agent-launcher-orchest…
Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a…
/cs:gc-review <plan> — General Counsel interrogation of contracts, IP, regulatory, term sheets, and employment-law surface. Use when reviewing a term sheet before signing, redlining a customer MSA, or checking IP assignment and regulatory exposure on a new product.
$ npx -y skills add alirezarezvani/claude-skills --skill gc-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/gc-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
/cs:gc-review <plan> — General Counsel interrogation of contracts, IP, regulatory, term sheets, and employment-law surface. Use when reviewing a term sheet before signing, redlining a customer MSA, or checking IP assignment and regulatory exposure on a new product.
name: "gc-review" description: "/cs:gc-review <plan> — General Counsel interrogation of contracts, IP, regulatory, term sheets, and employment-law surface. Use when reviewing a term sheet before signing, redlining a customer MSA, or checking IP assignment and regulatory exposure on a new product."
**Command:** `/cs:gc-review <plan>`
The General Counsel lens. Six questions before any contract, term sheet, IP move, or regulatory commitment. This is a lane gstack has zero of — and one where a single missed clause costs more than a year of engineering.
> ⚠️ **Not legal advice.** This command surfaces the right questions to ask before talking to outside counsel. Always engage qualified counsel for binding decisions.
**Who owns the IP being created or shared in this transaction?**
**What's the liability cap, and what's carved out from it?**
**What personal data is involved, and is a DPA in place?**
**What's the termination right, what's the notice period, and what's auto-renew?**
**Does this expose the company to a new regulatory regime?**
**If this is a hire or contractor: jurisdiction, classification, equity grant, IP assignment?**
1. Read the contract / term sheet end to end 2. Run the six questions 3. Identify the top-3 issues that need outside counsel review 4. Apply the verdict
# GC Review: <plan> **Date:** YYYY-MM-DD ## Document - Type: <contract / term sheet / grant / DPA> - Counterparty: <name> - $ value or scope: <amount> ## Issues | # | Issue | Risk | Recommendation | |---|---|---|---| | 1 | <e.g., uncapped IP indemnity> | HIGH | Cap at fees paid, mutual | | 2 | <e.g., 5-year auto-renew> | MED | 1-year max, 60-day notice | | 3 | <e.g., no DPA, EU data> | HIGH | Require DPA before sign | ## Regulatory Trigger - New regime triggered? <yes/no> - Specific frameworks: <HIPAA / GDPR / etc.> ## Outside Counsel Action Items - [ ] <specific item 1> - [ ] <specific item 2> - [ ] <specific item 3> ## Verdict 🟢 SIGN AS-IS (rare) 🟡 NEGOTIATE — counter on top-3 issues 🔴 DO NOT SIGN — material risk
Since v2.5.1, this command is backed by a full skill at `../../../c-level-advisor/skills/general-counsel-advisor/` with two Python tools:
# Automated contract scan (12 founder-killer patterns) python ../../../c-level-advisor/skills/general-counsel-advisor/scripts/contract_risk_scanner.py path/to/contract.txt # Term sheet scoring (0-100 founder-friendliness) python ../../../c-level-advisor/skills/general-counsel-advisor/scripts/term_sheet_analyzer.py path/to/term_sheet.json
The `cs-general-counsel-advisor` agent orchestrates both tools plus 3 references (contracts playbook, IP + regulatory, term sheet decoder).
---
**Version:** 1.0.0
388 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents.
Repo: alirezarezvani/claude-skills
Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a…
Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader),…
Phase 1 of building a Claude Managed Agent — interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table +…
Phase 4 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven…
Phase 2 of building a Claude Managed Agent — turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch…
Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2…