AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Review

skill-anylegal-ai-anylegal-oss-review · by anylegal-ai

Review a document against playbook positions. Analyze clauses for risks, flag issues, suggest specific changes, and apply edits. Subsumes redlining — review + fix is one workflow.

No reviews yet
0 installs
30 views
0.0% view→install

Install

$ agentstack add skill-anylegal-ai-anylegal-oss-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-anylegal-ai-anylegal-oss-review)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Contract Review

When to Use

Use this skill when:

  • The user asks to review a contract or document
  • The user wants a risk assessment or issue-spotting pass
  • The user says /review
  • The user asks to "check", "flag", "audit", or "assess" a document
  • The user asks to review and then apply changes (review + redline is one flow)

Process

  1. Identify which document to review — Check the "Active document" in your context. If the active document is a contract/agreement in the workspace documents list, review it. If the active document is an instructions file, playbook, template, or other non-contract file (or if no document is active), ask the user which document they want reviewed. List the available workspace documents and let them pick.
  2. Read the document via read_document — always read the full document first
  3. Read the relevant playbook(s) — check the "Available Playbooks" manifest in your context, then call read_document("Playbook/") to load the one(s) relevant to this contract type, jurisdiction, or client
  4. Research jurisdiction-specific requirements — identify the governing law from the contract, then:
  • Use web_search with the jurisdiction set to find relevant statutes and regulations for the contract type
  • Use web_fetch to retrieve full statutory text from authoritative sources (government domains, official gazettes)
  • Cross-reference: for any cited statute, run a follow-up search to verify it is current and not superseded
  • Use web_search for case law, regulatory guidance, and market standards (recent enforcement trends, standard market positions for the industry)
  1. Analyze each key clause:
  • Identify clause type (indemnification, limitation of liability, termination, etc.)
  • Assess position: favorable, balanced, or unfavorable for the represented party
  • Determine risk level: low, medium, high, or critical
  • Check alignment with playbook positions
  • Flag any clauses that conflict with mandatory statutory requirements — cite the exact source URL retrieved via web_fetch
  • Use web_search to check market standards if the clause deviates from typical positions
  • Consider market standards and jurisdiction-specific requirements
  1. Present findings in structured format with specific recommendations
  2. If user asks to apply changes ("redline", "implement", "apply", "do it"):
  • Invoke Skill(skill="docx-editing") for the full edit-pattern library, then call edit_document for each change. Edit the document in place — do not clone to a _v2 copy.
  • Copy the EXACT text span from the document — do not paraphrase or reconstruct from memory. Use the shortest unique snippet for old_text.
  • edit_document emits ` / tracked-change markup automatically. Author defaults to "Anylegal.ai"` — pass an explicit author only if the user supplies a different name.
  • Do NOT just describe changes — actually call edit_document for each one.
  • Do NOT use run_code for text edits.

Output Format

Provide analysis as:

  • Executive Summary: Overall risk level, key concerns, recommendation (proceed / negotiate / reject)
  • Clause-by-Clause Analysis: For each significant clause:
  • Clause reference and type
  • Current position and risk level
  • Playbook alignment (if playbook available)
  • Specific recommendation with suggested replacement language
  • Statutory Compliance: Any mandatory requirements from the governing jurisdiction that the contract must meet, with citations to authoritative sources
  • Priority Actions: Top 3-5 items to negotiate first

Risk Levels

  • low: Standard language, well-balanced, no significant exposure
  • medium: Some deviation from market standard, limited exposure
  • high: Significant exposure, one-sided provisions, should be negotiated
  • critical: Unacceptable risk, deal-breaker if not changed

Guidelines

  • Always consider the full document context, not just isolated clauses
  • Check for related clauses that may mitigate or compound risks
  • Reference specific clause numbers
  • Consider the contract type and industry context
  • When playbook positions exist, clearly indicate alignment or deviation
  • Be specific in recommendations — draft actual replacement language
  • If the user asks to "implement" or "apply" changes, invoke Skill(skill="docx-editing") and call edit_document for each change. Edit in place. Copy EXACT text from the document — never from memory.
  • Proactively research — don't just rely on your training data for legal requirements. Use web_search and web_fetch against authoritative jurisdiction-specific sources to verify statutory requirements. Cite source URLs when flagging compliance issues.
  • When flagging a statutory requirement, retrieve and quote the exact provision text from an authoritative source so you can cite it precisely.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.