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

DeepTutor Skill Creator

by HKUDS in HKUDS/DeepTutor

Explains how to design and write DeepTutor skills: the SKILL.md anatomy, a trigger-focused description, concise content and progressive disclosure into reference files.

Apache-2.0Auto-check passedAgent Workflows

Install DeepTutor Skill Creator

skills CLI
$ npx skills add HKUDS/DeepTutor --skill skill-creator -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/DeepTutor skill-creator --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/HKUDS/DeepTutor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/deeptutor/skills/builtin/skill-creator .claude/skills/skill-creator && 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
skill-creator
GitHub stars
41k
Token cost
~840 tokens
SKILL.md length
372 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Explains how to design and write DeepTutor skills: the SKILL.md anatomy, a trigger-focused description, concise content and progressive disclosure into reference files.

  • Works in 5 steps: The description is the trigger. It is… → Concise is key. The context window is… → Match freedom to fragility. Open-ended… → …
  • Creating a new DeepTutor skill from scratch
  • SKILL.md covers What a skill is, Anatomy, Core principles and Writing workflow
  • Needs GITHUB_TOKEN

What it does

In DeepTutor a skill is a self-contained package of a `SKILL.md` playbook plus optional `references/` files. The system prompt carries only each skill's name and description, and the model reads the full body with a `read_skill` tool when a task matches. The skill separates skills, which teach procedures and domain knowledge, from persona presets for tone and teaching style, which are managed elsewhere.

It sets out the frontmatter fields, a lowercase hyphenated name with a length cap, and five principles: put all when-to-use guidance in the description, stay concise because the context window is shared, match freedom to how fragile the task is, keep SKILL.md short and push schemas and long examples into reference files, and avoid auxiliary files such as READMEs. The writing workflow starts by collecting concrete usage examples from you and identifying knowledge that is re-derived every time.

When your agent uses it

  • Creating a new DeepTutor skill from scratch
  • Improving a skill whose description does not trigger
  • Splitting a long SKILL.md into references
  • Learning how skills are loaded and read by the model

Example prompts

  • “Write a DeepTutor skill for generating quiz questions from lecture notes.”
  • “My skill never triggers. Rewrite its description so it states what it does and when to use it.”
  • “This SKILL.md is too long. Move the long examples into reference files.”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. The description is the trigger. It is the only text the model sees
  2. Concise is key. The context window is shared. Assume the model is
  3. Match freedom to fragility. Open-ended tasks → heuristics and
  4. Progressive disclosure. Keep SKILL.md under ~500 lines. Move
  5. No auxiliary files. No README, changelog, or setup guides inside a

What it can do on your machine

Read from SKILL.md and the folder at commit 6cf793b. 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 these keys or tokens, usually read from environment variables:

    • GITHUB_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

DeepTutor Skill Creator loads about 840 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 372 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~840

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 HKUDS/DeepTutor at commit 6cf793b, republished under its Apache-2.0 licence (© HKUDS). 372 words, ~840 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator/SKILL.md (or your agent's skills folder).
name
skill-creator
description
Design and author DeepTutor skills (SKILL.md packages). Use when the user wants to create a new skill, improve an existing skill, or asks how skills work.

Skill Creator

Guidance for authoring effective DeepTutor skills.

What a skill is

A skill is a self-contained capability package: a SKILL.md playbook plus optional references/ files. The system prompt only carries each skill's name + description; the model fetches the full body with the read_skill tool when a task matches. Skills teach procedural knowledge — workflows, domain expertise, format conventions — that no model fully possesses.

Behaviour/voice presets (tone, teaching style) are NOT skills — those are personas, managed separately.

Anatomy

my-skill/
├── SKILL.md          (required: frontmatter + instructions)
└── references/       (optional: docs loaded on demand via read_skill)

Frontmatter schema:

yaml
---
name: my-skill            # lowercase, digits, hyphens; max 64 chars
description: One line stating WHAT it does and WHEN to use it.
tags: [tool]              # optional, user-facing organisation
always: false             # optional: eager-inject into every turn
requires:                 # optional availability gates
  bins: [git]             # host CLI binaries
  env: [GITHUB_TOKEN]     # environment variables
  sandbox: shell          # needs the shell execution sandbox
---

Core principles

  1. The description is the trigger. It is the only text the model sees before deciding to read the skill. State both what the skill does and the situations that should trigger it. Put ALL "when to use" guidance here — a "When to Use" section in the body is read too late.
  2. Concise is key. The context window is shared. Assume the model is already smart; only add what it doesn't know. Challenge every paragraph: does it justify its token cost?
  3. Match freedom to fragility. Open-ended tasks → heuristics and principles (high freedom). Fragile, error-prone sequences → exact steps to follow (low freedom).
  4. Progressive disclosure. Keep SKILL.md under ~500 lines. Move schemas, long examples, and variant-specific details into references/<file>.md, and link them from SKILL.md with a clear note on when to read each (the model fetches them with read_skill(name, file="references/<file>.md")).
  5. No auxiliary files. No README, changelog, or setup guides inside a skill — only what the model needs to do the job.
Show full SKILL.md (128 more words)Show less

Writing workflow

  1. Collect concrete usage examples. Ask the user: "What would you say that should trigger this skill? What should it do?" Stop when the trigger phrases and expected behaviour are clear.
  2. Plan reusable content. For each example, identify what knowledge is re-derived every time — that belongs in the skill (body or references).
  3. Draft the skill. Imperative form throughout. Frontmatter first; verify the description passes the trigger test: would a model reading only this line know when to use the skill?
  4. Create it. Use the skill management UI (Space → Skills) or the skills API. The name becomes the directory name.
  5. Iterate from real use. After the skill fires on real tasks, tighten what the model stumbled over and delete what it never needed.

© HKUDS, 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 deeptutor/skills/builtin/skill-creator of HKUDS/DeepTutor.

Open the folder on GitHubat commit 6cf793b

Compare with similar skills

DeepTutor Skill Creator 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.

DeepTutor Skill Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
DeepTutor Skill Creator this skillHKUDS/DeepTutor41k—~840Automated safety check: PassApache-2.0
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official38k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 11 repos~3.5k tokens
    Agent WorkflowsAuto-check passed

  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    38k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    38k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed

  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    66k GitHub stars~1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from HKUDS/DeepTutor

  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Word Document Reader and Writer

    HKUDS/DeepTutor

    Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.

    41k GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • PDF Processing with Python

    HKUDS/DeepTutor

    Reads, extracts from, creates, merges, splits, watermarks, encrypts and fills PDF files with pdfplumber, pypdf and reportlab inside a Python sandbox.

    41k GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Excel Workbook Editor

    HKUDS/DeepTutor

    Reads, creates and edits Excel workbooks with openpyxl, including formulas, styles, charts and CSV or TSV tables, with advice on formula values openpyxl cannot compute.

    41k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Categories

Questions about DeepTutor Skill Creator

What does DeepTutor Skill Creator do?

Explains how to design and write DeepTutor skills: the SKILL.md anatomy, a trigger-focused description, concise content and progressive disclosure into reference files. md` playbook plus optional `references/` files. The system prompt carries only each skill's name and description, and the model reads the full body with a `read_skill` tool when a task matches.

When should I use DeepTutor Skill Creator?

DeepTutor Skill Creator fits situations like: creating a new DeepTutor skill from scratch; improving a skill whose description does not trigger; splitting a long SKILL.md into references; learning how skills are loaded and read by the model.

How do I install DeepTutor Skill Creator in Claude Code?

Run `npx skills add HKUDS/DeepTutor --skill skill-creator -a claude-code`. Or copy the skill folder (deeptutor/skills/builtin/skill-creator in HKUDS/DeepTutor) into .claude/skills/skill-creator in your project. Claude Code loads it when a task matches its description.

How do I install DeepTutor Skill Creator in Codex?

Run `npx skills add HKUDS/DeepTutor --skill skill-creator -a codex`. Or copy the skill folder (deeptutor/skills/builtin/skill-creator in HKUDS/DeepTutor) into .agents/skills/skill-creator in your project. Codex loads it when a task matches its description.

Can I use DeepTutor Skill Creator 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 HKUDS/DeepTutor --skill skill-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-creator, .gemini/skills/skill-creator, .github/skills/skill-creator and .opencode/skills/skill-creator in your project.

What does DeepTutor Skill Creator need to run?

Going by SKILL.md and its folder, DeepTutor Skill Creator needs credentials named GITHUB_TOKEN.

Does DeepTutor Skill Creator 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 DeepTutor Skill Creator 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 DeepTutor Skill Creator use?

DeepTutor Skill Creator 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 DeepTutor Skill Creator use?

About 840 tokens (SKILL.md is roughly 3.4k 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 DeepTutor Skill Creator?

Skills that share tags, products or a category with DeepTutor Skill Creator: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains DeepTutor Skill Creator?

HKUDS (a GitHub organization) maintains it in HKUDS/DeepTutor, which has 40,905 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.

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