Pii Contract Analyze
gregmos/PII-Shield
Universal legal document processor with PII anonymization. An agent skill from gregmos/PII-Shield.
A skill your agent uses when the user uploads or pastes a Software-as-a-Service Master Services Agreement (MSA), Master Subscription Agreement, SaaS Agreement, or Cloud Services Agreement and asks…
$ npx skills add LegalQuants/lq-ai --skill msa-review-saas -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LegalQuants/lq-ai msa-review-saas --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LegalQuants/lq-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/msa-review-saas .claude/skills/msa-review-saas && rm -rf skills-srcUse ~/.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/
Install the "msa-review-saas" agent skill from https://github.com/LegalQuants/lq-ai/tree/main/skills/msa-review-saas into .claude/skills/msa-review-saas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "msa-review-saas", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LegalQuants/lq-ai/tree/main/skills/msa-review-saasType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LegalQuants/lq-ai --skill msa-review-saas -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LegalQuants/lq-ai msa-review-saas --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LegalQuants/lq-ai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/msa-review-saas .agents/skills/msa-review-saas && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "msa-review-saas" agent skill from https://github.com/LegalQuants/lq-ai/tree/main/skills/msa-review-saas into .agents/skills/msa-review-saas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "msa-review-saas", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LegalQuants/lq-ai --skill msa-review-saas -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LegalQuants/lq-ai msa-review-saas --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LegalQuants/lq-ai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/msa-review-saas .cursor/skills/msa-review-saas && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "msa-review-saas" agent skill from https://github.com/LegalQuants/lq-ai/tree/main/skills/msa-review-saas into .cursor/skills/msa-review-saas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "msa-review-saas", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LegalQuants/lq-ai.git --path skills/msa-review-saas--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LegalQuants/lq-ai --skill msa-review-saas -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LegalQuants/lq-ai msa-review-saas --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LegalQuants/lq-ai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/msa-review-saas .gemini/skills/msa-review-saas && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "msa-review-saas" agent skill from https://github.com/LegalQuants/lq-ai/tree/main/skills/msa-review-saas into .gemini/skills/msa-review-saas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "msa-review-saas", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LegalQuants/lq-ai msa-review-saasInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LegalQuants/lq-ai --skill msa-review-saas -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LegalQuants/lq-ai.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/msa-review-saas .github/skills/msa-review-saas && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "msa-review-saas" agent skill from https://github.com/LegalQuants/lq-ai/tree/main/skills/msa-review-saas into .github/skills/msa-review-saas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "msa-review-saas", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LegalQuants/lq-ai --skill msa-review-saas -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LegalQuants/lq-ai msa-review-saas --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LegalQuants/lq-ai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/msa-review-saas .opencode/skills/msa-review-saas && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "msa-review-saas" agent skill from https://github.com/LegalQuants/lq-ai/tree/main/skills/msa-review-saas into .opencode/skills/msa-review-saas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "msa-review-saas", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
msa-review-saasA skill your agent uses when the user uploads or pastes a Software-as-a-Service Master Services Agreement (MSA), Master Subscription Agreement, SaaS Agreement, or Cloud Services Agreement and asks…
Msa Review SaaS is an agent skill from LegalQuants/lq-ai. Use when the user uploads or pastes a Software-as-a-Service Master Services Agreement (MSA), Master Subscription Agreement, SaaS Agreement, or Cloud Services Agreement and asks for review, redline, risk assessment, or recommendation on whether to sign. Conducts a structured review of MSA framework terms (liability, indemnification, IP, data protection, warranties, term and termination, payment, and others), calibrated to the user's perspective (vendor or customer), with severity-rated findings, redline language…
Its SKILL.md is about 5.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files (for example `examples/example_customer_review.md`, `examples/example_vendor_review.md` and `reference/issue_checklist.md`).
It sits in Legal & Compliance, covering Contract review and Privacy and GDPR. The repository describes itself as: Open-source AI for legal teams. Bring your own keys, run it where you want, own your data. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit d185a62. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Msa Review SaaS loads about 5.3k tokens when it runs. Until then it costs about 165 tokens; SKILL.md has 1,871 words of instructions outside code blocks.
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.
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.
The full file from LegalQuants/lq-ai at commit d185a62, republished under its Apache-2.0 licence (© LegalQuants). 1,871 words, ~5,269 tokens.
.claude/skills/msa-review-saas/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.Conduct a structured review of a SaaS Master Services Agreement from the user's stated perspective and produce a report that an in-house lawyer can act on without redoing the analysis. The output is a draft for human review, not a final word; treat it accordingly.
This skill is calibrated to commercial-grade SaaS MSAs. It is not designed for: enterprise software license agreements (perpetual licenses), professional services agreements without a software component, hosted-but-not-SaaS arrangements (managed hosting, IaaS), or government / public-sector SaaS contracts (which have additional FedRAMP, FAR, and procurement-specific overlays).
Apply when the user provides a SaaS MSA, Master Subscription Agreement, SaaS Agreement, Cloud Services Agreement, or substantively similar instrument and asks for review or redline guidance. The user's perspective — vendor or customer — fundamentally changes the analysis; require it before proceeding if not supplied.
Do not apply this skill to:
order_form input) or via a dedicated Order Form Review skill (deferred — see DE-070).The skill requires the document and perspective. If perspective is not provided:
"Before I review, which side are you on? Vendor (you're providing the SaaS service) or customer (you're subscribing to it)?"
Optional inputs refine the analysis:
review_depth controls thoroughness. Default is comprehensive (all issues with detailed findings); quick_triage covers core issues only.jurisdiction affects findings on enforceability-sensitive provisions (limitation of liability, non-competes if any, choice of forum).deal_context changes severity calibration. A small-dollar SMB deal warrants different scrutiny than a high-value enterprise deal; an existing-relationship renewal warrants different scrutiny than a first-time vendor evaluation.order_form triggers MSA-vs-Order-Form conflict analysis (Pass 6, below).prior_agreements triggers conflict-with-prior-agreement analysis.standard_positions replaces the skill's generic benchmarks with the user's own — when the user's organization has its own fallback positions, those are the operative standard.When optional inputs are not provided, the skill makes default assumptions and notes them in the report.
Produce the review in six passes. Earlier passes inform later ones; do not collapse them.
Before substantive review:
Walk through the standard SaaS MSA issue checklist in reference/issue_checklist.md. The checklist groups issues into four tiers:
comprehensive and quick_triage): liability, indemnification, IP and data ownership, data protection (DPA reference), warranties and disclaimers, term and termination, payment, key SLAs.comprehensive only: confidentiality, assignment, governing law and venue, dispute resolution, force majeure, change-of-terms mechanics, suspension and acceleration rights, professional services scope, third-party components.comprehensive only: notice mechanics, integration / entire-agreement, amendment requirements, severability, waiver, counterparts, electronic signatures, definitions completeness, headings.For each item, classify:
Read every Tier 1 finding through the user's perspective lens (reference/perspective_lens.md). The same provision reads very differently from each side:
For each Tier 1 finding, identify which side the provision favors and by how much. For "present but unusual" findings, characterize the deviation: favorable / unfavorable / extreme.
Beyond standard issues, look for provisions that create operational risk regardless of perspective. The full list is in reference/red_flags.md; key categories:
If prior_agreements was provided, examine the document for:
If prior_agreements was not provided, this pass is skipped.
If order_form was provided, examine the Order Form against the MSA. Common conflicts:
The general interpretive rule (in most SaaS MSAs) is that Order Form-specific terms override MSA framework terms for that order; verify the MSA's "order of precedence" or "conflict" provision and apply it. If no conflict provision exists, flag — that itself is a deficiency.
If order_form was not provided, this pass is skipped.
Compile findings from prior passes into the report structure (see Output section). Calibrate severity using reference/severity_rubric.md. Cite specific section/clause numbers for every finding.
Produce the report in markdown with this structure (long, but proportional to the document — clean MSAs produce shorter reports; problematic MSAs produce longer ones):
# MSA Review — SaaS: [Document name or counterparty]
**Perspective:** [vendor | customer]
**Review depth:** [comprehensive | quick_triage]
**Document type:** [SaaS MSA | Master Subscription Agreement | Cloud Services Agreement | etc.]
**Governing law:** [jurisdiction or "not specified"]
**Term:** [duration / renewal mechanism summary]
**Order Form provided:** [yes / no]
**Prior agreements considered:** [list or "none"]
## Bottom line
[Two to four sentences. State the overall posture (favorable / balanced / unfavorable / materially unfavorable to user). State whether it is signable as-is, signable with minor edits, requires negotiation, or should be rejected. Identify the single most important issue.]
## Critical issues
[Issues rated "critical." Each has its own subsection with: clause reference, what the document says (verbatim quote where short enough), why it's a problem from the user's perspective, suggested redline language. Omit this section if there are no critical issues.]
## Material issues
[Issues rated "material." Same subsection structure.]
## Minor issues and observations
[Issues rated "minor" or items that are present-and-standard but worth noting. May be a bulleted list rather than full subsections. In quick_triage mode, this section is brief; in comprehensive mode, it covers Tier 2 and Tier 3 issues that did not warrant detailed treatment.]
## Missing standard protections
[Standard SaaS MSA elements that are absent and should be added. Each with suggested language or a reference.]
## Operational red flags
[Items from Pass 4 — even where they don't rise to critical/material, the user should be aware.]
## Conflicts with Order Form
[If Order Form was provided. Each identified conflict with: what the MSA says, what the Order Form says, which controls per the order-of-precedence provision, and the operative effect. Omit this section entirely if no Order Form was provided.]
## Conflicts with prior agreements
[If prior_agreements was provided. Each identified conflict similar to above. Omit if not applicable.]
## Recommended next steps
[Short bulleted list. Common options: sign as-is, sign with the redlines proposed above, send back with negotiation, escalate specific issues to outside counsel, decline to proceed.]
## Items requiring human judgment
[Items the skill cannot resolve and that need the user's business judgment or jurisdiction-specific expertise.]In quick_triage mode, the "Minor issues and observations" and "Missing standard protections" sections are condensed; the focus is Tier 1 issues with full treatment. In comprehensive mode, all sections are populated.
If the document is signable as-is or with only minor changes, the report should be short. Do not pad. A two-page report on a clean MSA is correctly two pages; do not stretch it to ten.
reference/issue_checklist.md — the full SaaS MSA issue checklist organized by tier.reference/perspective_lens.md — how to read each provision through vendor or customer eyes.reference/red_flags.md — operational and red-flag list used in Pass 4.reference/severity_rubric.md — the rubric for rating issues critical, material, minor.examples/example_customer_review.md — worked example: customer reviewing a vendor-prepared SaaS MSA.examples/example_vendor_review.md — worked example: vendor reviewing a customer-prepared MSA template.© LegalQuants, 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
SKILL.md and 7 other files in skills/msa-review-saas of LegalQuants/lq-ai.
Open the folder on GitHubat commit d185a62
Msa Review SaaS 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Msa Review SaaS this skillLegalQuants/lq-ai | 150 | — | ~5.3k | Automated safety check: Pass | Apache-2.0 | |
| Pii Contract Analyzegregmos/PII-Shield | 150 | — | ~8.9k | Automated safety check: Notes | MIT | |
| Turkish Commercial Contract ReviewZekaiSuni/claude-for-legal-turkish | 107 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Contract And Proposal Writeralirezarezvani/claude-skills | 28k | 2 repos | ~3.4k | Automated safety check: Pass | MIT | |
| General Counsel Advisoralirezarezvani/claude-skills | 28k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Canned Responses Anthropiclawve-ai/awesome-legal-skills | 847 | 1 repos | ~2.9k | Automated safety check: Pass | Apache-2.0 |
gregmos/PII-Shield
Universal legal document processor with PII anonymization. An agent skill from gregmos/PII-Shield.
ZekaiSuni/claude-for-legal-turkish
Reviews vendor agreements, NDAs, SaaS subscriptions and amendments under a Turkish-law commercial playbook, routing to specialist skills and merging the results into one memo.
alirezarezvani/claude-skills
Generate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs.
alirezarezvani/claude-skills
General Counsel advisory for startups: contract review (MSA, SaaS, NDA, DPA, employment), IP strategy, term sheet decoding, and regulatory landscape mapping.
lawve-ai/awesome-legal-skills
Generate templated responses for common legal inquiries and identify when situations require individualized attention.
lawve-ai/awesome-legal-skills
Audits a legal document against legal design principles. An agent skill from lawve-ai/awesome-legal-skills.
LegalQuants/lq-ai
A skill your agent uses when the user provides a client alert, regulatory bulletin, law firm memo, or similar legal update and wants the time-sensitive action items, deadlines, and obligations…
LegalQuants/lq-ai
A skill your agent uses when the user asks to find, read, or cite U.S.
LegalQuants/lq-ai
A skill your agent uses when the user has a piece of legal-jargon-heavy text and wants it rewritten in plain language for a specified non-legal audience.
LegalQuants/lq-ai
A skill your agent uses when the user has a contract loaded and asks a specific question about it — what a clause means, where something is addressed, whether a term is unusual, how a provision…
LegalQuants/lq-ai
A skill your agent uses when the user wants to compare the same handful of terms across N contracts side-by-side in a grid — what is the term, survival period, carveouts, and governing law in each…
LegalQuants/lq-ai
A skill your agent uses when the user provides a Data Processing Agreement, Data Processing Addendum, or HIPAA Business Associate Agreement and asks whether it contains the terms required under the…
Categories
A skill your agent uses when the user uploads or pastes a Software-as-a-Service Master Services Agreement (MSA), Master Subscription Agreement, SaaS Agreement, or Cloud Services Agreement and asks…. Msa Review SaaS is an agent skill from LegalQuants/lq-ai. Use when the user uploads or pastes a Software-as-a-Service Master Services Agreement (MSA), Master Subscription Agreement, SaaS Agreement, or Cloud Services Agreement and asks for review, redline, risk assessment, or recommendation on whether to sign.
Msa Review SaaS fits situations like: the user uploads; pastes a Software-as-a-Service Master Services Agreement (MSA); master Subscription Agreement; cloud Services Agreement and asks for review.
Run `npx skills add LegalQuants/lq-ai --skill msa-review-saas -a claude-code`. Or copy the skill folder (skills/msa-review-saas in LegalQuants/lq-ai) into .claude/skills/msa-review-saas in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LegalQuants/lq-ai --skill msa-review-saas -a codex`. Or copy the skill folder (skills/msa-review-saas in LegalQuants/lq-ai) into .agents/skills/msa-review-saas in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LegalQuants/lq-ai --skill msa-review-saas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/msa-review-saas, .gemini/skills/msa-review-saas, .github/skills/msa-review-saas and .opencode/skills/msa-review-saas in your project.
SKILL.md names no scripts, command-line tools or credentials: Msa Review SaaS is instructions for the agent only.
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.
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.
Msa Review SaaS 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.
About 5.3k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Msa Review SaaS: Pii Contract Analyze (gregmos/PII-Shield, 150 stars), Turkish Commercial Contract Review (ZekaiSuni/claude-for-legal-turkish, 107 stars), Contract And Proposal Writer (alirezarezvani/claude-skills, 28k stars) and General Counsel Advisor (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LegalQuants (a GitHub organization) maintains it in LegalQuants/lq-ai, which has 150 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 11, 2026.
Source: LegalQuants/lq-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.