Agent skill

Intent Taxonomy Builder

챗봇의 의도(Intent) 분류 체계를 체계적으로 설계하는 방법론. An agent skill from revfactory/harness-100.

Apache-2.0Auto-check passed

Install Intent Taxonomy Builder

skills CLI

$ npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 intent-taxonomy-builder --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder .claude/skills/intent-taxonomy-builder && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "intent-taxonomy-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder into .claude/skills/intent-taxonomy-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intent-taxonomy-builder", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/revfactory/harness-100/tree/main/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 intent-taxonomy-builder --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .agents/skills && cp -r skills-src/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder .agents/skills/intent-taxonomy-builder && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "intent-taxonomy-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder into .agents/skills/intent-taxonomy-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intent-taxonomy-builder", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 intent-taxonomy-builder --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder .cursor/skills/intent-taxonomy-builder && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "intent-taxonomy-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder into .cursor/skills/intent-taxonomy-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intent-taxonomy-builder", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/revfactory/harness-100.git --path ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 intent-taxonomy-builder --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder .gemini/skills/intent-taxonomy-builder && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "intent-taxonomy-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder into .gemini/skills/intent-taxonomy-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intent-taxonomy-builder", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install revfactory/harness-100 intent-taxonomy-builder

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .github/skills && cp -r skills-src/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder .github/skills/intent-taxonomy-builder && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "intent-taxonomy-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder into .github/skills/intent-taxonomy-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intent-taxonomy-builder", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 intent-taxonomy-builder --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder .opencode/skills/intent-taxonomy-builder && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "intent-taxonomy-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder into .opencode/skills/intent-taxonomy-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intent-taxonomy-builder", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: intent-taxonomy-builder
GitHub stars: 1.3k
Token cost: ~830 tokens
SKILL.md length: 169 words
Files: 1
Skills in repo: 464
Repo updated: Mar 22, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

챗봇의 의도(Intent) 분류 체계를 체계적으로 설계하는 방법론. An agent skill from revfactory/harness-100.

SKILL.md covers 대상 에이전트, 의도 분류 체계 설계 프레임워크, 엔티티 설계 방법론 and 학습 데이터 생성 가이드, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Intent Taxonomy Builder is an agent skill from revfactory/harness-100. 챗봇의 의도(Intent) 분류 체계를 체계적으로 설계하는 방법론. '의도 분류 설계', 'intent 체계', 'NLU 의도 목록', '엔티티 사전', '슬롯 설계' 등 챗봇 의도 분류 체계 설계 시 사용한다. 단, 실제 NLU 모델 학습, 클라우드 NLU 서비스 배포는 이 스킬의 범위가 아니다.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is Apache-2.0.

Example prompts

“intent 체계”
“NLU 의도 목록”
“/intent-taxonomy-builder”

What it can do on your machine

Read from SKILL.md and the folder at commit 8e8d35c. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Intent Taxonomy Builder loads about 830 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 169 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~48
When it runs · the whole SKILL.md, loaded when a task matches: ~830

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 169 words, ~830 tokens.

Download SKILL.mdSave it as .claude/skills/intent-taxonomy-builder/SKILL.md (or your agent's skills folder).

name: intent-taxonomy-builder
description: 챗봇의 의도(Intent) 분류 체계를 체계적으로 설계하는 방법론. '의도 분류 설계', 'intent 체계', 'NLU 의도 목록', '엔티티 사전', '슬롯 설계' 등 챗봇 의도 분류 체계 설계 시 사용한다. 단, 실제 NLU 모델 학습, 클라우드 NLU 서비스 배포는 이 스킬의 범위가 아니다.

Intent Taxonomy Builder — 의도 분류 체계 설계 방법론

nlu-developer와 conversation-designer의 의도 분류 설계를 강화하는 스킬.

대상 에이전트

nlu-developer — 의도/엔티티/슬롯 체계를 설계할 때 사용
conversation-designer — 대화 시나리오와 의도를 매핑할 때 사용

의도 분류 체계 설계 프레임워크

1단계: 도메인 의도 수집

사용자 발화 수집 → 그룹핑 → 의도 후보 도출

수집 소스:
- 기존 FAQ 문서
- CS 문의 로그
- 경쟁사 챗봇 분석
- 사용자 인터뷰/설문
- 도메인 전문가 브레인스토밍

2단계: 의도 계층 구조

Level 0 (도메인)
├── Level 1 (카테고리)
│   ├── Level 2 (세부 의도)
│   └── Level 2
└── Level 1
    └── Level 2

예시 (이커머스):
commerce
├── order (주문)
│   ├── order.place — "주문하고 싶어요"
│   ├── order.status — "주문 상태 확인"
│   ├── order.cancel — "주문 취소해줘"
│   └── order.modify — "주문 변경하고 싶어요"
├── product (상품)
│   ├── product.search — "이런 상품 있어요?"
│   ├── product.detail — "이 상품 상세 정보"
│   └── product.compare — "두 상품 비교해줘"
├── payment (결제)
│   ├── payment.method — "결제 방법 알려줘"
│   ├── payment.refund — "환불 요청"
│   └── payment.receipt — "영수증 발급"
└── general (일반)
    ├── general.greeting — "안녕하세요"
    ├── general.goodbye — "감사합니다"
    └── general.fallback — (미인식)

3단계: 의도 품질 체크리스트

기준	설명	통과 조건
상호배타성	의도 간 중복 없음	발화 1개 = 의도 1개
완전성	모든 사용자 시나리오 커버	fallback < 10%
균형성	의도당 학습 데이터 균등	최소 20개 발화/의도
명확성	이름만으로 목적 파악	`verb.noun` 형식
적정 개수	관리 가능 범위	20~~50개 (소규모), 50~~150개 (대규모)

엔티티 설계 방법론

엔티티 유형

유형	설명	예시
시스템 엔티티	플랫폼 내장	@sys.date, @sys.number, @sys.email
사전 엔티티	도메인 고정 목록	메뉴명, 사이즈, 색상
패턴 엔티티	정규식 기반	주문번호(`ORD-\d{8}`), 전화번호
복합 엔티티	엔티티 조합	주소(시+구+동), 날짜범위

엔티티-슬롯 매핑

의도: order.place
필수 슬롯:
  - product_name (@product) — "아메리카노"
  - quantity (@sys.number) — "두 잔"
선택 슬롯:
  - size (@size) — "톨 사이즈"
  - option (@option) — "얼음 적게"
  - takeout (@boolean) — "포장이요"

슬롯 미충족 시 → 프롬프트:
  - product_name 누락: "어떤 메뉴를 주문하시겠어요?"
  - quantity 누락: "몇 개 주문하시겠어요?"

학습 데이터 생성 가이드

발화 변형 패턴

원본: "주문 취소하고 싶어요"

변형 전략:
1. 어미 변형: "취소해주세요", "취소할래요", "취소 부탁드립니다"
2. 표현 대체: "주문 철회", "주문 취소", "주문 안 할래요"
3. 문맥 추가: "방금 주문한 거 취소", "아까 시킨 것 취소"
4. 오타/축약: "주문취소", "취소여", "캔슬"
5. 간접 표현: "주문한 거 안 받고 싶어요", "그냥 안 살래요"
6. 엔티티 포함: "ORD-12345678 취소해줘"

발화 수 가이드

의도 복잡도	최소 발화 수	권장 발화 수
단순 (인사/작별)	10	20
보통 (조회/확인)	20	50
복잡 (주문/변경)	30	80
혼동 가능 (유사 의도)	50	100+

의도 혼동 매트릭스 분석

높은 혼동 쌍 예시:
- order.cancel ↔ payment.refund (취소 vs 환불)
- product.search ↔ product.detail (검색 vs 상세)
- order.modify ↔ order.cancel (변경 vs 취소)

해결 전략:
1. 차별화 발화 추가 (각 의도의 고유 키워드 강화)
2. 의도 합병 (구분 불필요시)
3. 컨텍스트 의존 분리 (대화 상태 기반)
4. 확인 질문 ("취소를 원하시나요, 환불을 원하시나요?")

산출물 템플릿

yaml

intent_taxonomy:
  - intent: order.place
    description: "새 주문 접수"
    examples:
      - "아메리카노 두 잔 주문할게요"
      - "이거 주문하고 싶어요"
    required_slots:
      - name: product_name
        entity: "@product"
        prompt: "어떤 메뉴를 주문하시겠어요?"
    optional_slots:
      - name: quantity
        entity: "@sys.number"
        default: 1
    responses:
      success: "{product_name} {quantity}개 주문 접수되었습니다."
      slot_missing: "주문할 메뉴를 말씀해 주세요."

Files

Just SKILL.md in ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder of revfactory/harness-100.

Open the folder on GitHubat commit 8e8d35c

Compare with similar skills

Intent Taxonomy Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Intent Taxonomy Builder compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Intent Taxonomy Builder this skillrevfactory/harness-100	1.3k	—	~830	Automated safety check: Pass	Apache-2.0	6 mo ago
Taxonomy BuilderWILLOSCAR/research-units-pipeline-skills	513	—	~1k	Automated safety check: Pass	None	2 days ago
Intent Requirements IntakeYeachan-Heo/oh-my-claudecode	40k	—	~1.5k	Automated safety check: Pass	MIT	today
Browser Intentruvnet/ruflo	74k	—	~1.2k	Automated safety check: Notes	MIT	today
Team Builderaffaan-m/ECC	274k	1 repos	~1.8k	Automated safety check: Pass	MIT	2 days ago
Team Builderaffaan-m/ECC	274k	1 repos	~808	Automated safety check: Pass	MIT	2 days ago

Similar skills

Taxonomy Builder
WILLOSCAR/research-units-pipeline-skills
Build a 2+ level taxonomy (outline/taxonomy.yml) from a core paper set and scope constraints, with short descriptions per node.
513 GitHub stars~1k tokensUpdated 2 days ago
Auto-check passed
Intent Requirements Intake
Yeachan-Heo/oh-my-claudecode
Turns a pasted chat log or spoken problem report from support or ops staff into a reviewed five-section intent.md through numbered batches of questions.
40k GitHub stars~1.5k tokensUpdated today
Product & Project ManagementAuto-check passed
Browser Intent
ruvnet/ruflo
Execute a natural-language browser intent via page-agent (browseract) when the target is easier to describe than to select — degrades gracefully when page-agent or an OpenAI-compatible LLM provider…
74k GitHub stars~1.2k tokensUpdated today
Productivity & AutomationAuto-check: notes
Team Builder
affaan-m/ECC
Interactive picker that discovers available agent personas via the claude agents command and agents/ markdown globs, groups them into domains, has the user select up to five, dispatches them in…
274k GitHub starsUsed in 1 repo~1.8k tokens
Agent WorkflowsAuto-check passed
Team Builder
affaan-m/ECC
用于组合和派遣并行团队的交互式代理选择器
274k GitHub starsUsed in 1 repo~808 tokens
Auto-check passed
Dashboard Builder
affaan-m/ECC
Grafana、SigNoz、および同様のプラットフォーム用の実際のオペレータ質問に答える監視ダッシュボードを構築します。メトリクスを虚栄ボードではなく機能するダッシュボードに変える場合に使用します。
274k GitHub stars~221 tokensUpdated 2 days ago
DevOps & CloudAuto-check passed

Questions about Intent Taxonomy Builder

What does Intent Taxonomy Builder do?

챗봇의 의도(Intent) 분류 체계를 체계적으로 설계하는 방법론. An agent skill from revfactory/harness-100. Intent Taxonomy Builder is an agent skill from revfactory/harness-100. 챗봇의 의도(Intent) 분류 체계를 체계적으로 설계하는 방법론.

How do I install Intent Taxonomy Builder in Claude Code?

Run `npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a claude-code`. Or copy the skill folder (ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder in revfactory/harness-100) into .claude/skills/intent-taxonomy-builder in your project. Claude Code loads it when a task matches its description.

How do I install Intent Taxonomy Builder in Codex?

Run `npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a codex`. Or copy the skill folder (ko/38-chatbot-builder/.claude/skills/intent-taxonomy-builder in revfactory/harness-100) into .agents/skills/intent-taxonomy-builder in your project. Codex loads it when a task matches its description.

Can I use Intent Taxonomy Builder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add revfactory/harness-100 --skill intent-taxonomy-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/intent-taxonomy-builder, .gemini/skills/intent-taxonomy-builder, .github/skills/intent-taxonomy-builder and .opencode/skills/intent-taxonomy-builder in your project.

What does Intent Taxonomy Builder need to run?

SKILL.md names no scripts, command-line tools or credentials: Intent Taxonomy Builder is instructions for the agent only.

Does Intent Taxonomy Builder access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Intent Taxonomy Builder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Intent Taxonomy Builder use?

Intent Taxonomy Builder is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Intent Taxonomy Builder use?

About 830 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Intent Taxonomy Builder?

Skills that share tags, products or a category with Intent Taxonomy Builder: Taxonomy Builder (WILLOSCAR/research-units-pipeline-skills, 513 stars), Intent Requirements Intake (Yeachan-Heo/oh-my-claudecode, 40k stars), Browser Intent (ruvnet/ruflo, 74k stars) and Team Builder (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Intent Taxonomy Builder?

revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,290 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.

Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Intent Taxonomy Builder

Facts

At a glance

What it does

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Intent Taxonomy Builder — 의도 분류 체계 설계 방법론

대상 에이전트

의도 분류 체계 설계 프레임워크

1단계: 도메인 의도 수집

2단계: 의도 계층 구조

3단계: 의도 품질 체크리스트

엔티티 설계 방법론

엔티티 유형

엔티티-슬롯 매핑

학습 데이터 생성 가이드

발화 변형 패턴

발화 수 가이드

의도 혼동 매트릭스 분석

산출물 템플릿

Files

Compare with similar skills

Similar skills

More from revfactory/harness-100

Questions about Intent Taxonomy Builder