Skip to content
Agentmart
Submit a tool

case-strategy

Use when an attorney wants defense strategy, tactics or investigative questions for a specific matter, grounded in and cited to the firm's vetted…

Skill by Torq-Legal-Labs

IndexedMIT
Write a review

Chalk Labs

Need help deploying case-strategy?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/torq-legal-labs-case-strategy

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when an attorney wants defense strategy, tactics or investigative questions for a specific matter, grounded in and cited to the firm's vetted reference-library manuals in Torq.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/case-strategy

What's inside

Skill name
case-strategy
Description
Use when an attorney wants defense strategy, tactics or investigative questions for a specific matter, grounded in and cited to the firm's vetted reference-library manuals in Torq.
License
MIT
Instructions
19 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Case Strategy

Use this skill when an attorney wants recommended defense strategy, tactics, or investigative questions for a specific matter, grounded in the firm’s vetted reference-library manuals rather than general model knowledge.

This is a closed-corpus, no-guessing surface (same contract as library-qa): every recommendation must be traceable to a specific manual passage. Never fill a gap with outside/model knowledge, even if you are confident it is correct in general.

Note: the dedicated Case Strategy engine (POST /cases/:caseId/strategy) runs this end-to-end and lands a cited case_strategy_review card in the Action Inbox. Use THIS skill for interactive, in-chat strategy questions about a matter; prefer the engine route when the attorney wants the persisted, inbox-tracked analysis.

Workflow:
1. If the attorney named a case id, call get_case to load the matter facts (charge, court, jurisdiction, statutes, priors). Otherwise use the facts the attorney supplied verbatim — never invent facts.
2. Identify the distinct legal issues the facts raise, then call semantic_search_docs (one query per issue) to retrieve candidate manual passages. Never pass reference_library_only=false or scope on this surface. When the thread is pinned to the reference library the server forces the closed corpus and ignores those arguments, so a widened search is not available — never describe one to the user.
3. STOP for an issue when the result reports notCovered=true, or when the top hit’s score < 0.615 (the calibrated not-covered similarity threshold): say that issue is not covered in the reference library and name the space(s) searched (spacesSearched) — do not synthesize ungrounded guidance.
4. Otherwise, synthesize strategy / tactics / questions using ONLY the retrieved passage text. Attach a citation to every recommendation: manual title + section path + page number, drawn from each passage’s citation object.
5. Use kb_get_page_content for the same page_id when a recommendation needs more surrounding context than the chunk carries — never widen scope to a different page or manual to fill a gap.
6. Present strategy, tactics, and questions as separate groups, and never present a covered recommendation without its citation attached.

Torq tools this guide uses: `get_case`, `semantic_search_docs`, `kb_get_page_content`. They come from the Torq connector. If they are not available, Torq is not connected or the member's Torq permissions do not include them; setup is at https://torqlegallabs.com/ai-assistants.

From Torq-Legal-Labs/torq-claude-plugin, MIT.

More from Torq-Legal-Labs/torq-claude-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 17, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Torq-Legal-Labs

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get case-strategy running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying case-strategy?

CallGet help
Cite this page

case-strategy skill. Agent Mart. https://agentmart.dev/skills/torq-legal-labs-case-strategy (last updated 2026-10-24)