$ loading_
Draft a DMCA takedown notice, triage one you received, or draft a §512(g) counter-notice. Use when asserting copyright through a §512(c)(3) takedown with the fair-use and perjury gates, when an incoming takedown needs triage into comply / counter / engage / ignore options, or when drafting a §512(g)(3) counter-notice with the consent-to-federal-jurisdiction gate.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "takedown" skill from askskill: 1. Download https://raw.githubusercontent.com/anthropics/claude-for-legal/main/ip-legal/skills/takedown/SKILL.md 2. Save it as ~/.claude/skills/takedown/SKILL.md 3. Reload skills and tell me it's ready
Three modes. Pick one:
/ip-legal:takedown --send — draft a §512(c)(3) takedown notice. Fair-use gate (Lenz) + loud perjury / §512(f) gate before delivery./ip-legal:takedown --respond — triage a takedown someone sent you. Options: comply / counter / engage / ignore./ip-legal:takedown --counter — draft a §512(g)(3) counter-notice. Loud gate for the federal-jurisdiction admission and the perjury statement.Read the practice profile. Load ~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md. If it contains [PLACEHOLDER] markers or does not exist, stop and say: "This plugin needs setup before it can give you useful output. Run /ip-legal:cold-start-interview — the takedown skill depends on your approval matrix and practice profile."
Check matter workspaces. Per ## Matter workspaces: if Enabled is ✗, skip. If enabled and there is no active matter, ask: "Which matter is this for? Run /ip-legal:matter-workspace switch <slug> or say practice-level."
Dispatch on $ARGUMENTS:
--send → run send mode (below). Walk identify-the-work, identify-the-infringing-material, fair-use gate (Lenz), good-faith belief, accuracy/authority, draft the §512(c)(3) notice, run the loud gate, write output.--respond → run respond mode (below). Read the incoming notice, assess (license, fair use, defects, host §512(g) compliance, sender credibility), present the four options, recommend, write the triage memo.--counter → run counter mode (below). Confirm the predicate (taken down in response to a §512 notice, good-faith belief of mistake/misidentification, ready for federal-jurisdiction admission, attorney in the loop), draft the §512(g)(3) counter-notice, run the loud gate, write output.Respect the gates. In --send and --counter, the loud gate runs before any final output is written. The fair-use gate in --send is separate and runs earlier; "debatable" or "likely" fair use stops the draft and routes to attorney review.
Jurisdiction note. DMCA §512 is US federal law. If the service provider, content, or infringer sits outside US jurisdiction, flag before drafting — you may need an EU DSA notice, UK OSA notice, or local-regime instrument instead of (or in addition to) a DMCA notice.
Hand off where appropriate. --respond with a counter-notice recommendation chains into /ip-legal:takedown --counter — but only after the triage memo has been reviewed and the decision to counter has been made deliberately.
/ip-legal:takedown --send
/ip-legal:takedown --respond ~/Downloads/youtube-takedown-notice.pdf
/ip-legal:takedown --counter
/ip-legal:takedown
The DMCA §512 notice-and-takedown system is fast, cheap, and consequential in equal measure. A takedown is a sworn statement under penalty of perjury that gets content pulled with no judicial review. A counter-notice is another sworn statement that consents to federal jurisdiction and puts the content back. Both decisions can become litigation. This skill handles all three moves with the guardrails each warrants.
Three modes:
--send — draft a §512(c)(3) takedown notice…
Ask questions against an open investigation log — what witnesses said, where accounts conflict, what gaps exist, what the strongest evidence is on each issue. Use when the attorney needs to query the investigation record without re-reading every entry.
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer, distributor, authorized representative, product manufacturer) and risk tier (prohibited, high-risk, limited, minimal, GPAI, GPAI+systemic). Role and tier are assessed per system, not per company. Use when the user says "ai inventory", "add an ai system", "what systems do we have", "classify this ai system", "eu ai act register", or "ai system registry".
Draft a firm AI usage policy from published model policies, adapted to your practice profile — a research-and-synthesis tool whose output is a draft for attorney review and adoption, not a finished policy. Use when user says "draft an AI policy", "we need an AI policy", "build an AI usage policy", "our firm needs a GenAI policy", or similar requests to generate a first-cut internal AI policy.
Review vendor AI terms — agreement, addendum, or ToS AI provisions — against your governance positions; flag training-on-data, liability, model changes, and AI policy consistency. Use when user says "review this AI agreement", "check OpenAI terms", "what did we agree to with [vendor]", "vendor sent an AI addendum", "is this AI contract okay", or attaches vendor AI terms.
Route a contract issue to the right approver per the escalation matrix in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, and draft the ask. Use when the user says "who needs to approve this", "escalate this", "does this need GC sign-off", "route this for approval", or when another skill finds an issue that exceeds the reviewer's authority.
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent counsel review. This skill never concludes a product is clear to launch.