AGENT SKILL

firecrawl-gov-index

Find US statutes, regulations, codes, court opinions, and agency guidance via Firecrawl's free Government Index. Use for compliance questions, "is X legal in state Y", "what does the rule require", case law interpreting a rule, and citation lookups (U.S.C., CFR, case cites). US federal, state, and local material only; not for non-US law.

License 许可
ISC
最近更新
2026-11-15
Stars
★ 1
Forks
0

01 前言 Front Matter

name
firecrawl-gov-index
description
Find US statutes, regulations, codes, court opinions, and agency guidance via Firecrawl's free Government Index. Use for compliance questions, "is X legal in state Y", "what does the rule require", case law interpreting a rule, and citation lookups (U.S.C., CFR, case cites). US federal, state, and local material only; not for non-US law.

02 资源文件 2

03 SKILL.md 正文

Firecrawl Government Index

Find the legal or regulatory text behind a US question: federal, state, and local statutes, regulations, codes, court opinions, and agency publications. Ranked matches also include historical versions, bill text, agency guidance, and third-party reproductions, so a match is a lead to verify, not a statement of current governing law. Coverage is US only, and a page the index has not seen is not there; court labels are most complete for federal courts and case-law collections.

Tools

One verb, called through the harness wrapper (the Firecrawl MCP is retired and the wrapper verb is API-direct and does not use the vendor firecrawl gov command):

firecrawl-cli gov "<question, jurisdiction, date>" [filters] --json

It is free: credits_spent is 0 and no key is needed. A key in FIRECRAWL_API_KEY is sent only for higher rate limits.

  • --limit N (1-100, default 10). Never -k, which is the API-key option.
  • --jurisdiction CODE: us for federal, or us- plus a state or territory code (us-ca, us-dc). Use whenever the question is about one state.
  • --court ID: one CourtListener court (scotus, ca9, nysd).
  • --court-type TYPE: federal-supreme, federal-appellate, federal-district, federal-bankruptcy, federal-special, military, state-supreme, state-appellate, state-trial, state-special, state-attorney-general. Use to restrict to a class of courts.
  • --cites CITATION: pages citing a printed citation (42 U.S.C. § 1983, 5 U.S. 137) or an id (us:usc:42:1983).
  • --domain HOST: one site, such as irs.gov.
  • --timeout S, --full, -o PATH are the wrapper-common flags.

Filters combine with AND and keep only pages the index has labeled, so a filtered search can drop relevant pages. If a filtered query is empty, retry with fewer filters before concluding anything.

Results are in data.data.web[] (the envelope's data is the API payload):

{"surface":"gov","verb":"gov","credits_spent":0,
 "data":{"success":true,"data":{"web":[
  {"url":"https://leginfo.legislature.ca.gov/faces/codes_displaySection.xhtml?lawCode=CIV&sectionNum=1798.82",
   "title":"California Code, CIV 1798.82",
   "description":"Code Section > Code Text > ... 1798.82. (a) (1) An individual or business that conducts business in California ...",
   "position":2}]}}}

description is the matched excerpt and is often long statute text. The wrapper bounds body text at 24,576 characters; pass --full to lift that when you need every excerpt. A bad filter value exits 4 with no call; an API 400 (unknown court id, unreadable citation) exits 1 with the API's reason in error.message; 429 and 5xx exit 2 and are worth retrying.

Match the approach to the question

  • Compliance requirement ("allergen labeling rules", "data breach notice deadline") → plain-language query plus --jurisdiction. Run us and the state separately when both may apply.
  • Case law interpreting a rule → query the rule and the issue, add --court-type for a class of courts, or --court for one court.
  • Agency publication or guidance ("IRS guidance on X") → --domain set to the agency site.
  • Citation chase (who cites a statute or case) → --cites with the printed citation. Combine with --court-type to see how courts treat it.
  • Single named section ("Cal. Civ. Code 1798.82") → query the citation text with its --jurisdiction; then fetch the page to read the whole section.
  • Does the rule exist at all → search broadly first, filter second. Filters hide unlabeled pages.

Verify before citing

  • Check the issuer, jurisdiction, enacted or effective status, and version. Bill text, agency guidance, historical versions, and third-party copies all rank beside the current code.
  • Read the source: firecrawl-cli fetch <url> --json. An excerpt alone rarely settles scope, exceptions, or effective dates. Check a bill's status rather than inferring it from its title.
  • Cite the controlling section and the supporting passage; give a page, section, or date only when the evidence shows it.
  • No results is not no law. State what you searched and what could be missing.
  • Ask for the jurisdiction when it is missing before naming a governing rule.
  • This finds sources. It is not legal advice.

Routing

  • Non-US law, or US coverage the index lacks (unlabeled courts, municipal ordinances, very recent changes) → plain web search: exa-cli search, then firecrawl-cli search.
  • The user supplied a source URL → skip search and read it with firecrawl-cli fetch <url> --json.
  • Library, API, or code questions → firecrawl-developer-index; papers → firecrawl-research-index.

04 同仓库更多 Skills

StartupBros-com
StartupBros-com/hov-stack

review-adversarial-first

Operator-invoked adversarial review: 3 refute-by-default lenses plus a deterministic judge against a PR, branch, or path, then a decision on whether /ce-code-review's topic fan-out runs. Off the default merge path since the 2026-10-17 merge-and-end ruling; run only when asked for by name.

★ 1
StartupBros-com
StartupBros-com/hov-stack

memory-mine

Run one deterministic, budgeted directed-capture batch for an explicit Claude Code project store. Use manual workspace mode only when cross-agent cass sessions are intentionally in scope.

★ 1
StartupBros-com
StartupBros-com/hov-stack

papers

Search preprints from arXiv, bioRxiv, and medRxiv without API keys. Supports search, lookup, extraction, citations, enrichment, and paper downloads that bundle PDFs plus linked GitHub code.

★ 1
StartupBros-com
StartupBros-com/hov-stack

papers

Search preprints from arXiv, bioRxiv, and medRxiv without API keys. Supports search, lookup, extraction, citations, enrichment, and paper downloads that bundle PDFs plus linked GitHub code.

★ 1
StartupBros-com
StartupBros-com/hov-stack

wsl-cdp

Drive the user's real, logged-in Windows browser (Chrome, Edge, or Brave) from a Claude Code session running inside WSL2, over the Chrome DevTools Protocol - read authenticated dashboards and consoles, take real screenshots, open and read pages with the user's sessions. Use when a task needs the user's existing web logins and the session runs in WSL2, where the Claude in Chrome extension cannot work. Not for native-Windows or macOS Claude Code (use the official Claude in Chrome extension), not for anonymous scraping or CI (use headless Playwright inside WSL), not for getting past login walls (those are handed to the human).

★ 1
StartupBros-com
StartupBros-com/hov-stack

token-eater

[BETA] Spend a subscription's idle, about-to-expire credits on safe, machine-verified cleanup. You pick the service (Grok / Codex / Claude) and a token-heavy maintenance skill (de-monolithize, de-slop, simplify, dead-code); that service runs the whole skill -> gate -> self-review -> draft-PR loop on its own credits, in an isolated worktree. token-eater verifies the gate and never merges. Manual invocation only during beta.

★ 1