agentsclimarketplace
Sign in

Advise legal work skills

Skill the-long-ride/skill-master/skills/advise-legal-work-skills

Use when a human wants to design, evaluate, or improve AI agent skills for legal operations, contract review support, clause extraction, policy comparison, matter summaries, compliance evidence, or legal workflow assistanceFrom its SKILL.md

Install
npx -y skills add the-long-ride/skill-master --skill advise-legal-work-skills

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

One thing to look at

  • 1 stars1 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

4.9 KB, 930 tokens by cl100k_base, as published. Nobody here has run it

Legal Work Skill Advisor

Overview

Advisor for designing, evaluating, and improving AI agent skills in the legal work domain. Use this skill to turn a vague skill idea into a compact skill blueprint, not to perform the domain work itself.

When To Use

Use when a human asks to design, review, improve, migrate, publish, or validate an AI agent skill for legal work. Use when trigger quality, workflow shape, failure recovery, output format, references, scripts, or validation need improvement. Do not use when the human wants the agent to directly perform the legal work task instead of designing the skill.

Inputs And Tools

  • User's skill idea, draft SKILL.md, target runtime, example prompts, and any existing references, scripts, or assets.
  • Repository skill files, routing metadata, and validation reports when improving an existing repository.
  • Read-only inspection first; ask before edits, publishing, running commands, or spawning agents.

Workflow

  • Separate skill-design advice from target-domain execution.
  1. Identify the legal workflow: contract intake, clause extraction, playbook review, redline summary, matter timeline, policy comparison, or compliance evidence gathering.
  2. Define jurisdiction, governing documents, playbooks, and review authority.
  3. Specify what the skill may summarize, flag, extract, or draft.
  4. Require human legal review for legal conclusions, negotiation positions, or final approval.
  5. Define confidentiality and privilege handling.
  6. Return a legal-work skill blueprint with validation prompts.

Category Standards

  • Keep the skill compact enough to trigger reliably and load without flooding context.
  • Prefer reusable reference files and scripts for heavy domain-specific details.
  • Do not present legal conclusions as final advice.
  • Preserve source text and citations for clauses or obligations.
  • Define jurisdiction and contract type when relevant.
  • Separate business risk, legal risk, and missing information.
  • Protect confidential and privileged material.
  • Use playbooks or policies as the main standard when available.

Verification

  • Run at least two realistic prompts: one that should trigger the skill and one that should not.
  • Check that the skill asks for missing inputs before giving brittle advice.
  • Confirm failure modes include recovery behavior, not only warnings.
  • Confirm validation commands or manual checks are safe for the target runtime.

Checklist

  • Examples show concrete input and expected output.
  • Verification can be repeated by a human or another agent.
  • Trigger description names legal ops, contract, clause, redline, matter, compliance evidence, policy comparison, or legal workflow.
  • Workflow defines jurisdiction and authority.
  • Skill includes attorney or legal owner escalation rules.
  • Failure modes cover missing playbook, ambiguous clause, confidential data, and high-stakes advice.
  • Output format includes source references and review status.
  • Validation includes a conflicting-clause or missing-jurisdiction example.

Nice To Have

  • Trigger collision notes for adjacent skills.
  • PASS/PARTIAL/FAIL verification rubric.
  • Contract playbook reference.
  • Clause taxonomy.
  • Risk severity rubric.
  • Matter timeline template.
  • Privilege handling checklist.

Example Skill Ideas

  • Contract intake skill.
  • Clause extraction skill.
  • Redline summary skill.
  • Compliance evidence packet skill.

Examples

Input: "Help me design a skill for legal work workflows that reviews drafts and flags missing evidence." Output: A compact skill blueprint with trigger description, ordered workflow, resources, failure recovery, validation prompts, and output format.

Input: "This legal work skill triggers too often and gives generic advice." Output: A revision plan that narrows triggers, moves heavy details to references, adds examples, and defines repeatable verification.

Failure Modes

  • Jurisdiction is unknown: ask for it or mark jurisdiction-dependent content.
  • Playbook is missing: extract facts and request review standard.
  • Legal advice is requested: provide general support and require legal owner review.
  • Confidential data appears: minimize exposure and preserve access boundaries.

Human Verification

Score the revised skill before calling it ready:

Discovery: PASS | PARTIAL | FAIL
Content: PASS | PARTIAL | FAIL
Verification: PASS | PARTIAL | FAIL
Critical gaps:
1. <gap>
Required fixes:
1. <fix>
Decision: READY | NEEDS REVISION

Output Format

Return:

Skill concept: <name>
Legal workflow: <workflow>
Trigger description draft: <Use when...>
Authority and sources:
- <source>
Review boundaries:
- <rule>
Validation:
- <check>
Failure recovery:
- <mode and recovery>

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 930 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

  • separate skill design advice from domain execution
  • inspect read-only before editing or running commands
  • define jurisdiction and authority
  • require human legal review for legal conclusions
  • define confidentiality and privilege handling
  • preserve source text and citations

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.