thematic-analysis

thematic-analysis is a skill for Claude Code, Codex from yipng05-max/-skills. It costs 225 tokens per session (4,162 once invoked), scanned A, original, MIT.

A qualitative research aid for reflexive thematic analysis, a method for finding patterns of meaning in interview data. It can start from raw interview transcripts or an existing pool of initial codes.

In plain words
What is it for?
Use it to code interviews, group related codes, review possible themes, and suggest names and boundaries for a candidate theme structure.
Why use it?
It gives researchers a structured way to move from interview text or codes to possible themes, while showing unclear boundaries and leaving final theme names to the researcher.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to code interviews, group related codes, review possible themes, and suggest names and boundaries for a candidate theme structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yipng05-max/-skills/thematic-analysis
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yipng05-max/-skills --skill thematic-analysis
Clone the repo
git clone --depth 1 https://github.com/yipng05-max/-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for thematic-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/yipng05-max/-skills/thematic-analysis/github.svg)](https://agentmods.dev/skills/yipng05-max/-skills/thematic-analysis)
Your own site
<a href="https://agentmods.dev/skills/yipng05-max/-skills/thematic-analysis"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/thematic-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for thematic-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/yipng05-max/-skills/thematic-analysis"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/thematic-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,162 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00225 $0.04162
Opus 5 $0.00112 $0.02081
Sonnet 5 $0.00045 $0.00832
Haiku 4.5 $0.00022 $0.00416

Measured 9d ago against content hash fa8366317dfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

thematic-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

thematic-analysis/SKILL.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

主题分析辅助工具(Thematic Analysis)

本 skill 基于 Braun & Clarke(2006, 2019)的反思性主题分析框架,支持从原始访谈文本 到候选主题结构的完整分析流程。

重要定位:主题命名是分析行为,体现研究者的理论判断,最终命名必须由研究者作出。 本 skill 在命名阶段只提供备选,不做裁定。

方法论前提:Braun & Clarke 的反思性 TA 要求研究者对所有访谈逐份独立完成初始编码, 再将全部编码汇总为统一的编码池,然后才进入主题搜寻阶段。


启动:确认输入类型

触发后,第一步必须确认输入类型

"你现在准备做主题分析——你手上有的是: A. 原始访谈文本(尚未编码) B. 已完成的初始编码(一份或多份) 哪种情况?"

情况 A:提供原始访谈文本 → 进入初始编码阶段

情况 B:提供已有初始编码 → 询问是否已汇总,进入编码池处理


编码风格确认(情况 A 专用,可选)

确认为情况 A 后,在正式开始编码前,询问研究者是否希望提供示范编码:

"在正式编码前,你可以选择: A. 研究者示范:你先对文本中任意一小段(3–5 句)做示范编码,AI 会识别你的编码风格,然后按你的风格完成后续编码 B. AI 直接编码:跳过示范,AI 按照标准原则直接开始

哪种方式?(选 B 或不回应则直接开始)"

若研究者选择 A(研究者示范):

  1. 请研究者提供示范片段及其对应编码(格式:"原文" → [编码标签]
  2. AI 分析示范编码的风格特征,明确说明:
    • 粒度:偏细(逐句)还是偏粗(逐段)?
    • 用词:in-vivo(受访者原话)为主,还是研究者概括语言为主?
    • 长度:编码标签通常几个字?
    • 描述取向:倾向描述行为,还是描述情绪/态度?
  3. 输出风格确认:

    "我理解你的编码风格是:[描述]。我将按照此风格完成后续编码。如有偏差,请随时纠正。"

  4. 按研究者风格继续执行步骤 1–2.5

若研究者选择 B 或未回应:

直接进入步骤 1,按标准原则编码。


初始编码阶段(情况 A)

TA 的初始编码与扎根理论的开放编码有本质差异:

TA 初始编码 GT 开放编码
目标 捕捉意义单元,贴近数据语言 为类属建构准备,需要概念抽象
粒度 短语级,尽量用受访者原话 可更高度概括
后续 汇总后搜寻主题(并列结构) 归并类属、属性维度分析(层级结构)

单份访谈编码操作

研究者提供原始访谈文本后,执行以下步骤:

步骤 1:通读全文,识别意义单元

逐句扫描全文。只有以下两类才可跳过,且必须在编码结果中标注"已跳过":

  • 纯粹的单词应答,独立成句(如仅有"嗯""对""好的")
  • 访谈者的提问语句本身(非受访者发言)

其余所有语句,无论看起来信息量多少,都作为意义单元处理并给出编码。某句话是否重要,是研究者的判断权,不是 AI 的判断权。当不确定时,给出一个描述性编码(如"重复前述观点""表达不确定"),而不是跳过。

步骤 2:逐单元生成初始编码

编码原则:

  1. 贴近数据:编码词汇尽量来自受访者的语言,而非研究者的理论术语
  2. 描述性:编码描述"发生了什么"或"受访者表达了什么",不解释"为什么"
  3. 细粒度:一个意义单元只给一个最准确的编码,不做归并
  4. in-vivo 优先:若受访者某个表达特别精准,直接用原话作为编码
  5. 禁止对仗整齐:编码标签的字数和句法结构应由数据内容决定,而非由输出形式决定。in-vivo 编码可长可短,描述性编码因意义单元的复杂程度而异。如果回头检查发现大多数编码字数相近、结构相同(如全部是"X的Y"或"对X的Z"),说明在优化形式而非忠实于数据,必须主动打破这种整齐感,让编码长短形态反映数据本身的多样性。

输出格式:

【访谈 N】初始编码
(被访者简称 / 编号)

原文片段 → 编码
"......" → [编码标签]
"......" → [编码标签]
...

本份编码总数:N 条

步骤 2.5:自动保存编码结果到文件(强制执行,不可跳过)

编码输出完成后,必须立即调用 Write 工具将编码写入文件。不得仅在对话中输出而不写文件。

文件命名规则:coding_[被访者编号或简称].md (如 coding_A.mdcoding_P1.md

Read the full file on GitHub · 416 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 416 lines · 225 tokens per session scan A fa8366317dfa

Subscribe to this mod's changes

thematic-analysis is a skill published in the GitHub repository yipng05-max/-skills (285 stars, last pushed 4mo ago), licensed MIT. It adds 225 tokens to every session and 4,162 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens