theory-analysis-wom-motivation
About theory-analysis-wom-motivation
This skill analyzes why people share experiences or opinions using Word-of-Mouth Motivation Theory. It accepts evidence from interviews, support conversations, social posts, research notes, and observations, and returns traceable annotations in JSON and Markdown.
Key features
- 01Checks required input before analysis
- 02Codes four word-of-mouth motives
- 03Links conclusions to quoted evidence
- 04Outputs JSON and Markdown
- 05Supports optional review-mining-stp handoff
Use cases
- 01Analyzing motives in interview summaries
- 02Coding evidence from support conversations
- 03Comparing motives across social posts
- 04Preparing annotations for review-mining-stp
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ timlai666/ skills --skill theory-analysis-wom-motivationAfter installing, type/theory-analysis-wom-motivationin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
agents/openai.yamlreferences/00-theory-foundation.md01-input-and-gate.md02-dimension-coding-rules.md03-output-contract-json-markdown.md04-worked-example-turbocharger.mdDetails
From the project READMETheory Analysis WOM Motivation
Overview
用口碑動機理論(Word-of-Mouth Motivation Theory)解析證據提供者為何願意分享經驗或態度。
來源可為訪談摘要、客服對話、社群貼文、研究筆記、觀察紀錄等,不限於評論。
本 skill 含完整理論章節,可在分析前先校準口碑動機的判讀邏輯。
此 skill 可單獨使用,也可選擇把結構化結果交給 review-mining-stp。
Input Contract
至少提供:
analysis_goal: stringevidence_items: arrayitem_id: stringcontent: stringcontent_type: string
建議可選:
source_type: stringsource_ref: stringcontext_tags: string[]
Data Sufficiency Gate
缺必要資訊時,輸出 MissingDataOutput,不直接推論口碑動機。
{
"missing_fields": [],
"why_needed": {},
"questions_to_user": [],
"next_step_rule": "Provide analysis_goal and at least one evidence item with item_id, content, and content_type, then rerun coding."
}
Workflow
- 先讀
references/00-theory-foundation.md,校準理論概念、動機類型與研究應用語境。 - 讀
references/01-input-and-gate.md,檢核資料完整度。 - 讀
references/02-dimension-coding-rules.md,依四種口碑動機做證據標註:altruisticsocial_identityself_enhancementemotional_expression
- 讀
references/03-output-contract-json-markdown.md,輸出 JSON + Markdown。 - 用
references/04-worked-example-turbocharger.md對齊格式與深度。
STP Integration
theory_annotations.family固定為wom_motivationtheory_annotations.subtheory只可使用:altruisticsocial_identityself_enhancementemotional_expression
結果可直接對接 review-mining-stp 的理論標註。
review-mining-stp 屬於 optional downstream,不是本 skill 的必要依賴。
Quality Rules
- 口碑動機需要有可辨識意圖,若無意圖訊號需標記
insufficient。 self_enhancement與social_identity必須區分:- 前者偏「展現專業或能力」
- 後者偏「取得社群認同或歸屬」
- 所有結論都要可被
evidence_quotes追溯。
Suggested Prompts
Use $theory-analysis-wom-motivation to code sharing motives from mixed evidence items and return JSON + Markdown in Traditional Chinese.請用 $theory-analysis-wom-motivation 分析多來源證據中的口碑動機,並輸出可選串接 review-mining-stp 的 theory_annotations。