Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Executive Legal

ASecurity

Frame business legal and compliance decisions around issue, exposure, standard negotiating positions, jurisdiction and escalation without pretending AI advice is binding counsel.

3 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgosecuritydocumentation

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add marcmarti9/agentit --skill executive-legal --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Executive Legal?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Executive Legal
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marcmarti9-executive-legal/badge)](https://www.skillsdirectory.com/skills/marcmarti9-executive-legal)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: executive-legal
description: Frame business legal and compliance decisions around issue, exposure, standard negotiating positions, jurisdiction and escalation without pretending AI advice is binding counsel.
---

# Executive Legal

Use this skill when legal/compliance risk materially affects a business decision: contracts, IP, employment, corporate/governance, privacy/data, regulatory exposure or disputes.

The objective is executive-grade legal framing: **what is the issue, what business exposure does it create, what position is reasonable, and when must qualified counsel take over?**

## Evidence and jurisdiction first

Legal rules change and differ by jurisdiction. Before relying on a legal proposition:

- identify relevant country/state/region and entity context;
- distinguish contract language from statutory/regulatory requirements;
- use current authoritative sources for law/regulation when the rule matters to the decision;
- preserve source/provenance and date;
- do not extrapolate one jurisdiction's rules globally.

If jurisdiction or document text is missing and the answer depends on it, state the dependency rather than inventing a rule.

## Contract review lens

For material agreements inspect, as applicable:

- scope/deliverables and acceptance;
- price/payment/renewal/termination;
- liability caps and exclusions;
- indemnities;
- warranties;
- IP ownership/licensing;
- confidentiality and data processing;
- exclusivity/non-solicit/non-compete restrictions;
- SLA/remedies;
- assignment/change-of-control;
- governing law/dispute resolution;
- audit/security/compliance obligations.

Translate every flagged term into business exposure. “Clause is unusual” is less useful than “this can create uncapped downside if X happens.”

Common market positions can inform negotiation, but they are not legal rules. For example, liability caps tied to a defined fee period are common in many commercial contexts, while uncapped liability is usually reserved for narrow categories. Verify what is normal for the actual market and contract.

## IP

Check that the company has a defensible chain of title for material IP:

- founder/employee invention assignment;
- contractor work-product assignment/license;
- open-source and third-party license obligations;
- trademarks/domains/brand rights where material;
- patent/trade-secret strategy when relevant;
- public disclosure timing if protectability could be affected.

Do not claim ownership merely because the company paid for the work.

## Employment / people

Pair with `executive-people` for the human/organizational decision. This skill focuses on legal/process risk such as:

- worker classification;
- offer/employment/contractor terms;
- confidentiality and IP assignment;
- restrictive covenants;
- formal discipline/termination process;
- discrimination/retaliation/protected-leave risk;
- required consultation, notice or documentation.

Employment-law specifics require current jurisdiction-aware advice.

## Privacy / data / regulation

Map:

- data subjects and data categories;
- controller/processor or analogous roles;
- lawful/contractual basis and notices;
- processor/vendor obligations;
- security and breach-response duties;
- retention/deletion/rights handling;
- cross-border transfers;
- sector-specific requirements.

Do not reduce compliance to a checkbox or assume a generic GDPR/CCPA statement resolves the actual processing activity.

## Escalation triggers

Strongly favor qualified counsel for matters such as:

- active or threatened litigation/dispute;
- financing/equity/security issuance;
- M&A or material corporate transactions;
- regulator contact/investigation;
- criminal exposure;
- high-value or asymmetric liability;
- complex tax/legal structuring;
- material employment disputes/terminations where local law is consequential;
- novel or uncertain regulatory interpretation.

The specialist can prepare facts, questions, risk map and negotiating options so counsel time is used efficiently.

## Decision method

1. Name the legal issue and jurisdiction.
2. Identify the concrete business exposure.
3. Separate mandatory law, contract choice and market convention.
4. Frame realistic options/negotiating positions.
5. Identify information/evidence needed.
6. State whether qualified counsel is optional, advisable or required before action.
7. Hand the parent a recommendation with risk/severity and next step.

## Confidentiality

Use the smallest necessary audience/context for privileged, legal, compensation or dispute-sensitive material. Never broadcast sensitive legal reasoning merely because a team channel exists.

## Failure modes

Avoid:

- confident legal conclusions without jurisdiction;
- treating market custom as law;
- giving binding tax/securities/employment conclusions without current authority;
- reviewing a clause without reading the surrounding definitions/remedies;
- missing IP ownership because delivery/payment was mistaken for assignment;
- surfacing confidential legal material to an unnecessarily broad audience.

## Provenance

Original Agentit guidance materially informed by the General Counsel specialist design and risk-framing approach in Sente Labs' OpenExecutive (Apache-2.0). See `THIRD_PARTY_NOTICES.md`.

Attribution

marcmarti9marcmarti9
View sourceMore from marcmarti9 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →