Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add LegalQuants/lq-skills --skill skill-creatorgit clone --depth 1 https://github.com/LegalQuants/lq-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/legalquants/lq-skills/skill-creator)<a href="https://agentmods.dev/skills/legalquants/lq-skills/skill-creator"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/skill-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/legalquants/lq-skills/skill-creator"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.03349 |
| Opus 5 | $0.00044 | $0.01674 |
| Sonnet 5 | $0.00017 | $0.00670 |
| Haiku 4.5 | $0.00009 | $0.00335 |
Grade A, and why
skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
92% identical to skill-creator — 27 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
- Name and purpose. A short identifying name and a one-paragraph description of what the skill does.
- 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.
- 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.
- Output format. Markdown report? Structured JSON? A redlined document? A checklist? Be specific — vague outputs make for unreliable skills.
- 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.
- 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?
- 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.
- 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.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 197 lines · 87 tokens per session scan A 54e691bbfb37
skill-creator is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 3,349 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to skill-creator, differing in 27 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…