Install
$ agentstack add skill-anylegal-ai-anylegal-oss-compare ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Document Comparison
When to Use
Use this skill when:
- The user uploads two versions of the same document
- The user says /compare
- The user asks "what changed", "what's different", or "show me the differences"
- The user asks for a redline or tracked-changes document
- The user received a counterparty markup and wants to understand the changes
Process
- Identify the two documents — ask the user which is the original and which is the revised version if not clear
- Read both documents via
read_document - Run
comparewith both document paths or texts — this returns a structured diff, similarity percentage, and visual output - Analyze the differences:
- What was added, removed, or modified?
- Which changes are substantive vs. editorial?
- Are any changes risky or favorable?
- Do changes align with playbook positions (if available in context)?
- Present findings with a summary of key changes
- If user wants a Word redline — call
run_code(default Python) to generate a DOCX with tracked changes. Open the original with python-docx, compute a diff against the revised text, and insertw:ins/w:deltracked-change markup via lxml. See/docx-editingskill for OOXML tracked change patterns. Verify the output with structural checks.
Output Format
- Summary: Overall similarity %, number of changes, nature of changes (substantive vs. editorial)
- Key Changes: List of the most significant changes with assessment:
- What changed
- Why it matters (risk/benefit)
- Recommendation (accept / reject / negotiate)
- Full Change List: All detected changes in order
- Action Items: What to do next (accept, push back, request clarification)
Guidelines
- Always present the original vs. revised framing clearly
- Distinguish substantive changes (liability caps, notice periods, governing law) from editorial changes (formatting, numbering, defined terms)
- Prioritize substantive changes in the summary
- If playbook is available, flag changes that deviate from firm positions
- When producing a DOCX redline, confirm which direction the user wants (their changes tracked, or counterparty changes tracked)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: anylegal-ai
- Source: anylegal-ai/anylegal-oss
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.