Litigation Deadline Calendar
lawve-ai/awesome-legal-skills
Calendar litigation and arbitration deadlines from a scheduling order.
Draft a cease-and-desist letter (send mode) or triage one you received (receive mode).
$ npx skills add anthropics/claude-for-legal --skill cease-desist -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install anthropics/claude-for-legal cease-desist --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ip-legal/skills/cease-desist .claude/skills/cease-desist && rm -rf skills-srcUse ~/.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/
Install the "cease-desist" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills/cease-desist into .claude/skills/cease-desist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cease-desist", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills/cease-desistType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add anthropics/claude-for-legal --skill cease-desist -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install anthropics/claude-for-legal cease-desist --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .agents/skills && cp -r skills-src/ip-legal/skills/cease-desist .agents/skills/cease-desist && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cease-desist" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills/cease-desist into .agents/skills/cease-desist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cease-desist", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add anthropics/claude-for-legal --skill cease-desist -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install anthropics/claude-for-legal cease-desist --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/ip-legal/skills/cease-desist .cursor/skills/cease-desist && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cease-desist" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills/cease-desist into .cursor/skills/cease-desist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cease-desist", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/anthropics/claude-for-legal.git --path ip-legal/skills/cease-desist--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add anthropics/claude-for-legal --skill cease-desist -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install anthropics/claude-for-legal cease-desist --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/ip-legal/skills/cease-desist .gemini/skills/cease-desist && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cease-desist" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills/cease-desist into .gemini/skills/cease-desist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cease-desist", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install anthropics/claude-for-legal cease-desistInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add anthropics/claude-for-legal --skill cease-desist -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .github/skills && cp -r skills-src/ip-legal/skills/cease-desist .github/skills/cease-desist && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cease-desist" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills/cease-desist into .github/skills/cease-desist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cease-desist", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add anthropics/claude-for-legal --skill cease-desist -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install anthropics/claude-for-legal cease-desist --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/ip-legal/skills/cease-desist .opencode/skills/cease-desist && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cease-desist" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills/cease-desist into .opencode/skills/cease-desist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cease-desist", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cease-desistDraft a cease-and-desist letter (send mode) or triage one you received (receive mode).
Cease Desist is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Use when asserting your rights against an infringer with a demand letter calibrated to your enforcement posture, or when an incoming C&D needs triage into a structured options memo with a recommendation.
Its SKILL.md is about 9.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Legal & Compliance, covering Dispute resolution. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cease Desist loads about 9.3k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 4,180 words of instructions outside code blocks.
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.
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.
The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 4,180 words, ~9,314 tokens.
.claude/skills/cease-desist/SKILL.md (or your agent's skills folder).Two modes. Pick one:
/ip-legal:cease-desist --send — draft a cease-and-desist letter calibrated to your enforcement posture. Loud gate runs before delivery./ip-legal:cease-desist --receive — triage a C&D someone sent you. Produces an options memo with a recommendation.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 C&D skill depends on your enforcement posture, approval matrix, and practice-area mix, none of which are configured yet."
Check matter workspaces. Per ## Matter workspaces: if Enabled is ✗, skip — skills use practice-level context. 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 is present: run send mode (below). Walk through identify-the-right, identify-the-conduct, identify-the-relationship, identify-the-demand, calibrate-to-posture, draft, and the pre-delivery gate.--receive is present: run receive mode (below). Ask for the incoming letter (path or pasted text), then assess, identify exposure, present options, and write the triage memo.Respect the gate. In send mode, the loud gate runs before any final draft is written to disk. Do not skip it.
Respect the approval matrix. Pull the approver for the C&D row from ## Enforcement posture → Approval matrix. Pull automatic escalations. Surface both in the gate; do not smother them.
Hand off where appropriate. In receive mode, if the recommendation is to respond firmly, offer to chain into /ip-legal:cease-desist --send pre-populated with the response context. If the recommendation is to pre-empt with a DJ action or TTAB cancellation, escalate to outside counsel per the practice profile's IP litigation row — do not draft.
/ip-legal:cease-desist --send
/ip-legal:cease-desist --receive ~/Downloads/incoming-cd-acme.pdf
/ip-legal:cease-desistRegistered in: footprint. If the conduct or counterparty is somewhere else, flag before drafting.[CITE:___] is unverified until a citator run. Source attribution tags stay on the draft.A cease-and-desist letter asserts a legal right and demands that someone stop doing something. It is one of the most consequential letters an IP practice sends or receives. Sending one is a first step toward litigation — recipients can file a declaratory judgment action in a forum of their choosing, and overbroad or bad-faith assertions can be used against the sender. Receiving one starts a clock and forces a decision. This skill handles both sides with the guardrails the decision deserves.
Two modes:
--send — you are asserting. Draft a C&D calibrated to the posture, gate before delivery.--receive — you are defending. Triage the incoming letter, produce an options memo, route to matter creation if warranted.If the user does not pass a flag, ask once: "Are we sending a cease-and-desist (you're asserting) or triaging one we received (you're defending)?"
External deliverable (send mode): the drafted C&D is sent to counterparty. Do NOT include the
PRIVILEGED & CONFIDENTIAL — ATTORNEY WORK PRODUCTheader on the outgoing letter. Internal drafts, pre-send briefs, and triage memos keep the header per plugin config## Outputs.
Trademark rights are territorial — a US registration does not travel. Copyright is Berne-multilateral but enforcement is jurisdiction-specific, and statutory remedies (including US §504 statutory damages) turn on local law. This skill assumes the jurisdiction declared in the matter or the practice profile's Registered in: footprint. If the infringing conduct, counterparty, or forum is somewhere else, flag it — the draft may not apply as written.
~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md → ## Enforcement posture (posture, C&D triggers, soft-letter criteria, approval matrix, automatic escalations), ## IP practice profile (practice area mix, registered jurisdictions, outside counsel roster), ## Outputs (work-product header, role), ## Who's using this (role — lawyer vs. non-lawyer)## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗ (the default for in-house users), skip matter machinery — skills use practice-level context. 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." Load the active matter's matter.md for matter-specific overrides (e.g., posture override, approver override). Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/ip-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.Ask, in one batch:
Which IP right are we asserting?
- Trademark — is it registered? Where (USPTO, EUIPO, UKIPO, national)? Reg number and class(es)? Or common-law-only (first-use date, geographic scope)?
- Copyright — is it registered? Title, registration number, date? Or unregistered (note: US suits require registration for filed claims; statutory damages and fees require pre-infringement registration)?
- Both — identify each.
Record each right. Registered rights get cited by number. Common-law rights get the first-use evidence paragraph. Unregistered copyrights get a flag: "We may not be able to file suit on an unregistered US copyright without registering first — [SME VERIFY] before the letter threatens litigation."
Describe the infringing conduct in specifics, not adjectives:
- Who is doing it — entity name, individual, platform handle?
- What — the accused mark, the accused copy, the accused product? Attach or describe samples.
- Where — website URL, marketplace listing, physical retail, social media?
- Since when — date first observed, date of the earliest use you can document?
- Evidence — screenshots, receipts, watch-service hit, customer confusion reports?
Facts go in specific. "You sold product X on [URL] bearing the mark [Y] on [date]" beats "You have been infringing our rights." Adjectives tell on a thin record.
What's the relationship between us and the recipient?
- Competitor (direct or adjacent) — standard posture applies
- Reseller / channel partner — tone adjusts; consider the soft-letter path
- Former licensee / ex-employee / former partner — contract provisions likely apply; cite them
- Stranger / random infringer — standard
- Current customer / partner — automatic escalation per practice profile; flag before drafting
This changes tone, approver, and whether to draft at all without escalation.
What does the client actually want?
- Stop — cease the infringing use
- Account — report sales, profits, volumes (for damages baseline)
- Destroy — destroy or recall infringing inventory
- Damages — monetary settlement
- Transfer / assign — transfer the domain, hand over the account, assign the accused mark or copyright
- Public correction — takedown of offending content, public statement
- Confirm in writing — compliance undertaking by a date
Pick the actual remedies. The demand must be proportionate to the harm — an overbroad demand is evidence of bad faith if the matter is ever litigated.
Channel-takedown parallel path (marketplace infringement). If the accused conduct is on a marketplace (Amazon, Etsy, eBay, Alibaba, TikTok Shop, AliExpress, Walmart Marketplace, Shopify-hosted storefronts), flag the platform's brand-protection / IP-infringement reporting path as a faster, cheaper parallel track that does not require a C&D or litigation:
A marketplace takedown often resolves in days; a C&D gives the infringer time to sell through inventory while negotiating. The two paths are not mutually exclusive — recommend filing both when the conduct is marketplace-based, with the C&D covering off-platform conduct (DTC site, wholesale, social, physical retail) that the platform report cannot reach. Note in the pre-send brief whether the parallel-path has been filed, is queued, or is declined (and why).
Read ## Enforcement posture → Default posture: and apply:
Also read When we send a C&D, When we send a soft letter first, and When we just file. If the facts suggest this should be a soft letter or a direct filing per the practice profile, flag it before drafting: "Per your enforcement posture, this pattern matches [soft letter / filing]. Do you still want a C&D, or would you prefer [alternative]?"
Matter-level overrides in matter.md beat the practice default.
Before drafting, run counterparty diligence and present the results to the user. This is not conditional on "if the counterparty looks big." Every C&D assertion carries DJ / fee-shifting / bad-faith exposure calibrated to who the recipient is. The skill does not draft a C&D until the user has seen the diligence and confirmed they still want to pick this fight.
Collect and present — in one block, for user sign-off — the following:
d/b/a aliases. USPTO / EUIPO ownership records; state Secretary of State business search; public company filings if any. Flag [SME VERIFY] if the source is unconfirmed.Present this as a short memo in-chat BEFORE the draft:
## Counterparty diligence — [Entity Name]
- **Entity:** [name, state of formation, parent if any]
- **Size:** [headcount band, revenue band, funding stage] — [source, `[SME VERIFY]` where applicable]
- **IP portfolio:** [registered marks / patents / copyrights in adjacent classes — or "none found"]
- **Litigation history:** [prior IP cases as plaintiff or defendant — or "none found in quick pass"]
- **Counsel:** [known outside IP counsel — or "none identified"]
- **DJ-plaintiff risk:** [high / medium / low — reasoning]
- **Relationship risk:** [any customer / investor / partner / acquirer overlap — or "none identified"]
**Automatic escalations this triggers** (per practice profile `## Enforcement posture` → Automatic escalations):
- [list each trigger that this diligence surfaces]
**Confirm before I draft:**
- Do you want to proceed with a C&D against this counterparty, given the diligence above?
- Any of the automatic escalations applicable? If yes, the approver named in the profile signs off before drafting, not after.Do not proceed to Step 6 (Draft) until the user has engaged with the diligence block. A blank "ok" is worse than no confirmation — push back: "Before I draft — anything in the diligence that changes the calculus? Size, prior litigation, their counsel, relationship?"
If diligence surfaces anything in the practice profile's automatic-escalation list (customer, bigger counterparty, patent matter, press-attracting, etc.), route to the named approver per the profile — do not draft on the reviewer's behalf until the approver has signed off on going forward.
If critical diligence items cannot be answered (e.g., entity cannot be confirmed, size is unknown and the counterparty is not on any public register), say so and flag: "I can't confirm [entity / size / counsel] from available sources. Do you have this, or should we pause until a paralegal or OC runs the confirmation?"
Draft structure:
Re: Unauthorized use of [MARK] (US Reg. No. [•])[CITE: Lanham Act §32 / §43(a) / 17 U.S.C. §501 / state UCL / contract §] as applicableDrafting rules:
[CITE: Lanham Act §32, 15 U.S.C. §1114] stays as a placeholder unless the user provided the cite or a research tool returned it. Tag every citation with source — [Westlaw], [user provided], [model knowledge — verify], [web search — verify]. Never strip the tags.Before presenting the draft in-chat or writing the .docx, display this gate verbatim. The user must engage with it — a blank acknowledgment is worse than no gate.
┌─────────────────────────────────────────────────────────────┐
│ BEFORE THIS DRAFT GOES ANYWHERE │
├─────────────────────────────────────────────────────────────┤
│ │
│ This is a draft for attorney review — not a letter to │
│ send. Sending a cease-and-desist letter is an assertion │
│ of legal rights with real consequences: │
│ │
│ • It can trigger a declaratory judgment action in a │
│ jurisdiction of the recipient's choosing. A well-funded │
│ recipient can use a C&D as an invitation to pick a │
│ hostile forum. │
│ │
│ • Overbroad or bad-faith assertions can be used against │
│ the sender — §43(a)(1)(B) claims, Rule 11 sanctions, │
│ attorneys' fees under the Lanham Act / Copyright Act. │
│ │
│ • It starts a dispute that may not settle cheaply. │
│ │
│ Confirm before the letter leaves: │
│ │
│ 1. The rights asserted are valid — registered (pulled │
│ from the register, not assumed) or solidly common │
│ law with evidence of acquired distinctiveness. │
│ 2. The claim is colorable — a reasonable practitioner │
│ would make it on these facts. │
│ 3. The demand is proportionate — we are asking for │
│ relief the conduct warrants, not everything. │
│ 4. Whoever has authority to start a fight has approved. │
│ 5. Counterparty diligence (Step 5.5) was presented │
│ and confirmed — entity, size, IP portfolio, prior │
│ litigation, counsel, DJ-plaintiff risk, and │
│ relationship risk. Not conditional. Required. │
│ │
│ Approver per your practice profile: [approver name/role │
│ from Enforcement posture → Approval matrix → C&D row] │
│ │
│ Automatic escalations that apply here: [list any from the │
│ practice profile that this matter triggers — customer, │
│ bigger counterparty, patent, press-attracting, etc. — │
│ surfaced in Step 5.5 diligence] │
│ │
│ Parallel-path status (marketplace conduct): [filed / │
│ queued / declined — from Step 4. "Not applicable" if │
│ conduct is not on a marketplace.] │
│ │
└─────────────────────────────────────────────────────────────┘If the user is a non-lawyer (per ## Who's using this), add:
Sending a C&D has legal consequences that go beyond the recipient's response — it is an affirmative assertion of rights that can be held against you. Have you reviewed this with an attorney? If not, here's a brief to bring to them: [generate a 1-page summary: parties, rights asserted, infringing conduct, demand, posture, risks flagged above, what could go wrong, specific questions for the attorney].
If you need to find a licensed attorney, solicitor, barrister, or other authorised legal professional in your jurisdiction: your professional regulator's referral service is the fastest starting point (state bar in the US, SRA/Bar Standards Board in England & Wales, Law Society in Scotland/NI/Ireland/Canada/Australia, or your jurisdiction's equivalent). The ABA IP section and state IP associations (US), CIPA/ITMA (UK), and equivalent bodies elsewhere maintain referral rosters for trademark and copyright practitioners.
Do not write the .docx or mark the draft as ready without explicit engagement with the gate.
Primary: <matter-folder>/cease-desist/<slug>/draft-v<N>.docx (or cease-desist/<slug>/draft-v<N>.docx at practice level). Use the docx skill. Letter-formatted per the draft structure above. Strip the work-product header from the outgoing letter.
In-chat: show the draft as plain text for review before writing the .docx. Iterate before committing to disk.
Reviewer-facing closing note (appended to the in-chat preview only, stripped from the .docx):
This is a draft cease-and-desist letter for attorney review, not a letter ready to send. Sending it is an assertion of legal rights with the consequences described in the pre-delivery gate. A licensed attorney reviews, edits, and takes professional responsibility before sending. Do not send this draft unreviewed.
Citation verification. Every [CITE:___] and every cite carried from a template or provided authority is unverified until run through a citator. Before sending, verify each cite is good law on a legal research platform. Fabricated or misquoted cites in sent assertion letters are professional responsibility exposure. Preserve the source-attribution tags — [Westlaw], [CourtListener], [Descrybe], [user provided], [model knowledge — verify], [web search — verify] — tags flagged verify get checked first.
No silent supplement. If a configured research tool returns few or no results for an authority the draft needs, report what was found and stop. Do NOT backfill from web search or model knowledge without asking. Present options — broaden the query, try a different tool, accept web search with tags, leave the placeholder — and let the user decide.
Post-send checklist. After the draft is approved, write <matter-folder>/cease-desist/<slug>/checklist.md with: final read by approver, all [VERIFY] resolved, all [CITE] filled and verified, privilege markings stripped from the outgoing letter, approver signed, delivery method executed, proof of delivery retained, compliance deadline calendared, escalation plan if no response, matter created in matters/ if not already.
Extract:
Not a legal opinion — a structured read:
[SME VERIFY] the forum's test). For copyright: access + substantial similarity. Flag where the claim looks weakest.Present 4-5 options with tradeoffs:
A — Comply quickly
B — Negotiate
C — Respond firmly (reject)
/ip-legal:cease-desist --send reframed as a responseD — Ignore (and preserve)
E — Pre-empt with a DJ action or cancellation
F — File to cancel their mark (TTAB) or invalidate their copyright registration
Recommend one with two sentences of rationale. Be specific about why.
Ignoring a stated deadline entirely is a choice, not a default. Note that filing usually follows silence, not the deadline date.
Output: <matter-folder>/cease-desist/inbound/<slug>/triage.md (or at practice level if matter workspaces are off).
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
[PRIVILEGE INHERITANCE BLOCK — pick by role and matter type; see guidance below the template]
# C&D Received — Triage
> **READ FOR TRIAGE, NOT OPINION.** This is an intake scan and options analysis — not a legal merit opinion. The assessment below is a structured read to support counsel's decision on routing and response. Every cited statute, rule, or case is flagged for SME verification; every merit call is the counsel's, not this skill's.
**Slug:** [slug]
**Received:** [YYYY-MM-DD]
**Received by:** [entity / person]
**Incoming file:** [path]
## The assertion
**Sender:** [entity, signer, counsel]
**Asserted right:** [trademark / copyright / both — with specifics, reg numbers, jurisdictions]
**Alleged conduct:** [their version, one paragraph]
**Demand:** [list — specific asks]
**Their stated deadline:** [date]
**Tone:** [firm / soft / scorched-earth]
## Rights validity
[Registrations as asserted — `[SME VERIFY]` against the register; common-law claims evaluated against the evidence cited]
## Legal basis cited
[Each citation inline-tagged with `[SME VERIFY: applicability / currency / jurisdiction]` and source `[Westlaw / user provided / model knowledge — verify / web search — verify]`. Do not rely on any citation here without independent check.]
## Plausibility assessment
- **Confusion / similarity / infringement on the facts:** [read]
- **Overbreadth:** [read]
- **Timing issues (laches, SoL, registration timing):** [read]
- **Forum:** [their likely forum; DJ opportunity]
## Our exposure
- **Actually infringing?** [honest look]
- **Cost of compliance vs. cost of fight:** [read]
- **Sender credibility:** [troll / real claimant / repeat plaintiff — with any public-docket evidence]
- **Collateral stakes:** [brand, customers, precedent]
**Triage rating:** [substantial / debatable / weak / frivolous] — *structured read for routing, not a merit opinion; `[SME VERIFY]`*
## Options
### A. Comply quickly
[Rationale, tradeoffs, next step]
### B. Negotiate
[Rationale, tradeoffs, next step]
### C. Respond firmly
[Rationale, tradeoffs, next step]
### D. Ignore + preserve
[Rationale, tradeoffs, next step]
### E. Pre-empt (DJ)
[Rationale, tradeoffs, next step]
### F. File to cancel / invalidate
[Rationale, tradeoffs, next step]
**Recommendation:** [A/B/C/D/E/F] — [two sentences why] — `[SME VERIFY: counsel to confirm before executing]`
## Deadlines
- **Their stated deadline:** [date]
- **Our internal decision deadline:** [date]
- **Legal deadlines on any underlying claim:** [SoL, cure, procedural — with dates]
## Immediate actions
- [ ] Legal hold issued — [yes/no]
- [ ] Matter created in log — [yes/no/TBD]
- [ ] Counsel assigned — [who]
- [ ] Insurance tendered — [yes/no/N-A]
- [ ] Internal escalation — [who/when]Privilege inheritance block — pick by role and matter type. Read ## Who's using this (Role) in the plugin config and the matter type (trademark / copyright / patent / OSS / other). This triage records a first-pass merit read on an adverse assertion; whether it's actually privileged depends on who prepared it and what it's about. Getting this wrong in either direction is harmful — a false "privileged" marking creates a discoverable admission that reads as a concession; under-marking a genuinely privileged memo can waive the protection. Insert exactly one of the following:
Role = Lawyer / legal professional:
Privilege inheritance. This triage records our first-pass merit read and response posture on an adverse assertion. It is attorney-client and/or work-product material. Do not forward, attach to an insurance tender without scrubbing, or share with counterparty. Store with privileged matter material and mark per house privilege conventions.
Role = Registered patent agent, matter is a patent matter before the USPTO:
Privilege (patent agent-client). This triage is privileged under the federal patent agent-client privilege recognized in In re Queen's University at Kingston, 820 F.3d 1287 (Fed. Cir. 2016), because it relates to a matter reasonably necessary and incident to the prosecution of patents before the USPTO. That privilege is narrow: it does not extend to matters outside USPTO practice. Do not forward, attach to an insurance tender without scrubbing, or share with counterparty. Bring to supervising counsel for matter-specific privilege decisions.
Role = Registered patent agent, matter is NOT a patent matter (trademark, copyright, OSS, trade secret, contract, or anything else outside USPTO practice):
CONFIDENTIAL — NOT PRIVILEGED. This triage is not privileged because a registered patent agent's privilege is limited to patent prosecution before the USPTO (In re Queen's University at Kingston, 820 F.3d 1287 (Fed. Cir. 2016)). A trademark, copyright, OSS, or other non-patent matter falls outside that privilege. Treat this document as confidential, store it with care, bring it to counsel, and let counsel mark it. Do not forward it as a privileged document.
Role = Non-lawyer and not a registered patent agent:
CONFIDENTIAL — NOT PRIVILEGED. This document is not privileged unless and until reviewed by a licensed attorney. Treat it as confidential; do not forward to anyone outside the legal review chain; bring it to counsel and let counsel mark it. Forwarding this document as "privileged" before an attorney reviews it does not make it so and can harm you if the matter becomes contested.
Close the in-chat presentation with this guardrail verbatim:
This is a triage memo, not advice. The strength assessment above is a first read based on the letter alone — it does not account for facts you haven't told me, registrations I can't verify, or jurisdictional issues. An attorney evaluates before you respond, decide to ignore, or commit to a path.
If the user is a non-lawyer, add the "find-an-attorney" routing paragraph from send mode.
Based on the recommendation and user confirmation:
/ip-legal:cease-desist --send with context pre-populated as a response letter (this triggers the send-mode gate anew)./ip-legal:matter-workspace new <slug> pre-populated.Per ## Decision posture on subjective legal calls in the practice profile: when uncertain whether there is infringement, whether a mark is confusingly similar, whether a work is substantially similar, whether a claim is colorable, or whether sending is safe — do not silently decide it's fine. Flag for attorney review, surface the factors cutting both ways, note the uncertainty. Sending a C&D on an assumption is a one-way door; surfacing doubt is a two-way door.
--skip-gate flag (none is provided), the skill would log the skip in the draft file.© anthropics, 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
Just SKILL.md in ip-legal/skills/cease-desist of anthropics/claude-for-legal.
Open the folder on GitHubat commit 4a6c651
We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.
Cease Desist 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 | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cease Desist this skillanthropics/claude-for-legal | 9.6k | 3 repos | ~9.3k | Automated safety check: Pass | Apache-2.0 | |
| Litigation Deadline Calendarlawve-ai/awesome-legal-skills | 847 | — | ~4.3k | Automated safety check: Pass | MIT | |
| Moot Court Simulation Buildercat-xierluo/legal-skills | 721 | — | ~1.4k | Automated safety check: Pass | CC-BY-NC-4.0 | |
| Intake To Draftstella/stella | 259 | — | ~537 | Automated safety check: Pass | Apache-2.0 | |
| Nla Arbitrateinternet-court/internet-court-skill | 6.6k | 1 repos | ~866 | Automated safety check: Pass | MIT | |
| Nla Createinternet-court/internet-court-skill | 6.6k | 1 repos | ~915 | Automated safety check: Pass | MIT |
lawve-ai/awesome-legal-skills
Calendar litigation and arbitration deadlines from a scheduling order.
cat-xierluo/legal-skills
Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.
stella/stella
Collects the facts of an unpaid invoice, then drafts a payment demand letter.
internet-court/internet-court-skill
Manually arbitrate NLA escrow fulfillments as an alternative to the automated oracle.
internet-court/internet-court-skill
Create a Natural Language Agreement escrow on-chain. An agent skill from internet-court/internet-court-skill.
internet-court/internet-court-skill
Fulfill an existing NLA escrow and collect tokens. An agent skill from internet-court/internet-court-skill.
anthropics/claude-for-legal
Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.
anthropics/claude-for-legal
Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.
anthropics/claude-for-legal
Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.
anthropics/claude-for-legal
Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.
anthropics/claude-for-legal
Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.
anthropics/claude-for-legal
Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.
Categories
Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Cease Desist is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Draft a cease-and-desist letter (send mode) or triage one you received (receive mode).
Cease Desist fits situations like: asserting your rights against an infringer with a demand letter calibrated to your enforcement posture; an incoming C&D needs triage into a structured options memo with a recommendation.
Run `npx skills add anthropics/claude-for-legal --skill cease-desist -a claude-code`. Or copy the skill folder (ip-legal/skills/cease-desist in anthropics/claude-for-legal) into .claude/skills/cease-desist in your project. Claude Code loads it when a task matches its description.
Run `npx skills add anthropics/claude-for-legal --skill cease-desist -a codex`. Or copy the skill folder (ip-legal/skills/cease-desist in anthropics/claude-for-legal) into .agents/skills/cease-desist in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill cease-desist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cease-desist, .gemini/skills/cease-desist, .github/skills/cease-desist and .opencode/skills/cease-desist in your project.
SKILL.md names no scripts, command-line tools or credentials: Cease Desist is instructions for the agent only.
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.
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.
Cease Desist 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.
About 9.3k tokens (SKILL.md is roughly 37k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Cease Desist: Litigation Deadline Calendar (lawve-ai/awesome-legal-skills, 847 stars), Moot Court Simulation Builder (cat-xierluo/legal-skills, 721 stars), Intake To Draft (stella/stella, 259 stars) and Nla Arbitrate (internet-court/internet-court-skill, 6.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,633 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.
Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.