New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Research Start

by anthropics in anthropics/claude-for-legal

Research roadmap for a legal issue — statutes to check, case law areas to investigate, regulatory frameworks, Westlaw search terms.

OfficialApache-2.0Auto-check passedLegal & Compliance

Install Research Start

skills CLI
$ npx skills add anthropics/claude-for-legal --skill research-start -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/claude-for-legal research-start --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/legal-clinic/skills/research-start .claude/skills/research-start && rm -rf skills-src

Use ~/.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/

Facts

Skill name
research-start
GitHub stars
9.6k
Used in
3 other repos
Token cost
~2.8k tokens
SKILL.md length
1,198 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Research roadmap for a legal issue — statutes to check, case law areas to investigate, regulatory frameworks, Westlaw search terms.

  • Works in 5 steps: Seed documents first → Frame the issue → Build the roadmap → …
  • A student asks where to start researching
  • SKILL.md covers Purpose, Load context, Workflow and Output, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Research Start is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Research roadmap for a legal issue — statutes to check, case law areas to investigate, regulatory frameworks, Westlaw search terms. Leads and frameworks, NOT authoritative citations; students verify and develop everything. Use when a student asks where to start researching, wants a research roadmap for an issue, or needs gaps identified in existing research.

Its SKILL.md is about 2.8k 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 Legal research. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • A student asks where to start researching
  • Wants a research roadmap for an issue
  • Needs gaps identified in existing research

Example prompts

  • “/research-start”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Seed documents first
  2. Frame the issue
  3. Build the roadmap
  4. Flag what's uncertain
  5. Synthesize uploaded research (if any)

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Research Start loads about 2.8k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 1,198 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 1,198 words, ~2,777 tokens.

Download SKILL.mdSave it as .claude/skills/research-start/SKILL.md (or your agent's skills folder).
name
research-start
description
Research roadmap for a legal issue — statutes to check, case law areas to investigate, regulatory frameworks, Westlaw search terms. Leads and frameworks, NOT authoritative citations; students verify and develop everything. Use when a student asks where to start researching, wants a research roadmap for an issue, or needs gaps identified in existing research.
argument-hint
[legal issue]

/research-start

  1. Load ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → jurisdiction, practice area.
  2. Use the workflow below.
  3. Frame the issue specifically. Build roadmap: statutory starting points (unverified), case law areas (not cases), secondary sources, search terms.
  4. If student has existing research uploaded: synthesize and identify gaps.
  5. Output with prominent "leads not authorities" header. Everything is a starting point the student verifies.
/legal-clinic:research-start "habitability defense to nonpayment eviction in [State]"

Research Start: Roadmap, Not Research

Purpose

Legal research is essential to clinical education. But the initial phase — figuring out what to research, finding the right statute, understanding the framework — is often the most time-consuming and least educational part. Students spend hours finding the starting point before they can do the actual research.

This skill produces the starting point: statutes to check, case law areas to investigate, search terms for Westlaw and CourtListener. None of it is verified. None of it is authoritative. All of it is a lead for the student to run down.

This is a pedagogical safeguard, not just an ethical one. Students still learn to research. They just start from a better place.

Load context

~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → jurisdiction (state), practice areas.

Workflow

Step 0: Seed documents first

Before building the roadmap, read the clinic's own seed documents. The supervising attorney uploaded them at cold-start (handbook, filing guides, local court rules, intake forms, example case files, prior memos) — they are pre-vetted, jurisdiction-specific, and will beat any Westlaw query on the first 20 minutes of a student's research.

  1. Read ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → ## Seed documents. Identify any item whose purpose or filename matches the research area (e.g., "Alameda UD filing guide" for a UD habitability question; a redacted sample case file in the same practice area; a prior memo on the same issue).
  2. For each match, surface it as a Seed documents to read first block at the top of the roadmap output. Name the file, say why it matters for this specific question, and say what it likely covers vs. where outside research will still be needed.
  3. If no seed documents match the issue, say so plainly ("No clinic seed documents match this issue — proceeding straight to primary sources"). Don't fabricate a match.
  4. If the clinic has the LIMITED DATA flag set in ## Seed documents, add a one-line note: "Clinic has fewer than 10 seed docs; your professor's precedent bank is thin — lean harder on primary sources and flag what's missing for your supervisor."

The roadmap still covers statutes, case law areas, secondary sources, and search terms — seed docs are the first lead, not a replacement for the rest. But surface them above everything else so the student starts where their supervisor's precedent starts.

Step 1: Frame the issue

What's the research question? Be specific. Not "eviction defenses" — "habitability defense to nonpayment eviction in [State], specifically whether a broken heater qualifies and whether the tenant had to give written notice."

If the question is too broad, narrow it with the student: "That's three research questions. Let's take them one at a time. Which first?"

Step 2: Build the roadmap

Statutory starting points: List statutes likely relevant. State explicitly these are likely, not confirmed.

Likely relevant statutes (UNVERIFIED — confirm currency and applicability):

  • [State] Landlord-Tenant Act, likely at [State Code Title X] — look for "warranty of habitability" or "repair and deduct"
  • Local housing code for [City/County] — may define specific conditions (heat, water) as required
  • [VERIFY each citation is current and correct — codes get renumbered]

Case law areas to investigate: Not cases — areas. The student finds the cases.

Case law areas:

  • [State] Supreme Court or appellate decisions on implied warranty of habitability — look for the leading case establishing the doctrine
  • Cases on what conditions qualify — heat specifically, if any
  • Cases on procedural prerequisites — did tenant have to give notice? withhold rent? escrow?
  • Cases on the remedy — offset against rent owed, or a separate damages claim?

Regulatory / administrative sources: If applicable (immigration especially).

Administrative sources:

  • [Agency] regulations at [CFR cite area]
  • Agency guidance or policy manuals — often more current than regs
  • For immigration: USCIS Policy Manual, BIA precedent decisions

Secondary sources to orient: Where to get the framework before diving into primary.

Secondary sources (for framework, not to cite):

  • [State] practice guide on landlord-tenant (check clinic library)
  • Relevant CLE materials
  • Law review notes on the specific issue if it's contested

Search terms: For Westlaw, or whatever the clinic uses.

Search terms to try:

  • Westlaw: "warranty of habitability" /s heat! & [State]
  • CourtListener: implied warranty of habitability AND (heat OR heater) AND [State]
  • Refine based on what comes back — these are starting queries
Show full SKILL.md (450 more words)Show less
Step 3: Flag what's uncertain

If the skill is unsure whether a source is relevant or current:

[UNCERTAIN: whether [State] has a specific statute on this vs. common-law doctrine only — the search will tell you]

Uncertainty is stated, not hidden.

No silent supplement. This skill produces leads, not authoritative citations — by design, students run the citations down themselves. But if a query to a configured research tool (Westlaw, CourtListener) returns few or no results for a specific rule or case, say so and stop. Do NOT manufacture citations from web search or model knowledge to fill a thin result set without asking. Say: "The search returned [N] results from [tool]. Coverage appears thin for [rule]. Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged [web search — verify] and should be checked against a primary source before relying, or (4) stop here and flag the gap for your supervisor. Which would you like?" The supervising attorney decides whether to accept lower-confidence sources.

Source attribution. Tag every suggested citation with where it came from: [Westlaw], [CourtListener], or the MCP tool name for citations retrieved from a legal research connector; [web search — verify] for web-search citations; [model knowledge — verify] for citations recalled from training data; [user provided] for citations supplied by the supervising attorney or case file. Citations tagged verify carry higher fabrication risk and should be checked first. Never strip or collapse the tags — they tell the student which leads are raw research and which are model guesses to verify against a primary source.

Step 4: Synthesize uploaded research (if any)

If the student has already done some research and uploads it: read it, identify what's covered and what's missing.

From your research so far:

  • You have: [summary of what's covered]
  • Gap: [what the roadmap above suggests that you haven't found yet]
  • [VERIFY: the case you cited — [name] — run through a citator (verify it is good law) it, it may have been distinguished or limited]

Output

markdown
═══════════════════════════════════════════════════════════════════════
  RESEARCH ROADMAP — LEADS, NOT AUTHORITIES
  Nothing below is a verified citation. Every statute, every case area,
  every search term is a starting point for YOUR research. You verify
  currency, applicability, and accuracy. You find the actual cases.
  If something below turns out to be wrong or outdated, that's expected —
  this is a map of where to look, not a substitute for looking.
═══════════════════════════════════════════════════════════════════════

# Research Roadmap: [Issue]

**Jurisdiction:** [State] | **Practice area:** [area]

## Seed documents to read first

[Per Step 0. List any clinic seed docs that match the issue with a one-line
"what this likely covers" note. If none matched: "No clinic seed documents
match this issue — proceeding to primary sources."]

## Statutory starting points (UNVERIFIED)

[list with VERIFY flags]

## Case law areas to investigate

[areas, not cases]

## Administrative / regulatory sources

[if applicable]

## Secondary sources (for framework, not citation)

[list]

## Search terms

**Westlaw:** [queries]

## Uncertainty flags

[Everywhere the roadmap is genuinely unsure]

---

## What to do with this

1. Start with a secondary source to get the framework
2. Find and read the primary statutes — confirm the citations above are current
3. Run the searches, find the leading cases
4. run through a citator (verify it is good law) everything before relying on it
5. Come back and run `/memo` to scaffold your analysis once you have the rule

## What this roadmap does NOT do

- **It does not give you citations you can use.** Every cite above is a lead
  to verify, not an authority to rely on.
- **It does not do the research.** You do the research. This gets you to the
  starting line faster.
- **It does not replace Westlaw.** Those have the actual cases. This
  tells you where to point them.

---

**Cite verification — required before use.** Citations above were generated by an AI model and have not been verified. Before relying on any case, statute, or rule — or including it in client work — run it through Westlaw, CourtListener, or your clinic's research platform for accuracy and current good-law status. Flag unverified citations to your supervisor.

What this skill does NOT do

  • Provide authoritative citations. Explicitly, by design. The student verifies every cite before using it.
  • Replace legal research. Accelerates the "where do I start" phase; the research itself is still the student's.
  • Guarantee the roadmap is complete. It's a starting set of leads. The research may reveal sources the roadmap missed — that's fine, that's research.

Close with the next-steps decision tree

End with the next-steps decision tree per CLAUDE.md ## Outputs. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.

© 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

Files

Just SKILL.md in legal-clinic/skills/research-start of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 3 other repositories

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.

Compare with similar skills

Research Start 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.

Research Start compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Start this skillanthropics/claude-for-legal9.6k3 repos~2.8kAutomated safety check: PassApache-2.0
Tw Legal RAGaa0101181514/tw-legal-rag328—~580Automated safety check: PassCustom licence
Design Award SearchSeanJ1ang/design-judge-skills712—~3kAutomated safety check: PassApache-2.0
China Lawyer AnalystCSlawyer1985/china-lawyer-analyst196—~3.3kAutomated safety check: PassNone
Billing And Litigation BudgetTHUYRan/Legal-Skills-Chinese873—~5kAutomated safety check: PassNone
Legal Issue ResearchGolden2002/legal-research-skill156—~6.8kAutomated safety check: PassMIT

Similar skills

  • Tw Legal RAG

    aa0101181514/tw-legal-rag

    Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.

    328 GitHub stars~580 tokensUpdated yesterday
    Legal & ComplianceAuto-check passed

  • Design Award Search

    SeanJ1ang/design-judge-skills

    Find and verify award-winning designs in the same or adjacent functional category through eight explicit relevance dimensions: problem and user, core function, sensing technology, intervention…

    712 GitHub stars~3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • China Lawyer Analyst

    CSlawyer1985/china-lawyer-analyst

    通过中国法律视角分析事件，运用成文法解释、指导案例参照、请求权基础分析等方法， 理解权利义务、评估责任风险、识别法律依据并推荐合规策略。

    196 GitHub stars~3.3k tokensUpdated 8 mo ago
    Legal & ComplianceAuto-check passed

  • Billing And Litigation Budget

    THUYRan/Legal-Skills-Chinese

    A skill your agent uses when the user needs to track or manage attorney hours, expert fees, and investigation costs; control litigation spend; or prepare timesheets or expense statements for clients.

    873 GitHub stars~5k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • Legal Issue Research

    Golden2002/legal-research-skill

    中国法律全领域系统性检索专家. An agent skill from Golden2002/legal-research-skill.

    156 GitHub stars~6.8k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • Tax Law Research

    Serein-81/financial_rag

    Searches current Chinese tax laws, rates and policy changes with Tavily web search, prioritizing government sources and flagging outdated or conflicting results.

    148 GitHub stars~997 tokensUpdated 4 mo ago
    Legal & ComplianceAuto-check: notes

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    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.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    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.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Categories

Questions about Research Start

What does Research Start do?

Research roadmap for a legal issue — statutes to check, case law areas to investigate, regulatory frameworks, Westlaw search terms. Research Start is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Research roadmap for a legal issue — statutes to check, case law areas to investigate, regulatory frameworks, Westlaw search terms.

When should I use Research Start?

Research Start fits situations like: A student asks where to start researching; wants a research roadmap for an issue; needs gaps identified in existing research.

How do I install Research Start in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill research-start -a claude-code`. Or copy the skill folder (legal-clinic/skills/research-start in anthropics/claude-for-legal) into .claude/skills/research-start in your project. Claude Code loads it when a task matches its description.

How do I install Research Start in Codex?

Run `npx skills add anthropics/claude-for-legal --skill research-start -a codex`. Or copy the skill folder (legal-clinic/skills/research-start in anthropics/claude-for-legal) into .agents/skills/research-start in your project. Codex loads it when a task matches its description.

Can I use Research Start in Cursor, Gemini CLI or GitHub Copilot?

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 research-start -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-start, .gemini/skills/research-start, .github/skills/research-start and .opencode/skills/research-start in your project.

What does Research Start need to run?

SKILL.md names no scripts, command-line tools or credentials: Research Start is instructions for the agent only.

Does Research Start access the network?

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.

Is Research Start safe to install?

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.

What licence does Research Start use?

Research Start 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.

How many tokens does Research Start use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Research Start?

Skills that share tags, products or a category with Research Start: Tw Legal RAG (aa0101181514/tw-legal-rag, 328 stars), Design Award Search (SeanJ1ang/design-judge-skills, 712 stars), China Lawyer Analyst (CSlawyer1985/china-lawyer-analyst, 196 stars) and Billing And Litigation Budget (THUYRan/Legal-Skills-Chinese, 873 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Start?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,629 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.