agentsclimarketplace
Sign in

Search

Skill CaseMark/legal-plugin/search

Searches the web, legal databases, case law, patents, and case.dev knowledge base via the casedev CLI. Use when the user mentions "search", "legal research", "find cases", "case law", "patent search", "web search", "fetch URL", "webfetch", "legal skills", or needs to research legal topics, find similar cases, or retrieve web content.From its SKILL.md

Install
npx -y skills add CaseMark/legal-plugin --skill search

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.5 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

case.dev Search

Unified search across web, legal databases, case law, patents, vault contents, and the case.dev skills knowledge base.

Requires the casedev CLI. See setup skill for installation and auth.

Web Search

casedev search web "employment discrimination California" --json
casedev search web "SEC enforcement actions 2024" --limit 20 --json

Flags:

  • --limit / -l — max results (default: 10)
  • --news — news articles instead of general web
  • --type — explicit type: search or news
  • --include-domain — restrict to domain(s), repeatable
  • --exclude-domain — exclude domain(s), repeatable

Web Fetch

Fetch and extract content from URLs:

casedev search webfetch "https://example.com/ruling.html" --json

Flags:

  • --livecrawl — force live crawl instead of cache
  • --subpages — also crawl linked subpages
  • --subpage-target N — max subpages (default: 5)
  • --max-chars N — truncate content
  • --timeout N — livecrawl timeout in seconds (default: 30)
  • --context — contextual hint for extraction
  • --no-summary — skip summary generation
  • --no-highlights — skip highlights extraction
  • --strict — fail if any URL cannot be fetched
  • --fallback — if fetch fails, fall back to web search

Multiple URLs: casedev search webfetch URL1 URL2 --json

Legal Search

Find legal authorities by topic:

casedev search legal "breach of fiduciary duty" --json
casedev search legal "ERISA preemption" --jurisdiction "federal" --json

Flags:

  • --jurisdiction — filter by jurisdiction
  • --limit / -l — max results (default: 10)
  • --deep — uses the research endpoint with multi-query analysis
  • --alt-query — additional search queries for deep mode, repeatable

Deep mode example:

casedev search legal "force majeure pandemic" --deep \
  --alt-query "impossibility of performance COVID" \
  --alt-query "frustration of purpose" --json

Case Search

Two modes — query-based and similarity-based:

By query

casedev search cases "wrongful termination retaliation" --json
casedev search cases "patent infringement software" --jurisdiction "federal" --json

By similarity (find cases similar to a known case)

casedev search cases --url "https://casetext.com/case/example-v-example" --json
casedev search cases --url "https://example.com/case" --after "2020-01-01" --json

Flags:

  • --jurisdiction — filter by jurisdiction
  • --limit / -l — max results (default: 10)
  • --url — source case URL for similarity search
  • --after — only cases published after this date (ISO format, similarity mode)

Patent Search

casedev search patent "machine learning natural language processing" --json

Flags:

  • --assignee — filter by patent assignee
  • --inventor — filter by inventor name
  • --status — application status filter
  • --type — application type filter
  • --filing-from — filing date range start
  • --filing-to — filing date range end
  • --offset — pagination offset (default: 0)
  • --limit / -l — max results (default: 25)

Vault Semantic Search

Search within vault documents (also available via vaults skill):

casedev search vault "indemnification clause" --vault VAULT_ID --json

See vaults skill for full vault search documentation.

Skills Knowledge Base

Search and read from the case.dev legal skills knowledge base:

# Search skills
casedev skills search "contract review" --json
casedev search skills "deposition preparation" --json

# Read a specific skill
casedev skills read SKILL_SLUG --json
casedev skills read SKILL_SLUG --content-only

Skills search flags: --limit / -l (1-20, default: 10), --show-summary.

Skills read flags: --no-references, --content-only.

Troubleshooting

"Missing query": Provide the search query as a positional argument or with --query "...".

"Missing vault ID" for vault search: Use --vault VAULT_ID or set focus.

Web fetch unavailable: Use --fallback to fall back to web search, or use casedev search web directly.

No legal results: Try broader terms, remove jurisdiction filter, or use --deep mode with --alt-query variations.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most legal skills give in ~1.1k tokens

Counted across 234 of the 234 authors here whose files we hold, read 2026-08-07

  • Use text operators for text fieldsin 11 of 234, across 6 files
  • Consult qualified counsel before usein 11 of 234, across 3 files
  • Use PatentSearch API for patent searchesin 10 of 234, across 5 files
  • Confirm jurisdiction, employment type, and required clausesin 9 of 234, across 2 files
  • Choose a document template and tailor role-specific termsin 9 of 234, across 2 files
  • Validate compensation, benefits, and compliance requirementsin 9 of 234, across 2 files
  • Add signature, confidentiality, and IP assignment terms as neededin 9 of 234, across 2 files
  • Open the implementation playbook for detailed templatesin 9 of 234, across 2 files
  • Use TSDR for trademark data retrievalin 9 of 234, across 4 files
  • Ask for clarification if required inputs are missingin 8 of 234, across 2 files
  • Set the USPTO_API_KEY environment variablein 8 of 234, across 3 files
  • Use the uspto-opendata-python library for PEDSin 8 of 234, across 3 files

Said here and by no other author read

  • run search commands via the casedev CLI
  • provide the search query as a positional argument
  • specify a vault ID for vault search
  • use --fallback if web fetch fails
  • use broader terms or --deep mode if no results

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.