Skills, in plain language.

Think of a skill as a recipe for an LLM. You write down instructions once — what to do, what format the answer should take, when to escalate to a human — and the LLM follows the recipe every time the skill is active.

If you've ever copy-pasted the same long prompt into Claude or ChatGPT a hundred times, a skill is the cleaner version of that habit: write it once, share it, sell it.

A skill bundle has three pieces (the second two are optional):

• SKILL.md — YAML frontmatter (name, version, models, jurisdiction, etc.) plus a Markdown body with the actual instructions. This is the system prompt the LLM follows when the skill is active.
• examples/ — sanitized example input and output files so buyers can preview before purchase.
• assets/ — reference templates, checklists, or other files the skill body references.

The whole thing is zipped as a .skill (or plain .zip) bundle and uploaded to Counsel Commons™.

1. Author writes & tests.The author drafts the SKILL.md, runs it on at least one of Claude / GPT / Gemini, and confirms it produces useful output for the workflow they're automating.
2. Upload & affirm. The author uploads the bundle and signs the required acknowledgments — drafting aid not professional advice, no real client/firm-confidential data in examples, IP rights to license, etc.
3. Counsel Commons™ checks the submission. Each submission passes through automated structural checks and a human moderator's read. Review typically completes within 1–2 business days, occasionally longer. The platform does not warrant accuracy, quality, or fitness for any particular use — the author is ultimately responsible for the content, accuracy, effectiveness, and security of their skills, and buyers should read each skill's files before running it.
4. Listed in the catalog. The skill goes live. Buyers can find it through search or filter.
5. Buyer purchases. Stripe Checkout for paid skills; one-click claim for free samples (each buyer can install up to 2 free skills total - these are limited to skills authors may offer for free). License is one-time, lifetime access.
6. Buyer installs & runs. Library shows the install instructions tailored to the AI tool the buyer chooses (Claude Code, ChatGPT, Cursor, etc.).

Every SKILL.md starts with a YAML block. This is the metadata Counsel Commons™ reads to classify, route, and disclose the skill — and what the user's runtime reads to decide whether to activate it.

---
name: your-skill-slug
version: 1.0.0
description: One sentence describing what this skill does and when to activate it.
roles: [legal-ops, strategy]             # any of: legal-ops, it, marketing, people-and-culture, strategy, pricing-and-profitability, client-success, executive-assistant, knowledge-management, other
models: [claude-opus-4.6, gpt-5]
category: firm-operations-business       # currently the only top-level category
jurisdiction: US                         # or "Jurisdiction-neutral"
data_handling: claude
requires_professional_review: true
---

# Skill Name

## When to use
Be specific about which user intents and inputs activate this skill.

## Process
Step-by-step what the LLM should do.

## Output
The format and structure the LLM should produce.

## Disclaimer
Outputs require professional review and are not legal, financial, or HR advice.

The phrase “Outputs require professional review” must appear in the long description on the upload form — that's a moderation rule per spec §12.

When a buyer downloads a skill from their library, Counsel Commons asks which AI tool they'll use it with and tailors the install instructions to that tool. The bundle stays the same; only the install path differs.

• Claude Code — drop the SKILL.md folder into ~/.claude/skills/{slug}/.
• Claude.com chat— paste the SKILL.md body into a Project's custom instructions.
• ChatGPT Custom GPT— paste the SKILL.md body as the GPT's system prompt.
• Gemini Gem— paste the SKILL.md body as the Gem's instructions.
• Cursor / Windsurf / Ollama / LM Studio — if available, format of skill file may differ from Anthropic's open source standard format that is portable across some of the other frontier models.

Authors may push new versions over time — bug fixes, jurisdictional updates, expanded coverage. Existing buyers receive every future version at no additional cost.

• Auto-update by default. Your library always shows the latest approved version of each purchased skill.
• Pin for stability. If you depend on exact output behavior for a production workflow, you can pin to a specific version. Pinned buyers get a notification when a new version ships but stay on their pinned version unless they unpin. (UI for pinning ships in v1.5.)
• Authors can change price between versions. Existing buyers are not retroactively re-charged or credited, but they will automatically have access to new versions (unless they were disatisfied with the version they purchased and requested and received a refund).

Skills are productivity aids — drafting starting points, structured analyses, initial passes at checklist generation. They are not intended to provide personalized legal, financial, HR, or other professional advice and do not create a professional-client relationship between the author and any buyer or any buyer's firm.

Outputs vary run-to-run. Generative AI is non-deterministic — the same skill on the same input can produce different outputs across runs, and outputs can vary across sessions, model versions, and provider load conditions. Variance is a normal property of AI tools, not a defect of any specific skill or author.

Every output requires review by the relevant professional (CFO, COO, legal-ops lead, managing partner, HR director, depending on the skill) before it's used to make a firm-affecting decision. The author affirmed that at upload; the moderation rubric enforces it; and the disclaimers on every skill page restate it. If an output ever feels like it's overstepping into definitive advice, that's a quality issue and the buyer-feedback channel is where to raise it.