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.
ARA World Model — read-only reasoning engine over ONE Agent-Native Research Artifact (ARA), run LOCALLY with the coding agent itself as the LLM (no SDK, no API key).
Install Research Foresight
$ npx skills add ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ARA-Labs/Agent-Native-Research-Artifact research-foresight --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/ARA-Labs/Agent-Native-Research-Artifact.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/research-foresight .claude/skills/research-foresight && 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 "research-foresight" agent skill from https://github.com/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-foresight into .claude/skills/research-foresight/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-foresight", 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/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-foresightType 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 ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ARA-Labs/Agent-Native-Research-Artifact research-foresight --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-Artifact.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/research-foresight .agents/skills/research-foresight && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "research-foresight" agent skill from https://github.com/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-foresight into .agents/skills/research-foresight/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-foresight", 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 ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ARA-Labs/Agent-Native-Research-Artifact research-foresight --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-Artifact.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/research-foresight .cursor/skills/research-foresight && 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 "research-foresight" agent skill from https://github.com/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-foresight into .cursor/skills/research-foresight/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-foresight", 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/ARA-Labs/Agent-Native-Research-Artifact.git --path skills/research-foresight--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 ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ARA-Labs/Agent-Native-Research-Artifact research-foresight --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-Artifact.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/research-foresight .gemini/skills/research-foresight && 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 "research-foresight" agent skill from https://github.com/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-foresight into .gemini/skills/research-foresight/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-foresight", 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 ARA-Labs/Agent-Native-Research-Artifact research-foresightInstalls 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 ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-Artifact.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/research-foresight .github/skills/research-foresight && 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 "research-foresight" agent skill from https://github.com/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-foresight into .github/skills/research-foresight/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-foresight", 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 ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ARA-Labs/Agent-Native-Research-Artifact research-foresight --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-Artifact.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/research-foresight .opencode/skills/research-foresight && 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 "research-foresight" agent skill from https://github.com/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-foresight into .opencode/skills/research-foresight/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-foresight", 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.
Facts
- Skill name
research-foresight- GitHub stars
- 691
- Token cost
- ~626 tokens
- SKILL.md length
- 182 words
- Files
- 4 (incl. references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
ARA World Model — read-only reasoning engine over ONE Agent-Native Research Artifact (ARA), run LOCALLY with the coding agent itself as the LLM (no SDK, no API key).
- Works in 2 steps: Retrieve — adopt references/RETRIEVE.md.… → Answer — adopt references/PREDICT.md.…
- Tasks that involve Legal research
- SKILL.md covers Inputs and Procedure
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Research Foresight is an agent skill from ARA-Labs/Agent-Native-Research-Artifact. ARA World Model — read-only reasoning engine over ONE Agent-Native Research Artifact (ARA), run LOCALLY with the coding agent itself as the LLM (no SDK, no API key). Given an ARA directory and a free-text query, it answers any question about the ARA — a forward "what if I change X", but equally why-did-this-work, what-should-I-try, is-this-sound, how-do-these-compare, or anything else — by retrieving precedent from the ARA's native files (references/RETRIEVE.md) and answering as the Predictor…
Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/CONTRACT.md`, `references/PREDICT.md` and `references/RETRIEVE.md`).
It sits in Legal & Compliance, covering Legal research. The repository describes itself as: Research Artifact Protocol for Rigorous and Trustworthy AI Scientists. The licence is MIT.
When your agent uses it
- Tasks that involve Legal research
Example prompts
- “what if I change X”
- “/research-foresight”
Requirements
- Pre-approved tools (allowed-tools): Read, Grep, Glob
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Retrieve — adopt references/RETRIEVE.md. Read it now and follow it exactly against
- Answer — adopt references/PREDICT.md. Read it now and follow it exactly, consuming the
What it can do on your machine
Read from SKILL.md and the folder at commit e52a925. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlob
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Research Foresight loads about 626 tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 221 tokens; SKILL.md has 182 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from ARA-Labs/Agent-Native-Research-Artifact at commit e52a925, republished under its MIT licence (© ARA-Labs). 182 words, ~626 tokens.
Download SKILL.mdSave it as
.claude/skills/research-foresight/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- research-foresight
- description
- ARA World Model — read-only reasoning engine over ONE Agent-Native Research Artifact (ARA), run LOCALLY with the coding agent itself as the LLM (no SDK, no API key). Given an ARA directory and a free-text query, it answers any question about the ARA — a forward "what if I change X", but equally why-did-this-work, what-should-I-try, is-this-sound, how-do-these-compare, or anything else — by retrieving precedent from the ARA's native files (references/RETRIEVE.md) and answering as the Predictor (references/PREDICT.md): a bold, grounded, falsifiable Answer shaped to what the question actually calls for. TRIGGERS: ask the world model, wm predict, predict with the world model, what if I change X, forecast the loss curve, will this help, why did this work, what should I try next, is this claim sound, compare these, retrieve precedent, what precedent surfaces.
- allowed-tools
- Read, Grep, Glob
- metadata.author
- ara-commons
- metadata.category
- research-tooling
- metadata.version
- 1.1.0
- metadata.tags
- research, world-model, retrieval, prediction, grounded-answering
research-foresight — the ARA World Model
You (the coding agent) are the LLM that runs the engine — no SDK, no API key, no network call. The
engine is three reference contracts under this skill's references/ directory (quote every path;
it may contain spaces):
references/CONTRACT.md— the foundation both contracts bind to; if documents disagree, it wins.references/RETRIEVE.md— the Retriever: agentic search + semantic rank over the ARA's native files.references/PREDICT.md— the Predictor: grounded, honest answering of the question asked.
Inputs
From the user's message (or $ARGUMENTS): an <ara_dir> (the ARA in scope) and a free-text
query. If <ara_dir> turns out not to be an ARA (a plain paper, repo, or notes folder),
compile it into one first with /compiler <path>, then rerun this skill.
Procedure
- Retrieve — adopt
references/RETRIEVE.md. Read it now and follow it exactly against<ara_dir>. - Answer — adopt
references/PREDICT.md. Read it now and follow it exactly, consuming the retrieval from Step 1.
Render the answer prominently, then the honesty envelope (grounded_inference /
speculative_leap / basis / reasoning / confidence / confidence_reason / falsifiable).
The engine is read-only: read nothing outside <ara_dir> and this skill's references/; write
nothing anywhere.
© ARA-Labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in skills/research-foresight of ARA-Labs/Agent-Native-Research-Artifact.
- SKILL.md
- references/CONTRACT.md
- references/PREDICT.md
- references/RETRIEVE.md
Open the folder on GitHubat commit e52a925
Compare with similar skills
Research Foresight 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 |
|---|---|---|---|---|---|---|
| Research Foresight this skillARA-Labs/Agent-Native-Research-Artifact | 691 | — | ~626 | Automated safety check: Pass | MIT | |
| Tw Legal RAGaa0101181514/tw-legal-rag | 328 | — | ~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 | 196 | — | ~3.3k | Automated safety check: Pass | None | |
| Billing And Litigation BudgetTHUYRan/Legal-Skills-Chinese | 874 | — | ~5k | Automated safety check: Pass | None | |
| Legal Issue ResearchGolden2002/legal-research-skill | 156 | — | ~6.8k | Automated safety check: Pass | MIT |
Similar skills
Design Award Search
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…
China Lawyer Analyst
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。
Billing And Litigation Budget
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.
Legal Issue Research
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.
Tax Law Research
Serein-81/financial_rag
Searches current Chinese tax laws, rates and policy changes with Tavily web search, prioritizing government sources and flagging outdated or conflicting results.
More from ARA-Labs/Agent-Native-Research-Artifact
Research Fuzzer
ARA-Labs/Agent-Native-Research-Artifact
Treat an open-ended investigation the way a fuzzer treats a program.
Submit Ara
ARA-Labs/Agent-Native-Research-Artifact
ARA Submitter. An agent skill from ARA-Labs/Agent-Native-Research-Artifact.
Rigor Reviewer
ARA-Labs/Agent-Native-Research-Artifact
ARA Seal Level 2: Semantic Epistemic Review. An agent skill from ARA-Labs/Agent-Native-Research-Artifact.
Compiler
ARA-Labs/Agent-Native-Research-Artifact
Universal ARA Compiler. An agent skill from ARA-Labs/Agent-Native-Research-Artifact.
Research Manager
ARA-Labs/Agent-Native-Research-Artifact
End-of-turn research process recorder with progressive crystallization.
Related
Categories
Questions about Research Foresight
What does Research Foresight do?
ARA World Model — read-only reasoning engine over ONE Agent-Native Research Artifact (ARA), run LOCALLY with the coding agent itself as the LLM (no SDK, no API key). Research Foresight is an agent skill from ARA-Labs/Agent-Native-Research-Artifact. ARA World Model — read-only reasoning engine over ONE Agent-Native Research Artifact (ARA), run LOCALLY with the coding agent itself as the LLM (no SDK, no API key).
When should I use Research Foresight?
Research Foresight fits situations like: tasks that involve Legal research.
How do I install Research Foresight in Claude Code?
Run `npx skills add ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a claude-code`. Or copy the skill folder (skills/research-foresight in ARA-Labs/Agent-Native-Research-Artifact) into .claude/skills/research-foresight in your project. Claude Code loads it when a task matches its description.
How do I install Research Foresight in Codex?
Run `npx skills add ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a codex`. Or copy the skill folder (skills/research-foresight in ARA-Labs/Agent-Native-Research-Artifact) into .agents/skills/research-foresight in your project. Codex loads it when a task matches its description.
Can I use Research Foresight in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ARA-Labs/Agent-Native-Research-Artifact --skill research-foresight -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-foresight, .gemini/skills/research-foresight, .github/skills/research-foresight and .opencode/skills/research-foresight in your project.
What does Research Foresight need to run?
SKILL.md names no scripts, command-line tools or credentials: Research Foresight is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob.
Does Research Foresight access the network?
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.
Is Research Foresight safe to install?
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.
What licence does Research Foresight use?
Research Foresight is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Research Foresight use?
About 626 tokens (SKILL.md is roughly 2.5k 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 10k tokens, read only when the agent opens those files.
What are the alternatives to Research Foresight?
Skills that share tags, products or a category with Research Foresight: Tw Legal RAG (aa0101181514/tw-legal-rag, 328 stars), Design Award Search (SeanJ1ang/design-judge-skills, 712 stars), China Lawyer Analyst (CSlawyer1985/china-lawyer-analyst, 196 stars) and Billing And Litigation Budget (THUYRan/Legal-Skills-Chinese, 874 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Research Foresight?
ARA-Labs (a GitHub organization) maintains it in ARA-Labs/Agent-Native-Research-Artifact, which has 691 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.
Source: ARA-Labs/Agent-Native-Research-Artifact on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.