New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Intent Taxonomy Builder

by revfactory in revfactory/harness-100

Methodology for systematically designing a chatbot's intent classification taxonomy.

Apache-2.0Auto-check passedAI & LLM Engineering

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/en/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/

Facts

Skill name
intent-taxonomy-builder
GitHub stars
1.3k
Token cost
~1.3k tokens
SKILL.md length
183 words
Files
1
Skills in repo
96
Repo updated
First seen
Licence
Apache-2.0

At a glance

Methodology for systematically designing a chatbot's intent classification taxonomy.

  • Works in 3 steps: Domain Intent Collection → Intent Hierarchy → Intent Quality Checklist
  • Intent taxonomy design
  • SKILL.md covers Target Agents, Intent Classification Taxonomy…, Entity Design Methodology and Training Data Generation Guide, 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. Methodology for systematically designing a chatbot's intent classification taxonomy. Use this skill for 'intent taxonomy design', 'intent system', 'NLU intent list', 'entity dictionary', 'slot design', and other chatbot intent classification taxonomy design tasks. Note: actual NLU model training and cloud NLU service deployment are outside the scope of this skill.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Fine-tuning. The licence is Apache-2.0.

When your agent uses it

  • Intent taxonomy design
  • NLU intent list
  • Entity dictionary
  • Other chatbot intent classification taxonomy design tasks

Example prompts

  • “s intent classification taxonomy. Use this skill for”
  • “intent system”
  • “NLU intent list”
  • “/intent-taxonomy-builder”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Domain Intent Collection
  2. Intent Hierarchy
  3. Intent Quality Checklist

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 1.3k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 183 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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). 183 words, ~1,315 tokens.

Download SKILL.mdSave it as .claude/skills/intent-taxonomy-builder/SKILL.md (or your agent's skills folder).
name
intent-taxonomy-builder
description
Methodology for systematically designing a chatbot's intent classification taxonomy. Use this skill for 'intent taxonomy design', 'intent system', 'NLU intent list', 'entity dictionary', 'slot design', and other chatbot intent classification taxonomy design tasks. Note: actual NLU model training and cloud NLU service deployment are outside the scope of this skill.

Intent Taxonomy Builder — Intent Classification Taxonomy Design Methodology

A skill that enhances intent classification design for the nlu-developer and conversation-designer.

Target Agents

  • nlu-developer — Used when designing intent/entity/slot systems
  • conversation-designer — Used when mapping conversation scenarios to intents

Intent Classification Taxonomy Design Framework

Step 1: Domain Intent Collection
Collect user utterances > Group > Derive intent candidates

Collection sources:
- Existing FAQ documents
- Customer service inquiry logs
- Competitor chatbot analysis
- User interviews/surveys
- Domain expert brainstorming
Step 2: Intent Hierarchy
Level 0 (Domain)
├── Level 1 (Category)
│   ├── Level 2 (Specific intent)
│   └── Level 2
└── Level 1
    └── Level 2

Example (E-commerce):
commerce
├── order
│   ├── order.place — "I want to place an order"
│   ├── order.status — "Check my order status"
│   ├── order.cancel — "Cancel my order"
│   └── order.modify — "I want to change my order"
├── product
│   ├── product.search — "Do you have this kind of product?"
│   ├── product.detail — "Details about this product"
│   └── product.compare — "Compare these two products"
├── payment
│   ├── payment.method — "What payment methods are available?"
│   ├── payment.refund — "Refund request"
│   └── payment.receipt — "Issue a receipt"
└── general
    ├── general.greeting — "Hello"
    ├── general.goodbye — "Thank you"
    └── general.fallback — (unrecognized)
Step 3: Intent Quality Checklist
CriterionDescriptionPass Condition
Mutual exclusivityNo overlap between intents1 utterance = 1 intent
CompletenessCovers all user scenariosfallback < 10%
BalanceEven training data per intentMinimum 20 utterances/intent
ClarityPurpose clear from name aloneverb.noun format
Appropriate countManageable range20-50 (small-scale), 50-150 (large-scale)

Entity Design Methodology

Entity Types
TypeDescriptionExamples
System entityPlatform built-in@sys.date, @sys.number, @sys.email
Dictionary entityDomain fixed listMenu items, sizes, colors
Pattern entityRegex-basedOrder number (ORD-\d{8}), phone number
Composite entityEntity combinationsAddress (city+district+street), date range
Entity-Slot Mapping
Intent: order.place
Required slots:
  - product_name (@product) — "Americano"
  - quantity (@sys.number) — "two"
Optional slots:
  - size (@size) — "tall size"
  - option (@option) — "less ice"
  - takeout (@boolean) — "to go"

When slot is unfilled > Prompt:
  - product_name missing: "What would you like to order?"
  - quantity missing: "How many would you like?"

Training Data Generation Guide

Utterance Variation Patterns
Original: "I want to cancel my order"

Variation strategies:
1. Ending variation: "Please cancel", "Cancel this", "I'd like to cancel please"
2. Expression substitution: "Revoke order", "Undo order", "I don't want my order anymore"
3. Context addition: "Cancel the order I just placed", "Cancel what I ordered earlier"
4. Typos/abbreviations: "cancle order", "cancel plz", "cxl"
5. Indirect expression: "I don't want to receive my order", "I changed my mind"
6. With entity: "Cancel ORD-12345678"
Utterance Count Guide
Intent ComplexityMinimum UtterancesRecommended Utterances
Simple (greeting/goodbye)1020
Medium (lookup/confirmation)2050
Complex (order/modification)3080
Easily confused (similar intents)50100+

Intent Confusion Matrix Analysis

High-confusion pair examples:
- order.cancel <> payment.refund (cancel vs refund)
- product.search <> product.detail (search vs detail)
- order.modify <> order.cancel (modify vs cancel)

Resolution strategies:
1. Add distinguishing utterances (strengthen unique keywords for each intent)
2. Merge intents (when distinction is unnecessary)
3. Context-dependent separation (based on dialog state)
4. Clarifying question ("Do you want to cancel or get a refund?")

Deliverable Template

yaml
intent_taxonomy:
  - intent: order.place
    description: "Place a new order"
    examples:
      - "I'd like to order two Americanos"
      - "I want to order this"
    required_slots:
      - name: product_name
        entity: "@product"
        prompt: "What would you like to order?"
    optional_slots:
      - name: quantity
        entity: "@sys.number"
        default: 1
    responses:
      success: "Your order for {quantity} {product_name}(s) has been placed."
      slot_missing: "Please tell me what you'd like to order."

© revfactory, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in en/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
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Intent Taxonomy Builder this skillrevfactory/harness-1001.3k—~1.3kAutomated safety check: PassApache-2.0
Peft Fine TuningOrchestra-Research/AI-Research-SKILLs13k9 repos~3.1kAutomated safety check: PassMIT
Hugging Face LLM Trainerhuggingface/skills11k3 repos~7.2kAutomated safety check: PassApache-2.0
Sentence-Transformers Training Routerhuggingface/skills11k1 repos~2.6kAutomated safety check: PassApache-2.0
Dataset Evaluationawslabs/agent-plugins9152 repos~1.3kAutomated safety check: PassApache-2.0
Train RlOpenPipe/ART11k—~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Peft Fine Tuning

    Orchestra-Research/AI-Research-SKILLs

    Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.

    13k GitHub starsUsed in 9 repos~3.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face LLM Trainer

    huggingface/skills

    Official

    Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.

    11k GitHub starsUsed in 3 repos~7.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Sentence-Transformers Training Router

    huggingface/skills

    Official

    Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.

    11k GitHub starsUsed in 1 repo~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Dataset Evaluation

    awslabs/agent-plugins

    Official

    Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).

    915 GitHub starsUsed in 2 repos~1.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Train Rl

    OpenPipe/ART

    RL training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Qwopus27b Rl Training

    R6410418/Jackrong-llm-finetuning-guide

    Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.

    1.7k GitHub stars~830 tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

More from revfactory/harness-100

All 96 skills in this repo

  • Anti Bot Analyzer

    revfactory/harness-100

    A skill for analyzing website anti-bot defense mechanisms and developing legitimate evasion strategies.

    1.3k GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed

  • API Error Design Patterns

    revfactory/harness-100

    Reference for designing how an API reports failures: structured error codes, response shapes, client-friendly messages, an error catalog and retry or fallback advice.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

  • API Security Checklist

    revfactory/harness-100

    Walks a backend-dev agent through OWASP API Top 10 checks, authentication and authorization patterns, and defense code during API design.

    1.3k GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed

  • Arg Parser Generator

    revfactory/harness-100

    Methodology for systematically designing and generating CLI tool argument parser structures.

    1.3k GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed

  • Audience Segmentation

    revfactory/harness-100

    Audience segmentation skill used by the analyst and curator agents.

    1.3k GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed

  • Audio Storytelling

    revfactory/harness-100

    Audio storytelling skill used by the podcast scriptwriter and show note editor.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Intent Taxonomy Builder

What does Intent Taxonomy Builder do?

Methodology for systematically designing a chatbot's intent classification taxonomy. Intent Taxonomy Builder is an agent skill from revfactory/harness-100. Methodology for systematically designing a chatbot's intent classification taxonomy.

When should I use Intent Taxonomy Builder?

Intent Taxonomy Builder fits situations like: intent taxonomy design; NLU intent list; entity dictionary; other chatbot intent classification taxonomy design tasks.

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 (en/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 (en/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 1.3k tokens (SKILL.md is roughly 5.3k 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: Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars), Hugging Face LLM Trainer (huggingface/skills, 11k stars), Sentence-Transformers Training Router (huggingface/skills, 11k stars) and Dataset Evaluation (awslabs/agent-plugins, 915 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 1,293 GitHub stars. The repository holds 96 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.