Agent skill

Skill Creator Skill

by OpenLoaf in OpenLoaf/OpenLoaf

Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill.

AGPL-3.0Auto-check passedAgent Workflows

Install Skill Creator Skill

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

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

GitHub CLI
$ gh skill install OpenLoaf/OpenLoaf skill-creator-skill --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/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/skill-creator/en .claude/skills/skill-creator-skill && 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-skill
GitHub stars
108
Token cost
~2.7k tokens
SKILL.md length
1,154 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill.

  • Works in 5 steps: Understand the Requirements → Write SKILL.md → Create openloaf.json (Optional but… → …
  • The user wants to create
  • SKILL.md covers Tool Inventory, Scope: Global Skill vs Project…, Step 1: Understand the… and Step 2: Write SKILL.md, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Creator Skill is an agent skill from OpenLoaf/OpenLoaf. Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill. Typical phrasings: "help me create a skill", "build a new skill", "turn what we just did into a skill", "write a skill that auto-XX", "tweak this skill", "why isn't this skill triggering", "edit my custom skill", "add a global skill", "add a skill to the current project". Any create / modify / tune request touching a SKILL.md under .openloaf/skills/ should load this skill. Also applies when the user wants to understand the…

Its SKILL.md is about 2.7k 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 Agent Workflows, covering Skill authoring. The repository describes itself as: 🍞Open-source, local-first AI workspace with Agents, multi-model chat (GPT/Claude/Gemini/DeepSeek), Notion-like docs, AI image & video generation, email, calendar & terminal…. The licence is AGPL-3.0.

When your agent uses it

  • The user wants to create
  • Debug an OpenLoaf custom Skill
  • Wants to understand the skill format
  • Troubleshoot triggering issues

Example prompts

  • “help me create a skill”
  • “build a new skill”
  • “turn what we just did into a skill”
  • “/skill-creator-skill”

Workflow steps

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

  1. Understand the Requirements
  2. Write SKILL.md
  3. Create openloaf.json (Optional but Recommended)
  4. Save to Disk
  5. Verify and Iterate

What it can do on your machine

Read from SKILL.md and the folder at commit f7eccf6. 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 markdown and json).

    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

Skill Creator Skill loads about 2.7k tokens when it runs. Until then it costs about 194 tokens; SKILL.md has 1,154 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~194
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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 OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 1,154 words, ~2,711 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator-skill/SKILL.md (or your agent's skills folder).
name
skill-creator-skill
description
Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill. Typical phrasings: "help me create a skill", "build a new skill", "turn what we just did into a skill", "write a skill that auto-XX", "tweak this skill", "why isn't this skill triggering", "edit my custom skill", "add a global skill", "add a skill to the current project". Any create / modify / tune request touching a `SKILL.md` under `.openloaf/skills/` should load this skill. Also applies when the user wants to understand the skill format, troubleshoot triggering issues, or solidify a conversation workflow into a reusable capability. Not for: modifying built-in skills (e.g. file-ops, email-ops) — those are read-only capabilities shipped with the platform.

Skill Creation and Optimization Guide

This skill guides you in creating, editing, and improving custom Skills for OpenLoaf. A Skill is a chunk of Markdown instructions that gets auto-loaded into the conversation when the user's request matches its description, letting the AI perform tasks following the method inside.

Tool Inventory

ToolResponsibilityRead-only
Read / Glob / GrepRead existing skills and locate anchors (always-available tools)Yes
WriteCreate new SKILL.md / openloaf.json / helper scripts (always-available tools)No
EditModify existing skill content (always-available tools)No

Loading: All core tools, always available, no ToolSearch activation needed. This skill has no dedicated deferred tools — it's an instructional skill that teaches the AI how to organize custom skill files.

Scope: Global Skill vs Project Skill

User-defined skills come in two scopes. Figure out where it belongs before doing anything. Priority from low to high: builtin < global < project; project skills override global skills of the same name.

Global Skill
  • Path: ~/.openloaf/skills/<skill-name>/SKILL.md
  • Visibility: All conversations across all projects
  • Fit for: Capabilities that generalize across projects / personal work habits / generic document generation / default output styles
  • Typical examples: "My fixed daily report template", "Run lint before committing code", "My translation glossary"
Project Skill
  • Path: {projectRoot}/.openloaf/skills/<skill-name>/SKILL.md
  • Visibility: Only conversations inside the current project
  • Fit for: Project-specific knowledge / code conventions / business processes / workflows that only make sense in this repo
  • Typical examples: "This repo's module conventions", "This project's API auth flow", "How to run E2E tests"
How to Choose
Does the capability only make sense in the current project (file paths, business terms, repo conventions)?
  └─ Yes → Project skill (default first choice)
  └─ No  → Reusable across projects (personal habits, generic templates)?
        └─ Yes → Global skill
        └─ Unsure → Start with a project skill; promote to global later if multiple projects need it

Iron rule: Project-specific business knowledge does not belong in global skills — it pollutes other projects. Conversely, stuffing a generic capability into a project skill misses the reuse opportunity. When uncertain, ask the user: "Is this capability only useful in this project, or do you want it in your other projects too?"

Step 1: Understand the Requirements

Before touching files, nail down four things (the conversation context may already contain the answers — don't ask again):

  1. What should the AI do with this skill? — Core capability description
  2. Under what circumstances should it trigger? — How the user will phrase it, in what scenarios
  3. What's the expected output? — Files, data, an operation result, or a conversation reply
  4. Is it global or project scope? — Use the decision tree above

If the user says "turn what we just did into a skill", review the conversation history to extract the actual tool sequence used, the decision logic, and places where the user corrected you — that's the knowledge the skill truly needs to capture.

Step 2: Write SKILL.md

Every skill is a folder, and the one essential file is SKILL.md.

File Structure
<skill-name>/
├── SKILL.md          # Required — skill instructions (YAML frontmatter + Markdown body)
├── openloaf.json     # Optional — UI metadata (icon, color, display name)
└── scripts/          # Optional — helper scripts (python/bash, etc.)
SKILL.md Format
markdown
---
name: my-skill-name        # kebab-case, matches folder name
description: >             # Decides when the AI loads this skill — getting this line right is critical
  Triggers when the user... Typical phrasings: "...". Not for: ...
---

# Skill Title

Body content...
Key Points for Writing description

description is the only gate for skill triggering; triggering accuracy almost entirely rides on it:

  • Explain both "what it does" and "when to use it" — neither can be missing
  • List typical phrasings, quoting what the user might actually say — the AI directly compares against these examples when deciding whether to trigger
  • Lean aggressive, err wide rather than narrow — a missed trigger hurts far more than an occasional extra trigger. Instead of "how to generate daily reports", write "triggers when the user mentions daily reports, weekly reports, work summaries, time logs, or wants to turn today's work into any form of report"
  • Use 'not for' to draw boundaries — avoid mis-triggering. Example: "Not for: Office documents (→ docx/xlsx/pptx-skill)"
  • Include synonyms and colloquial expressions — users don't always use standard terms; cover "gimme one", "whip up a", "cook up a" and similar casual phrasings
Key Points for the Body
  • Tell the AI why, don't pile up MUST/NEVER — use causal explanations instead of mandatory commands, so the model can reason about edge cases
  • Use decision trees instead of long prose — the ├─ Yes → ... format expresses branching logic clearly
  • Give concrete examples — JSON parameters, command invocations, conversation snippets are ten times more useful than abstract descriptions
  • Keep it lean — ideal length < 500 lines; split into scripts/ or use layered references when it grows too long
  • Use imperative voice — write "use Write to create the file" rather than "you should use Write"
markdown
# Skill Title

One paragraph overview of what this skill covers.

## Triggering Conditions
List which user phrasings / scenarios should trigger this skill.

## Workflow
Describe step by step what the AI should do. Use numbered steps + decision trees.

## Tool Usage
List the tools this skill depends on and the key usage points.

## Examples
1–2 end-to-end complete examples.

## Common Pitfalls
Easy mistakes and things to watch out for.

## Iron Rules
3–5 inviolable core rules.

openloaf.json provides UI display info and sits alongside SKILL.md:

json
{
  "name": "Display Name",
  "description": "One-line description",
  "icon": "🔧",
  "version": "0.1.0",
  "sourceLanguage": "zh-CN",
  "targetLanguage": "zh-CN",
  "colorIndex": 0
}

colorIndex palette: 0=cyan 1=purple 2=amber 3=sky 4=rose 5=emerald 6=indigo 7=lime

icon: Pick the emoji that best represents the skill's function.

Show full SKILL.md (449 more words)Show less

Step 4: Save to Disk

Use the Write tool to write the file. Paths strictly differ by scope:

ScopeWrite path
Global skill~/.openloaf/skills/<skill-name>/SKILL.md
Project skill{projectRoot}/.openloaf/skills/<skill-name>/SKILL.md

Check for name conflicts before creating to avoid accidental overwrites:

Glob: ~/.openloaf/skills/<skill-name>/SKILL.md               # Check global
Glob: {projectRoot}/.openloaf/skills/<skill-name>/SKILL.md   # Check project

On conflict, ask the user: overwrite / rename / cancel.

Always tell the user after creation: the skill list is loaded at conversation init, so the new skill is not visible in the current conversation — they need to open a new conversation for it to take effect.

Step 5: Verify and Iterate

Once the skill is created, suggest the user test it:

  1. Open a new conversation
  2. Use a triggering phrasing to get the AI to load the skill (watch for the skill-loaded notice)
  3. Check whether the AI follows the skill's instructions
  4. If something's off, come back and edit SKILL.md, then open a new conversation and retry
Common Troubleshooting
SymptomCauseFix
Skill doesn't triggerdescription too narrowAdd more typical phrasings, cover colloquial and synonym forms
Skill mis-triggersdescription too broadAdd "not for" qualifiers, draw boundaries with other skills
AI doesn't follow instructionsBody too long or too vagueShorten, add decision trees, add concrete examples
Tool calls error outTool usage not explainedAdd parameter examples and call ordering
Picked up by other projectsMistakenly placed in globalMove to project scope ({projectRoot}/.openloaf/skills/)

Improving an Existing Skill

When the user asks to improve an existing skill:

  1. Read the current SKILL.md to understand what's there
  2. Confirm the direction with the user (triggering accuracy / output quality / coverage)
  3. Only change the problem areas — don't rewrite the whole file — keep the parts the user has already validated stable
  4. After saving, have the user open a new conversation to verify

description optimization specialty: If the user reports "it didn't trigger when it should have", focus on refining the description:

  • Ask the user "what exactly did you say at the time?" and add that wording to the typical phrasings
  • Supplement synonyms, colloquial expressions, Chinese/English variants
  • Check whether the "not for" clause was written too aggressively and excluded legitimate cases

Iron Rules

  1. Ask first, act second — what to do / when to trigger / what to output / global or project: four questions answered before any file is written
  2. Don't pick the wrong scope — project-specific business knowledge doesn't go global; generic capabilities shouldn't be buried in a single project
  3. description errs wide, not narrow — a missed trigger hurts far more than an occasional extra trigger
  4. Body explains why, not piles up commands — causal explanation beats MUST/NEVER
  5. Glob for conflicts before creating, prompt the user to test in a new conversation after — the skill list is loaded at conversation init

© OpenLoaf, AGPL-3.0. 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 apps/server/src/ai/builtin-skills/skill-creator/en of OpenLoaf/OpenLoaf.

Open the folder on GitHubat commit f7eccf6

Compare with similar skills

Skill Creator Skill 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.

Skill Creator Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Creator Skill this skillOpenLoaf/OpenLoaf108—~2.7kAutomated safety check: PassAGPL-3.0
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 OpenLoaf/OpenLoaf

All 33 skills in this repo
  • Agent Orchestration Skill

    OpenLoaf/OpenLoaf

    Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Browser Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or…

    108 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed
  • Canvas Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.

    108 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Reads, edits, converts and reviews Word documents through three dedicated tools, covering tracked changes, comments, tables, images and format conversion.

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Email Operations

    OpenLoaf/OpenLoaf

    Handles a real email account through query and mutate tools: check the inbox, read, search, reply, forward, compose and organize, with sending always confirmed first.

    108 GitHub stars~1.8k tokensUpdated 4 mo ago
    Auto-check passed
  • macOS Desktop Control

    OpenLoaf/OpenLoaf

    Guides an agent to operate native macOS apps by surveying an app first, acting through intents, menus or keystrokes, and verifying each step, in OpenLoaf Desktop only.

    108 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Skill Creator Skill

What does Skill Creator Skill do?

Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill. Skill Creator Skill is an agent skill from OpenLoaf/OpenLoaf. Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill.

When should I use Skill Creator Skill?

Skill Creator Skill fits situations like: the user wants to create; debug an OpenLoaf custom Skill; wants to understand the skill format; troubleshoot triggering issues.

How do I install Skill Creator Skill in Claude Code?

Run `npx skills add OpenLoaf/OpenLoaf --skill skill-creator-skill -a claude-code`. Or copy the skill folder (apps/server/src/ai/builtin-skills/skill-creator/en in OpenLoaf/OpenLoaf) into .claude/skills/skill-creator-skill in your project. Claude Code loads it when a task matches its description.

How do I install Skill Creator Skill in Codex?

Run `npx skills add OpenLoaf/OpenLoaf --skill skill-creator-skill -a codex`. Or copy the skill folder (apps/server/src/ai/builtin-skills/skill-creator/en in OpenLoaf/OpenLoaf) into .agents/skills/skill-creator-skill in your project. Codex loads it when a task matches its description.

Can I use Skill Creator Skill 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 OpenLoaf/OpenLoaf --skill skill-creator-skill -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-skill, .gemini/skills/skill-creator-skill, .github/skills/skill-creator-skill and .opencode/skills/skill-creator-skill in your project.

What does Skill Creator Skill need to run?

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

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

Skill Creator Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Creator Skill use?

About 2.7k tokens (SKILL.md is roughly 11k 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 Skill Creator Skill?

Skills that share tags, products or a category with Skill Creator Skill: 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 Skill Creator Skill?

OpenLoaf (a GitHub organization) maintains it in OpenLoaf/OpenLoaf, which has 108 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on May 14, 2026.

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