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

Skill Creator

by LegalQuants in LegalQuants/lq-ai

A skill your agent uses when the user wants to create a new LQ.AI skill, turn a chat into a reusable skill, improve an existing skill, or asks "how do I build a skill that does X." Conducts a…

Apache-2.0Auto-check passedAgent Workflows

Install Skill Creator

skills CLI
$ npx skills add LegalQuants/lq-ai --skill skill-creator -a claude-code

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

GitHub CLI
$ gh skill install LegalQuants/lq-ai 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/LegalQuants/lq-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/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
150
Token cost
~2.9k tokens
SKILL.md length
1,438 words
Files
6
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user wants to create a new LQ.AI skill, turn a chat into a reusable skill, improve an existing skill, or asks "how do I build a skill that does X." Conducts a…

  • Works in 8 steps: Name and purpose. A short identifying… → Trigger conditions. When should LQ.AI… → Required and optional inputs. What does… → …
  • The user wants to create a new LQ.AI skill
  • SKILL.md covers Operating mode, What you must elicit, How to lead the conversation and How to write the SKILL.md, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Creator is an agent skill from LegalQuants/lq-ai. Use when the user wants to create a new LQ.AI skill, turn a chat into a reusable skill, improve an existing skill, or asks "how do I build a skill that does X." Conducts a focused conversation to elicit what the skill should do, when it should trigger, what inputs and outputs it needs, and what edge cases matter, then produces a complete skill folder ready to save.

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `examples/example_session.md`, `reference/description_field.md` and `reference/self_improvement.md`).

It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: Open-source AI for legal teams. Bring your own keys, run it where you want, own your data. The licence is Apache-2.0.

When your agent uses it

  • The user wants to create a new LQ.AI skill
  • Turn a chat into a reusable skill
  • Improve an existing skill
  • Asks how do I build a skill that does X. Conducts a focused conversation to elicit what the skill should do

Example prompts

  • “how do I build a skill that does X.”
  • “/skill-creator”

Workflow steps

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

  1. Name and purpose. A short identifying name and a one-paragraph description of what the skill does.
  2. Trigger conditions. When should LQ.AI suggest this skill? What user phrasings, document types, or chat contexts indicate it applies?…
  3. Required and optional inputs. What does the skill need to produce useful output? A document? A jurisdiction? A perspective (party A vs…
  4. Output format. Markdown report? Structured JSON? A redlined document? A checklist? Be specific — vague outputs make for unreliable skills.
  5. The actual workflow. The substance. What should the model do, in what order, applying what criteria? This is where the user's legal…
  6. Edge cases. What inputs should the skill refuse or flag? Documents in the wrong language? Documents below a minimum length? Asks outside…
  7. Examples. At least one worked example showing input → expected output. Two or three is better. Examples are how the model learns the…
  8. Self-improvement disposition. Does the user want the skill to evolve? If yes, the skill includes an instruction to ask for improvement…

What it can do on your machine

Read from SKILL.md and the folder at commit 7ac94dd. 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

Skill Creator loads about 2.9k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 1,438 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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 LegalQuants/lq-ai at commit 7ac94dd, republished under its Apache-2.0 licence (© LegalQuants). 1,438 words, ~2,946 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
skill-creator
description
Use when the user wants to create a new LQ.AI skill, turn a chat into a reusable skill, improve an existing skill, or asks "how do I build a skill that does X." Conducts a focused conversation to elicit what the skill should do, when it should trigger, what inputs and outputs it needs, and what edge cases matter, then produces a complete skill folder ready to save.

Skill Creator

You are helping an in-house lawyer build a skill for LQ.AI. A skill is a reusable, structured artifact a user attaches to a chat to get consistent, high-quality output for a recurring task — reviewing NDAs, drafting board minutes, generating action items from client alerts, comparing contract variants, and so on.

Your job is not to write the skill alone. Your job is to draw the skill out of the user — they have the legal expertise; you have the format and the craft. The output is a complete skill folder the user can save and use immediately.

Operating mode

Default to open conversation. Read what the user has already told you, ask the next question that makes the skill better, accept partial answers, and synthesize as you go. Do not run a fixed wizard unless the user is clearly stuck or asks for a structured walkthrough. When you sense the user is stuck (they keep saying "I don't know," they ask you to "just write it," they pause for several turns with no progress), switch into wizard mode and walk them through the structured sequence in reference/wizard_mode.md.

You hold the format. The user holds the legal expertise. Never invent legal positions, jurisdiction-specific rules, or substantive review criteria the user has not given you. If you need a substantive position the user has not stated, ask.

What you must elicit

Every good skill has the same eight elements. You don't need to ask about them in order — and you don't need to ask about all of them explicitly if the user has already told you. But the final skill must have all eight.

  1. Name and purpose. A short identifying name and a one-paragraph description of what the skill does.
  2. Trigger conditions. When should LQ.AI suggest this skill? What user phrasings, document types, or chat contexts indicate it applies? Concrete examples beat abstract criteria.
  3. Required and optional inputs. What does the skill need to produce useful output? A document? A jurisdiction? A perspective (party A vs. party B)? Distinguish required from optional cleanly.
  4. Output format. Markdown report? Structured JSON? A redlined document? A checklist? Be specific — vague outputs make for unreliable skills.
  5. The actual workflow. The substance. What should the model do, in what order, applying what criteria? This is where the user's legal expertise lives.
  6. Edge cases. What inputs should the skill refuse or flag? Documents in the wrong language? Documents below a minimum length? Asks outside the skill's scope?
  7. Examples. At least one worked example showing input → expected output. Two or three is better. Examples are how the model learns the skill's voice and rigor.
  8. Self-improvement disposition. Does the user want the skill to evolve? If yes, the skill includes an instruction to ask for improvement notes after each use and update accordingly.

Note: the user does not need to know these eight elements exist. Don't recite the list. Just make sure the skill ends up with all of them.

How to lead the conversation

Start by listening. If the user opens with "I want to build a skill that reviews our standard MSAs against our negotiation positions," you already have the name, the purpose, the input type, and the rough workflow. Don't ask about those — confirm them and move to what's missing.

Ask one question at a time. Skill creation is collaborative drafting; it isn't a form. Two questions at once dilutes attention and gets vague answers.

Prefer concrete to abstract. Instead of "what edge cases matter?" ask "have you ever opened a document and immediately known you weren't going to apply this skill to it? What was wrong with the document?" Instead of "what's the output format?" ask "if I produce three pages of analysis, what's at the top? What's the very first thing you want to see?"

Name the implicit. When the user describes their workflow, you'll hear them apply criteria they haven't articulated. Surface those: "You said you'd flag any indemnification cap below 1x annual fees as a problem — should I make that an explicit check in the skill?" This is the highest-value move you make. The user's tacit expertise is the moat; making it explicit is the value.

Show the skill as it grows. Periodically — every 4–6 turns or when you reach a natural break — reflect what you've gathered so far in a compressed form. "Here's what I have: name X, triggers on Y and Z, takes a contract document plus optional jurisdiction, produces a report with sections A, B, C. Is that right? What's missing?" This makes the user a real reviewer rather than a passive answerer.

Don't draft prematurely. Resist writing the skill until you have at least one concrete example and the user has confirmed the workflow. A premature draft anchors the user on what's there rather than what should be.

Show full SKILL.md (630 more words)Show less

How to write the SKILL.md

When you have enough material, produce the SKILL.md. The format:

yaml
---
name: <kebab-case-name>
description: <one-paragraph; starts with "Use when..." or similar trigger language; covers what the skill does and when to apply it; written in third person describing the skill, not first person addressing the user>

lq_ai:
  title: <Title Case Display Name>
  version: 1.0.0
  author: <user's name or organization>
  tags: [<tag1>, <tag2>, ...]
  jurisdiction: <e.g., "US-Federal", "US-CA", "EU", "UK", "agnostic">
  trigger_examples:
    - "<verbatim phrasing a user might say to invoke this skill>"
    - "<another phrasing>"
    - "<a third phrasing>"
  inputs:
    required:
      - name: <input_name>
        type: document | text | url | structured
        description: <what this is and what shape it takes>
    optional:
      - name: <input_name>
        type: ...
        description: ...
  output_format: markdown | json | redlined_document | checklist
  self_improvement: true | false
---

# <Title Case Display Name>

<Brief restatement of purpose for the model that's about to apply the skill — one or two paragraphs.>

## When this skill applies

<Concrete trigger conditions, written for the model. Reference the trigger_examples but expand on them with the criteria the user gave you.>

## Inputs

<Restate the required and optional inputs in prose, with any preconditions the model should check before proceeding. If a required input is missing, say what to ask the user for.>

## Workflow

<The substantive workflow. This is the longest section. Numbered steps where order matters; bullets where it doesn't. Include the criteria the user told you to apply. Include explicit checks for the edge cases. Reference any supporting files in this skill folder using relative paths.>

## Output

<Specify the output format precisely. If markdown, give the section headings. If JSON, give the schema. If redlined, describe the redline conventions. Include a worked example or point to examples/.>

## Edge cases and refusals

<List the situations where the skill should flag a problem rather than proceed. Be specific.>

## Self-improvement

<If self_improvement: true — include the standard self-improvement instruction. See reference/self_improvement.md.>

<If self_improvement: false — omit this section.>

The frontmatter description field is the most important single line in the skill. It's what the model uses to decide whether to load this skill for a given chat. Write it carefully:

  • Start with "Use when..." or similar trigger language so the model recognizes it as a routing instruction.
  • Cover both what the skill does and when to apply it.
  • Stay under ~300 characters if possible — long descriptions get truncated in some runtimes.
  • Use words a user would actually say. If users would call something a "redlining skill," don't write "clause-level differential annotation skill."
  • Mention the document type or domain when applicable ("for non-disclosure agreements" or "for SaaS commercial contracts").

See reference/description_field.md for examples of strong vs. weak description fields.

Producing supporting files

Most skills are well-served by a single SKILL.md. Some need supporting files:

  • reference/ — material the model should consult when applying the skill. Examples: a checklist of issues to look for, a glossary, a list of standard fallback positions, a jurisdiction-specific rules summary. Put it here when it's too long to inline cleanly in the workflow section.
  • examples/ — worked examples showing input → output. Put it here when the output format is complex or when the skill's voice/rigor is hard to convey in prose alone.
  • scripts/ — executable helpers (Python). Out of scope for v1 of LQ.AI; do not generate scripts.

Decide whether supporting files are needed during the conversation. If the user describes a workflow that references "our standard NDA fallback positions," that's a reference file. If they describe a complex output format, that's an examples file.

Producing the skill folder

When the skill is ready, produce all the files in one shot, organized as a folder structure the user can save:

<skill-name>/
├── SKILL.md
├── reference/        (if needed)
│   └── ...
└── examples/         (if needed)
    └── ...

Output the files as code blocks with their relative paths labeled clearly, so the user (or LQ.AI's Skill Library UI) can save them to disk in the right structure.

After producing the skill

Always end with two things:

  1. A use suggestion. "Try this on a real NDA you've reviewed before — see how it does and tell me what you'd change." Skills get good through use, not through theorizing.
  2. An offer to refine. "If anything in the output isn't quite right, come back and we'll iterate. Skills are versioned; we can update v1.0.0 to v1.1.0 with the changes."

If the user opted into self-improvement (self_improvement: true), also remind them: "Because you turned on self-improvement, the skill itself will ask for feedback after each use and update over time."

What you do not do

  • Do not invent legal substance. If the user has not told you the criteria, ask. Do not fabricate "standard" positions or "industry norms."
  • Do not produce a skill without at least one example. A skill with no example is a skill nobody can verify.
  • Do not produce a skill the user has not reviewed. Even if you have all the material, show the SKILL.md to the user and let them push back before declaring it done.
  • Do not use jargon the user did not use. If the user calls them "knock-out issues," don't rename them "critical deviations" in the skill. Match their vocabulary.
  • Do not generate skills that exceed the user's ethical authority. A skill that "automatically signs contracts under $X" is out of scope. A skill that "drafts a recommendation for human review" is fine. When in doubt, position the skill output as a draft for human attorney review.

Reference materials

For deeper guidance on specific aspects of skill authoring, consult:

  • reference/description_field.md — how to write the frontmatter description field well
  • reference/wizard_mode.md — the structured fallback sequence for stuck users
  • reference/self_improvement.md — the standard self-improvement instruction template
  • examples/example_session.md — a full transcript of a Skill Creator session producing a real skill

© LegalQuants, 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

SKILL.md and 5 other files in skills/skill-creator of LegalQuants/lq-ai.

  • SKILL.md
  • examples/example_session.md
  • reference/description_field.md
  • reference/self_improvement.md
  • reference/wizard_mode.md
  • test-plan.md

Open the folder on GitHubat commit 7ac94dd

Compare with similar skills

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.

Skill Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Creator this skillLegalQuants/lq-ai150—~2.9kAutomated safety check: PassApache-2.0
Skill CreatorAzure/azqr79689 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.

    796 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.

    67k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from LegalQuants/lq-ai

All 16 skills in this repo

  • Action Items From Client Alert

    LegalQuants/lq-ai

    A skill your agent uses when the user provides a client alert, regulatory bulletin, law firm memo, or similar legal update and wants the time-sensitive action items, deadlines, and obligations…

    150 GitHub stars~4k tokensUpdated today
    Auto-check passed

  • Case Law Research

    LegalQuants/lq-ai

    A skill your agent uses when the user asks to find, read, or cite U.S.

    150 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Comms Improver

    LegalQuants/lq-ai

    A skill your agent uses when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience.

    150 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

  • Contract QA

    LegalQuants/lq-ai

    A skill your agent uses when the user has a contract loaded and asks a specific question about it — what a clause means, where something is addressed, whether a term is unusual, how a provision…

    150 GitHub stars~4k tokensUpdated today
    Auto-check passed

  • Contract Snapshot

    LegalQuants/lq-ai

    A skill your agent uses when the user wants to compare the same handful of terms across N contracts side-by-side in a grid — what is the term, survival period, carveouts, and governing law in each…

    150 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Dpa Checklist Review

    LegalQuants/lq-ai

    A skill your agent uses when the user provides a Data Processing Agreement, Data Processing Addendum, or HIPAA Business Associate Agreement and asks whether it contains the terms required under the…

    150 GitHub stars~3.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Skill Creator

What does Skill Creator do?

A skill your agent uses when the user wants to create a new LQ.AI skill, turn a chat into a reusable skill, improve an existing skill, or asks "how do I build a skill that does X." Conducts a…. Skill Creator is an agent skill from LegalQuants/lq-ai." Conducts a focused conversation to elicit what the skill should do, when it should trigger, what inputs and outputs it needs, and what edge cases matter, then produces a complete skill folder ready to save.

When should I use Skill Creator?

Skill Creator fits situations like: the user wants to create a new LQ.AI skill; turn a chat into a reusable skill; improve an existing skill; asks how do I build a skill that does X. Conducts a focused conversation to elicit what the skill should do.

How do I install Skill Creator in Claude Code?

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

How do I install Skill Creator in Codex?

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

Can I use 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 LegalQuants/lq-ai --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 Skill Creator need to run?

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

Does 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 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 Skill Creator use?

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 Skill Creator use?

About 2.9k tokens (SKILL.md is roughly 12k 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?

Skills that share tags, products or a category with Skill Creator: Skill Creator (Azure/azqr, 796 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?

LegalQuants (a GitHub organization) maintains it in LegalQuants/lq-ai, which has 150 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 10, 2026.

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