Social Isolation

**2. Impaired Autonomy**
- Dependence/Incompetence, Vulnerability to Harm, Enmeshment, Failure

**3. Impaired Limits**
- Entitlement/Grandiosity, Insufficient Self-Control

**4. Other-Directedness**
- Subjugation, Self-Sacrifice, Approval-Seeking

**5. Overvigilance & Inhibition**
- Negativity/Pessimism, Emotional Inhibition, Unrelenting Standards, Punitiveness

### Downward Arrow Technique

When someone expresses a surface concern, gently probe for the deeper belief:

> Person: "I'm worried about the presentation."
> You: "What's the worst that could happen?"
> Person: "I could mess up in front of everyone."
> You: "And if that happened, what would that mean?"
> Person: "They'd see I don't know what I'm doing."
> You: "And what would that mean about you?"
> Person: "That I'm a fraud. That I don't deserve to be here."

The bottom of the arrow often reveals a schema (in this case: Defectiveness/Shame or Failure).

### Linguistic Markers of Schemas

| Schema | Language Patterns |
|--------|-------------------|
| Abandonment | "Everyone leaves eventually..." |
| Defectiveness | "There's something wrong with me..." |
| Failure | "I never finish anything..." |
| Emotional Deprivation | "No one really understands..." |
| Unrelenting Standards | "It's never good enough..." |

See: [Schema Detection Reference](elicitation/schema-detection.md)

---

## The Reminiscence Bump

People have disproportionately more and more vivid memories from ages 10-30 (the "reminiscence bump"). This is when identity forms.

**Target the bump:**
- First romantic relationship
- First job or career defining moment
- Leaving home
- Key friendships formed
- Educational turning points
- Early adult struggles and triumphs

**Bridge from present to bump:**
> "You mentioned feeling like an outsider at work. Was there a time earlier in life—maybe in school or when you were first starting out—when you felt something similar?"

---

## Question Sequences by Life Stage

Barbara Haight's Life Review Interview provides structured sequences:

### Childhood (before 12)
1. What was your home like?
2. What were your parents like?
3. What was your role in the family?
4. What were you like as a child?
5. What did you enjoy doing most?

### Adolescence (12-18)
1. How did your body change? How did you feel about it?
2. What was school like for you?
3. What were your friendships like?
4. What did you dream about becoming?
5. What was hardest about being a teenager?

### Early Adulthood (18-30)
1. What was leaving home like?
2. What were your first serious relationships?
3. What work did you do and how did you feel about it?
4. What were your goals during this time?
5. What was the biggest challenge you faced?

### Middle Adulthood (30-60)
1. How did your sense of yourself change?
2. What were your major accomplishments?
3. What losses did you experience?
4. How did your relationships evolve?
5. What did you learn about yourself?

### Later Life (60+)
1. How has your daily life changed?
2. What matters most to you now?
3. What legacy do you want to leave?
4. What do you understand now that you didn't before?
5. What would you tell your younger self?

See: [Question Sequences Reference](elicitation/question-sequences.md)

---

## Sensitizing Questions by Theme

James Birren's Guided Autobiography uses thematic prompts:

### Family Theme
- What was the emotional climate of your home?
- Who were you closest to? Who did you clash with?
- What family stories get told and retold?

### Work Theme
- What does work mean to you beyond earning money?
- When have you felt most fulfilled professionally?
- What work would you do even if you weren't paid?

### Money Theme
- What were the messages about money in your family?
- What does financial security mean to you?
- What would you do if money were no object?

### Health Theme
- How has your relationship with your body changed?
- What health experiences shaped how you think about life?
- How do you take care of yourself?

### Death Theme
- Have you experienced significant losses?
- How do thoughts of mortality affect how you live?
- What do you want to be remembered for?

### Meaning Theme
- What gives your life meaning?
- What beliefs or values guide you?
- What questions are you still trying to answer?

---

## Language Markers for Personality

LIWC (Linguistic Inquiry and Word Count) research identifies patterns, **but use with caution**:

| Pattern | Possible Indication |
|---------|---------------------|
| High "I" usage | Self-focus, possible depression, honesty |
| High "we" usage | Collectivist orientation, intimacy |
| Negative emotion words | Distress, but also processing |
| Cognitive complexity words (because, think, know) | Analytic thinking, meaning-making |
| Present tense focus | Immediacy, possibly impulsivity |
| Past tense focus | Reflection, possibly rumination |

### Critical Caveats

1. **Context matters enormously.** The same word patterns mean different things in different contexts.
2. **Cross-validate.** Never rely on language alone. Triangulate with behavior and explicit statements.
3. **Aggregates, not individuals.** LIWC findings are about group averages. Individual variation is huge.
4. **Cultural differences.** Word usage norms vary dramatically across cultures and languages.

See: [Language Inference Reference](elicitation/language-inference.md)

---

## Anti-Patterns

**What NOT to do:**

### The Interrogation Trap
Rapid-fire questions feel like an interview, not a conversation. People become guarded.

Instead: Slow down. Reflect more, question less.

### The Interpretation Leap
Jumping to psychological conclusions before you have evidence.

Instead: Hold hypotheses lightly. Seek disconfirming evidence.

### The Agenda Push
Steering toward topics you think are important rather than following their energy.

Instead: Let them lead. Their emphasis is data.

### The Premature Depth
Asking deeply personal questions before trust is established.

Instead: Earn disclosure gradually. Start with easier territory.

### The Therapy Cosplay
Using clinical language or techniques that imply you're treating them.

Instead: Be curious, not clinical. You're learning about them, not diagnosing.

### The Monologue Response
Responding to their disclosure with your own lengthy story.

Instead: Keep focus on them. Brief self-disclosure can build rapport, but always return to them.

### The Validation Trap
Agreeing with everything to maintain rapport.

Instead: Genuine reflections can gently challenge without confrontation.

---

## References

Detailed technique guides:

- [Narrative Identity](elicitation/narrative-identity.md) - McAdams' Life Story Interview, identity themes
- [Self-Defining Memories](elicitation/self-defining-memories.md) - Singer's memory elicitation techniques
- [Motivational Interviewing](elicitation/motivational-interviewing.md) - OARS framework deep dive
- [Schema Detection](elicitation/schema-detection.md) - Young's 18 schemas, downward arrow
- [Values Elicitation](elicitation/values-elicitation.md) - Schwartz's values, elicitation techniques
- [Question Sequences](elicitation/question-sequences.md) - Haight and Birren's structured approaches
- [Language Inference](elicitation/language-inference.md) - LIWC patterns and limitations

---

## Further Reading

Primary sources:

- Singer, J.A. & Salovey, P. (1993). *The Remembered Self: Emotion and Memory in Personality*
- McAdams, D.P. (2006). *The Redemptive Self: Stories Americans Live By*
- Miller, W.R. & Rollnick, S. (2023). *Motivational Interviewing* (4th ed.)
- Young, J.E., Klosko, J.S., & Weishaar, M.E. (2003). *Schema Therapy: A Practitioner's Guide*
- Schwartz, S.H. (1992). Universals in the content and structure of values. *Advances in Experimental Social Psychology*
- Haight, B.K. & Haight, B.S. (2007). *The Handbook of Structured Life Review*
- Birren, J.E. & Cochran, K.N. (2001). *Telling the Stories of Life through Guided Autobiography Groups*
- Pennebaker, J.W. & King, L.A. (1999). Linguistic styles: Language use as an individual difference. *Journal of Personality and Social Psychology*

Popular in Data Analysis

全能金融爬虫Data Analysis

中国金融机构数据爬取与分析综合 Skill v12.0.0。2334家/43大类机构名单、60+财经媒体源舆情、 A股报告/公告/研报、60+种查询多源金融数据(自动降级+缓存)、爬取调度与网页操作增强、 实时数据中枢、24 技术指标引擎、多源证据融合、110 MCP 工具 + 10 Resource + 14 Prompt。 🆕 v12.0.0 四条线(信息获取 / 打包下载 / 数据分析 / 登录): 编排:gather_info() 一次跑完"路由→抓取→去占位→质量分→能力边界→回执→打包", 8 类意图各带问法、输入输出、典型耗时与 not_for(说清哪件事做不了)。 诚实:反爬占位条目一律剔除并记账,空结果报 E_SOURCE_EMPTY,不把假数据判成 B 级成功。 交付:包内自带 manifest.json(逐文件 sha256),verify 查得出改动/缺失/多塞, 批量下载单条失败不中断整批,失败清单可直接只重下那几条。 登录:Cookie 由用户导出或扫码接管,档案化 + 健康度四档,对外输出全脱敏(值永不回显)。 何时触发:爬取机构、舆情爬取、东方财富、公告下载、实时行情、技术指标、统一查询、 交付包、批量重下、我已经登录了、登录态还有效吗(完整触发词见下方 auto_trigger)。

↓ 770.1K★ 288user_9d5a2a39
钢联AI - 智能问数Data Analysis

大宗商品价格数据查询技能。用于查询大宗商品期现货价格、宏观经济指标、产业链供需数据、进出口库存数据、金融市场数据等。当用户询问:(1) 期货/现货价格查询,如"螺纹钢价格"、"铜期货收盘价"; (2) 历史行情或趋势分析;(3) 区域或企业价格对比;(4) 宏观经济指标,如GDP、CPI;(5) 产业链上下游数据;(6) 多市场金融数据(期权、股票、债券、外汇);(7) 结算确认单生成时触发此技能。

↓ 704.6K★ 6u_9ed3401d
smart-chartsData Analysis

将数据文件(CSV/TSV/TXT/XLSX/XLS/JSON)转化为独立交互式 ECharts HTML 图表——32 类图表、3 套主题,全离线无需 CDN。出图前可先取数据画像(--profile:每列 dtype/基数/缺失/样本/统计、实体粒度、候选洞察信号、疑似非数据行),让 agent 在用户没说想看什么时自己读懂数据并决定出什么图——哪列是 ID、哪列是维度、出什么图,全部由 agent 从画像的客观事实自行判断,技能不代笔;每张图内置事实卡(plot_stats + data_preview),其数值是解读时唯一可引用的数字。本技能负责出图与算事实,不产出书面报告或叙事文档。触发:用户提供或指向表格数据文件并要求出图;提到「画图/出图/可视化/生成图表/generate a chart/make a graph」;想把表格渲染成交互式 HTML 图表。不触发:要的是书面报告、叙事分析或幻灯片;没有数据文件;需要后端的仪表盘;图片/音频/视频等非表格内容。

↓ 604.6K★ 135user_5b28ea14
AdMapixData Analysis

The data layer for AdMapix: turn ad and app queries into API calls that return raw JSON only.

↓ 574.6K★ 304fly0pants
论文配图一键生成Data Analysis

论文配图一键生成:一条命令从 JSON/CSV/Excel 生成顶刊级学术图表,科研绘图 与期刊配图全场景覆盖。40 种图表(森林图/KM 生存曲线(自动风险表)/竞争风险累计发生率/ROC/校准 曲线/决策曲线 DCA/列线图/RCS 非线性剂量反应/亚组分析森林图/RMST 限制平均生存时间/Galbraith 径向图/火山图/雨云图/山脊图/哑铃图/游泳图(逐例时长+里程碑)/ 肿瘤缓解瀑布图/UpSet 交集/PRISMA 流程图/漏斗/BA 一致性/PCA/热图/箱线/小提琴/ 组合图/Cox 多因素回归森林图等),9 套配色(含色盲安全 Okabe-Ito 与期刊色板),9 种期刊投稿预设, YAML 流水线一条命令出全套论文图,一次渲染多格式导出(TIFF/PNG/PDF), PDF 重叠门禁,600dpi。纯本地运行,数据不出机,中文零配置。适用:写论文/ 投稿要配图、把数据变成可投稿图表、批量重出全套图。不适用:文本润色/翻译/ 改写(请用写作类工具);商业报表/仪表盘/海报装饰;无数据支撑的纯示意图。

↓ 421.5K★ 83user_481397b5
smart-chartsData Analysis

Intelligent chart generation and data analysis skill. Reads user-supplied data files (CSV/Excel/JSON), analyzes data characteristics with LLM assistance, auto-recommends and generates interactive ECharts visualizations. Use when the user asks to analyze data, generate charts, create visualizations, or work with tabular data files.

↓ 257.5K★ 1user_814dbe54
股票/基金/期货量化分析工具Data Analysis

全球智能投研工具(stock-researcher)v13.0:多源数据 + 概率预测 + 可导出报告。 核心能力: - 多源数据路由:按市场/类别选源,逐级降级;每个结果标注来源与时效等级;源不可用时明确标 unavailable - 全资产量化:股票/ETF/场外基金/指数/期货(期限结构、基差、持仓、折溢价)多因子分析 - 概率预测:1d/5d/1M/3M/6M 经验分布 + 分位数 + 方向概率 + 区间,kNN 邻域收缩融合全局分布; 样本不足自动弃权,可按历史命中样本(同桶)做概率校准 - 证据链简报:每条结论绑定来源、时间与数据质量,冲突信号保留而不抹平 - 报告导出:Word/PPT/PDF/Markdown/JSON/纯文本,纯标准库渲染 + 可选第三方引擎 - MCP Server 24 工具,Claude Code 可直接调用;知识库 12 适配器双向同步 三条铁律: - 数据不装:拿不到就报不可用,不拿 0 价、不拿空表冒充 - 预测不装:概率来自历史相似条件的经验分布,样本不足就说不足,不硬给方向 - 评分≠盈利保证:任何结论都带免责声明

↓ 191.7K★ 147user_9d5a2a39
Tavily SearchData Analysis

Searches the public web through Tavily and returns structured results with links and snippets.

↓ 164.9K★ 286Xiaoran Li

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.