Legal Writing MethodologySAFE
Overview
An agent skill published by revfactory.
459e1bb8f76eOBSERVED · 2026-10-12What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
```markdown --- name: legal-writing-methodology description: "Professional methodology for drafting legal opinions and strategy reports. The 'opinion-writer' and 'strategy-advisor' agents must utilize the document structure, argumentation techniques, and citation formats in this skill when drafting legal opinions or formulating strategies. Used for 'legal opinion drafting', 'legal document structure', 'argumentation methods', etc. Note: case law research and legal doctrine analysis are outside the scope of this skill." --- # Legal Writing Methodology Professional structure and argumentation techniques for legal opinions and strategy reports. ## Standard Legal Opinion Structure ### Official Opinion Template ```markdown # Legal Opinion **To**: [Client/Department] **From**: [Author] **Date**: [YYYY.MM.DD] **Re**: [Matter/Issue Title] **Document No.**: LO-[YYYY]-[Sequence] --- ## I. Issue Presented [Clearly state the client's legal question] ## II. Statement of Facts [Organize the facts underlying the analysis, in chronological or thematic order] ※ Unverified facts should be noted as "assumed to be ~" ## III. Analysis ### 1. Issue [1]: [Issue Name] #### a. Applicable Law [Relevant statutory provisions + commentary] #### b. Relevant Case Law [Key cases + extracted legal principles] #### c. Analysis [Analysis using the IRAC method] #### d. Sub-Conclusion [Conclusion on this issue] ### 2. Issue [2]: [Issue Name] [Repeat same structure] ## IV. Overall Opinion [Overall conclusion + level of certainty + risk summary] ## V. Recommendations 1. [Immediate action items] 2. [Medium-term action items] 3. [Items requiring caution] ## VI. Disclaimer This opinion is a legal review based on the facts presented and current applicable law, and does not constitute legal advice. Please consult a qualified attorney before making any final decisions. ``` ## Argumentation Techniques ### Deductive Reasoning ``` Major Premise: [Legal Rule] "If ~, then ~" (Civil Code § 750) Minor Premise: [Fact] "In this case, the defendant ~" Conclusion: "Therefore, the defendant is obligated to ~" ``` ### Analogical Reasoning ``` Precedent Facts: [Facts from Case A] Precedent Holding: [Court's ruling in Case A] Similarity: [Key similarities to the present case] Distinctions: [Why differences do not affect the conclusion] Conclusion: "The legal principle from Case A applies to the present case" ``` ### Policy Argument ``` Current Doctrine: [Current interpretation/application] Problem: [Limitations of the current interpretation] Alternative Interpretation: [Proposed interpretation] Policy Justification: [Social validity, legislative intent] ``` ## Citation Formats ### Case Citation ``` Supreme Court, May 15, 2023, Case No. 2022Da12345 Seoul High Court, Aug. 10, 2022, Case No. 2021Na67890 Constitutional Court, Mar. 20, 2023, Case No. 2022HeonMa123 ``` ### Statutory Citation ``` Civil Code § 750 (Content of Unlawful Acts) Personal Information Protection Act § 15(1)(1) Enforcement Decree of the Labor Standards Act § 12 ``` ### Literature Citation ``` [Author], "[Title of Article/Book]", [Publisher/Journal], [Year], [Page(s)] Example: Kim Sang-yong, "Law of Obligations — Special Part", Hwasan Media, 2023, p. 205 ``` ## Risk Response Strategy Framework ### Strategy Options Comparison Table ```markdown | Option | Litigation | Mediation/Arbitration | Negotiation | Avoidance | |--------|------------|-----------------------|-------------|-----------| | Expected Duration | 1–3 years | 3–6 months | 1–3 months | Immediate | | Expected Cost | High | Medium | Low | None | | Win Probability | [%] | - | - | - | | Confidentiality | Not possible | Possible | Possible | - | | Precedential Effect | Yes | No | No | - | | Enforceability | Strong | Medium | Weak | - | | Relationship Impact | Destructive | Neutral | Preserved | Preserved | ``` ### Cost-Benefit Analysis ``` Expected Value of Litigation = (Win Probability × Award Amount) - (Litigation Costs + Opportunity Costs + Loss Risk) Decision Criteria: Expected Value > 0: Litigation worth considering Expected Value < 0: Prioritize negotiation/mediation Expected Value ≈ 0: Consider non-monetary factors (precedent, deterrence effect) ``` ## References - Refer to the Korean Bar Association opinion template - Detailed writing examples: see `references/legal-writing-examples.md` ```
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass.
459e1bb8f76efull audit observations/trust-audit/skill/revfactory__legal-writing-methodology.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 459e1bb8f76e | SAFE | B | 89 | first audit |
Questions
Is Legal Writing Methodology safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Legal Writing Methodology access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (459e1bb8f76e), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.