agentleFS
mementomori-comementomori-co/maker-mastery/.claude/skills/ip-check/SKILL.md

ip-check

Skill2 starsChanged 25 days agoMITView on GitHub

Use when a design, name, logo, derivative or licence question must be checked against primary IP sources before anything is sold, published or named. Runs the ip-researcher in a fresh context and writes a facts-only table (statute, agency, licence text, platform term) to research\ip\; never legal advice.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before /unit-cost finalises a price, before /makerworld-publish, before a brand name or logo is adopted, before any fan-art or AI-generated …

    line 14
  2. Very specific:

    Write the file; return its path and counts (rows by kind, needs-an-attorney items, not found).

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Overview

IP question: $ARGUMENTS, three fields separated by |: topic slug, question slug, the question.

Output on disk: research\ip\<topic-slug>\<question-slug>.md in the ip-researcher's table format, with a ## Needs an attorney section. The lead then runs /verify on that path.

When to use

Before /unit-cost finalises a price, before /makerworld-publish, before a brand name or logo is adopted, before any fan-art or AI-generated asset is sold. Not for safety or product-compliance rules (business-strategist), not for what a client's own contract says (the maker's attorney).

Steps

  1. Parse the three fields. Check knowledge\ and research\verified\ip\ first; link existing facts by path rather than re-fetching them.
  2. Fetch the primary pages for the question with WebFetch this run. Start from the source list in the ip-researcher agent, for example (US sources; use your own jurisdiction's equivalents): https://www.uspto.gov/learning-and-resources/fees-and-payment/uspto-fee-schedule, https://www.uspto.gov/trademarks/basics/strong-trademarks, https://www.copyright.gov/about/fees.html, https://www.copyright.gov/circs/circ33.pdf, https://www.law.cornell.edu/uscode/text/17/101, https://creativecommons.org/licenses/, and the platform's own terms page (for MakerWorld: https://makerworld.com/en/user-agreement and https://makerworld.com/en/exclusive-model-policy).
  3. One row per fact: short quote (about 15 words at most), URL, kind (statute / agency / licence / platform / community), effective or page date. A fee or class without its date is incomplete. A page that returns HTTP 402/403 is written as fetch blocked (HTTP nnn) for the lead to re-fetch with /research-one.
  4. For a trademark question, run the knockout search in the official trademark search system and record the system URL, query string, date and verbatim hit list; do not conclude "clear".
  5. ## Needs an attorney: every judgment the sources leave open (likelihood of confusion, fair use, separability, registrability), with the factors the source names.
  6. Write the file; return its path and counts (rows by kind, needs-an-attorney items, not found). Name /verify <path> as the next step.

Common rationalizations

RationalizationReality
"This is obviously fair use."Fair use is a judgment. Quote the four factors from the statute and stop.
"The fee has not changed."Fee schedules carry effective dates. Fetch and quote the row.
"A single trademark search with no hits means clear."Record the search; a knockout search is a fact about a query, not a clearance opinion.
"I'll skip the attorney section, there is nothing to add."Every IP question has at least one judgment call. Name it.

Red flags (stop and fix)

  • Advice phrasing ("you can", "safe to", "allowed to") anywhere in the file.
  • A URL not fetched this run; a search snippet used as a page.
  • A row of kind community with no primary row beside it.
  • A write outside research\ip\.

Verification

  • File exists at research\ip\<topic-slug>\<question-slug>.md.
  • Every row has quote, fetched URL, kind, date.
  • ## Needs an attorney is non-empty.
  • Knockout search (if a name or logo) recorded with system URL, query, date, hit list.
  • Path and counts returned; /verify named as next step.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.