Tw Legal RAG
aa0101181514/tw-legal-rag
Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.
Statute and regulation interpretation framework. An agent skill from borghei/Claude-Skills.
$ npx skills add borghei/Claude-Skills --skill statute-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install borghei/Claude-Skills statute-analysis --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/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/legal/statute-analysis .claude/skills/statute-analysis && 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 "statute-analysis" agent skill from https://github.com/borghei/Claude-Skills/tree/main/legal/statute-analysis into .claude/skills/statute-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "statute-analysis", 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/borghei/Claude-Skills/tree/main/legal/statute-analysisType 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 borghei/Claude-Skills --skill statute-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install borghei/Claude-Skills statute-analysis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/legal/statute-analysis .agents/skills/statute-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "statute-analysis" agent skill from https://github.com/borghei/Claude-Skills/tree/main/legal/statute-analysis into .agents/skills/statute-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "statute-analysis", 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 borghei/Claude-Skills --skill statute-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install borghei/Claude-Skills statute-analysis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/legal/statute-analysis .cursor/skills/statute-analysis && 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 "statute-analysis" agent skill from https://github.com/borghei/Claude-Skills/tree/main/legal/statute-analysis into .cursor/skills/statute-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "statute-analysis", 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/borghei/Claude-Skills.git --path legal/statute-analysis--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 borghei/Claude-Skills --skill statute-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install borghei/Claude-Skills statute-analysis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/legal/statute-analysis .gemini/skills/statute-analysis && 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 "statute-analysis" agent skill from https://github.com/borghei/Claude-Skills/tree/main/legal/statute-analysis into .gemini/skills/statute-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "statute-analysis", 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 borghei/Claude-Skills statute-analysisInstalls 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 borghei/Claude-Skills --skill statute-analysis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/legal/statute-analysis .github/skills/statute-analysis && 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 "statute-analysis" agent skill from https://github.com/borghei/Claude-Skills/tree/main/legal/statute-analysis into .github/skills/statute-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "statute-analysis", 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 borghei/Claude-Skills --skill statute-analysis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install borghei/Claude-Skills statute-analysis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/legal/statute-analysis .opencode/skills/statute-analysis && 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 "statute-analysis" agent skill from https://github.com/borghei/Claude-Skills/tree/main/legal/statute-analysis into .opencode/skills/statute-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "statute-analysis", 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.
statute-analysisStatute and regulation interpretation framework. An agent skill from borghei/Claude-Skills.
Statute Analysis is an agent skill from borghei/Claude-Skills. Statute and regulation interpretation framework. Use when reading statutes, classifying requirements, analyzing operative keywords, applying canons of construction, or mapping compliance obligations from legislative text.
Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/canons_of_construction.md`, `references/statutory_structure.md` and `scripts/requirement_classifier.py`).
It sits in Legal & Compliance, covering Legal research. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 4a698e8. 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.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom 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.
Statute Analysis loads about 4.5k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 1,883 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); the scripts in this folder are not scanned.
The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 1,883 words, ~4,541 tokens.
.claude/skills/statute-analysis/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.⚠️ EXPERIMENTAL — This skill is provided for educational and informational purposes only. It does NOT constitute legal advice. All responsibility for usage rests with the user. Consult qualified legal professionals before acting on any output.
Production-ready framework for reading, interpreting, and applying statutes, regulations, and rules. Covers the full lifecycle from identifying the legal hierarchy through extracting actionable requirements and mapping implementation obligations.
Understanding the source hierarchy is the foundation of statutory analysis.
| Source | Created By | Authority | Example |
|---|---|---|---|
| Constitution | Sovereign/people | Supreme | U.S. Constitution, EU Treaties |
| Statute | Legislature | Primary legislation | GDPR, Clean Air Act, AI Act |
| Regulation | Executive agency | Delegated authority | FDA 21 CFR, FTC rules |
| Rule | Agency or court | Procedural/interpretive | Federal Rules of Civil Procedure |
| Guidance | Agency | Non-binding, persuasive | FDA guidance documents, CNIL guides |
| Case law | Courts | Binding within jurisdiction | Supreme Court precedent |
Key principle: Higher sources override lower sources. Regulations cannot exceed statutory authority. Guidance cannot create new obligations not grounded in statute.
Before the analysis, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the analysis.
Before interpreting any statutory provision, complete these checks:
Scans statute text for operative keywords and classifies obligations, permissions, conditions, and exemptions.
# Analyze a statute file
python scripts/statute_keyword_analyzer.py --input statute.txt
# Analyze with JSON output
python scripts/statute_keyword_analyzer.py --input regulation.txt --json
# Analyze inline text
python scripts/statute_keyword_analyzer.py --text "The controller shall implement appropriate technical measures..."
# Save analysis report
python scripts/statute_keyword_analyzer.py --input statute.txt --output analysis.jsonClassifies statutory requirements by type, implementation team, enforcement mechanism, and penalty.
# Classify requirements from a JSON list
python scripts/requirement_classifier.py --input requirements.json
# Classify with JSON output
python scripts/requirement_classifier.py --input requirements.json --json
# Classify inline requirement
python scripts/requirement_classifier.py --text "Controllers must provide data subjects with a privacy notice at the point of collection"
# Generate implementation matrix
python scripts/requirement_classifier.py --input requirements.json --output matrix.jsonStatutory definitions control meaning. Pay attention to the verb used:
| Verb | Type | Meaning | Example |
|---|---|---|---|
| "means" | Exhaustive | The definition is complete; no other meaning applies | "'Personal data' means any information relating to an identified or identifiable natural person" |
| "includes" | Illustrative | The definition provides examples but is not limited to them | "'Processing' includes collection, recording, organization, structuring..." |
| "does not include" | Exclusion | Explicitly carves out items from scope | "'Consumer' does not include a natural person acting in a commercial or employment context" |
| "refers to" | Pointer | Incorporates an external definition | "'Harmonised standard' refers to a European standard as defined in Regulation (EU) No 1025/2012" |
| Keyword | Classification | Legal Effect |
|---|---|---|
| shall | Mandatory | Creates an obligation; must be done |
| must | Mandatory | Same as "shall" in modern drafting |
| may | Permissive | Creates permission; optional |
| may not | Prohibitive | Creates a prohibition |
| and | Conjunctive | All listed items required |
| or | Disjunctive | Any listed item sufficient |
| unless | Exception | Negates the rule when condition is met |
| except | Exception | Carves out specific items from the rule |
| subject to | Conditional | Rule applies but another provision modifies it |
| notwithstanding | Override | This provision prevails over conflicting provisions |
| provided that | Condition | Adds a requirement that must be satisfied |
| if...then | Conditional | Trigger condition and consequence |
| upon | Temporal trigger | Action required when event occurs |
This distinction determines whether ALL conditions must be met or ANY single condition suffices.
| Pattern | Reading | Practical Impact |
|---|---|---|
| "A, B, and C" | All three required | Must satisfy every element |
| "A, B, or C" | Any one sufficient | Satisfy any single element |
| "A, B, and/or C" | Ambiguous | Flag for clarification; analyze context |
| "both A and B" | Explicitly conjunctive | Must satisfy both |
| "either A or B" | Explicitly disjunctive | Satisfy one |
| Serial comma ambiguity | Context-dependent | Apply whole-act rule for consistency |
See references/canons_of_construction.md for the complete 12-canon reference.
| Canon | Core Rule | When to Apply |
|---|---|---|
| General-Terms Canon | General terms get general meaning | Default interpretation |
| Expressio Unius | Expressing one thing excludes others | Specific lists without catchall |
| Whole-Act Rule | Interpret provisions consistently | Apparent conflicts between sections |
| Consistent Usage | Same term = same meaning throughout | Term appears multiple times |
| Meaningful Variation | Different terms = different meanings | Similar but distinct terms used |
| Surplusage Canon | Every word has meaning; no redundancy | Tempted to treat words as surplus |
| Noscitur a Sociis | Words known by their associates | Ambiguous term in a list |
| Ejusdem Generis | General follows specific = limited | "...and other similar" patterns |
| Against Ineffectiveness | Prefer reading that gives effect | Two possible readings |
| Avoiding Absurdity | Reject absurd outcomes | Literal reading produces nonsensical result |
| Remedial Statutes | Construe liberally | Consumer protection, safety statutes |
| Rule of Lenity | Ambiguity favors the regulated party | Criminal or penalty provisions |
When statutory text is ambiguous, consult sources in this order:
| Priority | Source | Weight | Where to Find |
|---|---|---|---|
| 1 | Statutory text itself | Controlling | Official gazette, codified law |
| 2 | Definitions section | Controlling | Usually first articles/sections |
| 3 | Legislative purpose (recitals, preamble) | Strong | Preamble, "Whereas" clauses |
| 4 | Canons of construction | Strong | Legal treatises, case law |
| 5 | Case law interpreting the provision | Strong-to-moderate | Court databases |
| 6 | Agency regulations implementing statute | Moderate | Agency websites, CFR |
| 7 | Agency guidance and FAQs | Persuasive only | Agency websites |
| 8 | Legislative history | Weak (varies by jurisdiction) | Congressional record, Hansard |
| 9 | Academic commentary | Persuasive only | Legal journals |
Every statutory requirement maps to an implementation category:
| Type | Description | Typical Owner | Example |
|---|---|---|---|
| Disclosure | Information must be provided to someone | Legal / Compliance | Privacy notice requirements |
| Operational | Process or procedure must exist | Operations / Compliance | Record-keeping obligations |
| Technical | System capability or safeguard required | Engineering | Encryption, access controls |
| UI/Design | User interface must include specific elements | Product / Design | Consent mechanisms, opt-out buttons |
| Organizational | Governance structure or role required | Management / HR | Appointing a DPO, board oversight |
| Documentation | Written records must be maintained | Legal / Compliance | Impact assessments, audit trails |
| Reporting | Information must be submitted to authority | Legal / Compliance | Breach notification, annual reports |
When requirements from multiple jurisdictions apply:
For each statutory requirement, assess enforcement risk:
| Factor | Assessment Questions |
|---|---|
| Enforcement authority | Which agency enforces? How active are they? |
| Penalty types | Civil fines, criminal penalties, administrative sanctions? |
| Penalty severity | Fixed amounts, percentage of turnover, per-violation? |
| Cure periods | Is there a right to cure before penalties apply? |
| Private right of action | Can individuals sue for violations? |
| Enforcement history | Has this provision been actively enforced? |
| Regulatory guidance | Has the agency clarified enforcement priorities? |
| Guide | Path | Description |
|---|---|---|
| Canons of Construction | references/canons_of_construction.md | 12 canons with definitions, examples, and misapplication warnings |
| Statutory Structure | references/statutory_structure.md | How statutes are organized, effective dates, preemption, enforcement |
scripts/statute_keyword_analyzer.py on the full text.scripts/requirement_classifier.py on the extracted requirements.| Problem | Likely Cause | Resolution |
|---|---|---|
| Term not defined in statute | Legislature used ordinary meaning | Apply general-terms canon; check case law for judicial definitions |
| "And/or" ambiguity | Drafting imprecision | Check legislative history; apply whole-act rule; flag for legal review |
| Conflicting provisions | Later provision may override earlier | Check for "notwithstanding" clauses; apply later-in-time rule |
| Undefined threshold | Delegated to regulation | Check implementing regulations and agency guidance |
| Provision seems to have no effect | May be transitional or placeholder | Check effective dates and amendment history |
| Cross-reference to repealed section | Statute not updated after amendment | Check saving clauses; apply presumption against ineffectiveness |
| Criterion | Target |
|---|---|
| All defined terms cataloged | 100% of definitions section mapped |
| Obligations extracted | Every "shall/must" provision identified |
| Requirements classified | Each requirement has type, owner, enforcement, and priority |
| Cross-references resolved | No unresolved references remain |
| Enforcement risk assessed | Every material obligation has enforcement analysis |
| Implementation matrix complete | Requirements mapped to teams with timelines |
In scope: Reading and interpreting statutory text, extracting requirements, classifying obligations, applying canons of construction, mapping enforcement risk.
Out of scope: Providing legal advice, predicting court outcomes, drafting legislation, interpreting case law holdings, constitutional analysis.
Disclaimer: This skill provides a structured methodology for statutory analysis. It does not constitute legal advice. Always consult qualified legal counsel for binding interpretations.
| Anti-Pattern | Why It Fails | Better Approach |
|---|---|---|
| Reading a section in isolation | Statutes are interconnected; isolated reading misses cross-references, definitions, and scope limitations | Always read definitions, scope, and cross-referenced provisions before interpreting |
| Treating guidance as law | Agency guidance is non-binding and can change; building compliance solely on guidance creates risk | Use guidance to inform interpretation but anchor compliance to statutory text |
| Ignoring "what the statute doesn't say" | Silence can mean permission, delegation, or an oversight; assuming the statute covers everything leads to compliance gaps | Affirmatively check: does the statute address this scenario? If not, analyze why and what fills the gap |
| Applying one jurisdiction's interpretation to another | "Personal data" in GDPR is not identical to "personal information" in CCPA; cross-pollinating definitions creates errors | Analyze each statute independently using its own definitions and interpretive framework |
| Skipping the definitions section | Statutory definitions override ordinary meaning; missing them leads to fundamental misreadings | Always read the definitions section first, before any substantive analysis |
| Tool | Input | Output | Use Case |
|---|---|---|---|
statute_keyword_analyzer.py | Statute text file or inline text | Obligation/permission/exception map | First pass analysis of any legislative text |
requirement_classifier.py | List of requirements (text or JSON) | Implementation matrix with types, teams, enforcement | Converting statutory obligations to actionable implementation tasks |
© borghei, MIT. 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 4 other files (scripts, references) in legal/statute-analysis of borghei/Claude-Skills.
Open the folder on GitHubat commit 4a698e8
Statute Analysis 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 |
|---|---|---|---|---|---|---|
| Statute Analysis this skillborghei/Claude-Skills | 881 | — | ~4.5k | Automated safety check: Pass | MIT | |
| Tw Legal RAGaa0101181514/tw-legal-rag | 327 | — | ~580 | Automated safety check: Pass | Custom licence | |
| Design Award SearchSeanJ1ang/design-judge-skills | 712 | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| China Lawyer AnalystCSlawyer1985/china-lawyer-analyst | 194 | — | ~3.3k | Automated safety check: Pass | None | |
| Billing And Litigation BudgetTHUYRan/Legal-Skills-Chinese | 868 | — | ~5k | Automated safety check: Pass | None | |
| Hard Predict Futuredavepoon/buildwithclaude | 3.6k | 1 repos | ~4.2k | Automated safety check: Pass | MIT |
aa0101181514/tw-legal-rag
Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.
SeanJ1ang/design-judge-skills
Find and verify award-winning designs in the same or adjacent functional category through eight explicit relevance dimensions: problem and user, core function, sensing technology, intervention…
CSlawyer1985/china-lawyer-analyst
通过中国法律视角分析事件,运用成文法解释、指导案例参照、请求权基础分析等方法, 理解权利义务、评估责任风险、识别法律依据并推荐合规策略。
THUYRan/Legal-Skills-Chinese
A skill your agent uses when the user needs to track or manage attorney hours, expert fees, and investigation costs; control litigation spend; or prepare timesheets or expense statements for clients.
davepoon/buildwithclaude
Activate this agent for any future-oriented question that requires deep quantitative analysis, historical precedents, and structured scenario planning.
Golden2002/legal-research-skill
中国法律全领域系统性检索专家. An agent skill from Golden2002/legal-research-skill.
borghei/Claude-Skills
Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.
borghei/Claude-Skills
Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.
borghei/Claude-Skills
Idea to AI-generated prototype to customer validation to engineering handoff.
borghei/Claude-Skills
Analytics engineering across data modeling, dbt, transformation, and semantic layers.
borghei/Claude-Skills
Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.
borghei/Claude-Skills
OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.
Categories
Statute and regulation interpretation framework. An agent skill from borghei/Claude-Skills. Statute Analysis is an agent skill from borghei/Claude-Skills. Statute and regulation interpretation framework.
Statute Analysis fits situations like: reading statutes; classifying requirements; analyzing operative keywords; applying canons of construction.
Run `npx skills add borghei/Claude-Skills --skill statute-analysis -a claude-code`. Or copy the skill folder (legal/statute-analysis in borghei/Claude-Skills) into .claude/skills/statute-analysis in your project. Claude Code loads it when a task matches its description.
Run `npx skills add borghei/Claude-Skills --skill statute-analysis -a codex`. Or copy the skill folder (legal/statute-analysis in borghei/Claude-Skills) into .agents/skills/statute-analysis 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 borghei/Claude-Skills --skill statute-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/statute-analysis, .gemini/skills/statute-analysis, .github/skills/statute-analysis and .opencode/skills/statute-analysis in your project.
Going by SKILL.md and its folder, Statute Analysis needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Statute Analysis is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Statute Analysis: Tw Legal RAG (aa0101181514/tw-legal-rag, 327 stars), Design Award Search (SeanJ1ang/design-judge-skills, 712 stars), China Lawyer Analyst (CSlawyer1985/china-lawyer-analyst, 194 stars) and Billing And Litigation Budget (THUYRan/Legal-Skills-Chinese, 868 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 881 GitHub stars. The repository holds 349 skills in this directory. The repository was last updated on October 7, 2026.
Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.