Agent skill

Answer From Sources

by stella in stella/stella

Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim.

Apache-2.0Auto-check passedLegal & Compliance

Install Answer From Sources

skills CLI
$ npx skills add stella/stella --skill answer-from-sources -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install stella/stella answer-from-sources --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/stella/stella.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/skills/blueprints/answer-from-sources .claude/skills/answer-from-sources && rm -rf skills-src

Use ~/.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/

Facts

Skill name
answer-from-sources
GitHub stars
258
Token cost
~735 tokens
SKILL.md length
283 words
Files
4 (incl. references)
Skills in repo
24
Repo updated
First seen
Licence
Apache-2.0

At a glance

Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim.

  • Works in 5 steps: GDPR, the regulation text itself → CJEU case law interpreting it → EDPB guidelines and opinions → …
  • Questions about personal data
  • SKILL.md covers Input, Sources, Reasoning structure and Output rules, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Answer From Sources is an agent skill from stella/stella. Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim. Use for questions about personal data, consent, or data-subject rights.

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `prompts/research.prompt.md`, `references/sources/eu/gdpr.md` and `references/sources/source-map.md`).

It sits in Legal & Compliance, covering Privacy and GDPR and Citation management. The repository describes itself as: Open-source legal workspace. The licence is Apache-2.0.

When your agent uses it

  • Questions about personal data
  • Data-subject rights

Example prompts

  • “Use the answer-from-sources skill to answer data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation…”
  • “/answer-from-sources”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. GDPR, the regulation text itself
  2. CJEU case law interpreting it
  3. EDPB guidelines and opinions
  4. National supervisory-authority guidance
  5. Commentary

What it can do on your machine

Read from SKILL.md and the folder at commit 269655d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • 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

Answer From Sources loads about 735 tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 283 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~735
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.3k

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 stella/stella at commit 269655d, republished under its Apache-2.0 licence (© stella). 283 words, ~735 tokens.

Download SKILL.mdSave it as .claude/skills/answer-from-sources/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
answer-from-sources
description
Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim. Use for questions about personal data, consent, or data-subject rights.
<!-- guide: This skill ships as a worked example — GDPR Q&A. Keep the structure, swap the domain: rename it, point the description at the questions YOUR skill answers, and rebuild the source map in references/sources/. -->

What this skill does

Answers a data-protection question by working through the sources in references/sources/ in order of authority, citing the provision behind every claim.

Input

A data-protection question. If two things are not obvious from it, ask for both at once before answering: the jurisdiction (EU-wide, or a member state whose national derogations matter) and the role of the party asking (controller or processor).

<!-- guide: State what comes in, and which missing context justifies a clarifying question. Ask once, not piecemeal. -->

Sources

Authority order, highest first — on conflict, the higher source wins:

  1. GDPR, the regulation text itself
  2. CJEU case law interpreting it
  3. EDPB guidelines and opinions
  4. National supervisory-authority guidance
  5. Commentary

National law may derogate where the GDPR leaves room (for example the age of consent or the employment context); flag it when the question touches such an area. The per-source notes live in references/sources/.

<!-- guide: The hierarchy is the heart of this pattern: write down what wins on conflict, and where national variation can change the general answer. -->

Reasoning structure

Build every answer in four steps, in this order:

  1. Issue — restate the question as the legal issue it raises.
  2. Source — the governing provision(s), cited by article.
  3. Application — how the provision applies to the facts asked.
  4. Answer — the conclusion, and what remains open.
Show full SKILL.md (135 more words)Show less

Output rules

  • Cite the article or guideline paragraph for every claim.
  • Separate what the sources say from any practical suggestion.
  • If the sources do not settle the question, say so explicitly; do not paper over the gap.
  • Frame the answer as research support, not legal advice.
<!-- guide: Add your non-negotiables — answer language, how to handle conflicting sources, when to refuse. -->

Reference index

  • references/sources/source-map.md — the source list in authority order, with one row per source
  • references/sources/eu/gdpr.md — orientation notes on the regulation itself
<!-- guide: Keep one line per file under references/ — this index is how the assistant decides which file to open. -->

Workflow

  1. Identify the issue; ask once for jurisdiction and role if missing.
  2. Find the governing source via references/sources/source-map.md.
  3. Apply the reasoning structure.
  4. Answer with citations, flagging anything the sources leave open.

© stella, Apache-2.0. 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 packages/skills/blueprints/answer-from-sources of stella/stella.

  • SKILL.md
  • prompts/research.prompt.md
  • references/sources/eu/gdpr.md
  • references/sources/source-map.md

Open the folder on GitHubat commit 269655d

Compare with similar skills

Answer From Sources 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.

Answer From Sources compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Answer From Sources this skillstella/stella258—~735Automated safety check: PassApache-2.0
Legal Design Assessmentlawve-ai/awesome-legal-skills836—~3.7kAutomated safety check: PassCC-BY-4.0
Scholar Ethicsjoshzyj/open-scholar-skill168—~9.6kAutomated safety check: PassCustom licence
C15tc15t/c15t1.9k1 repos~1.6kAutomated safety check: PassApache-2.0
HIPAA Safe Harbor Coverage Auditmaziyarpanahi/openmed5.5k—~1.7kAutomated safety check: PassApache-2.0
Tw Legal RAGaa0101181514/tw-legal-rag327—~580Automated safety check: PassCustom licence

Similar skills

  • Legal Design Assessment

    lawve-ai/awesome-legal-skills

    Audits a legal document against legal design principles. An agent skill from lawve-ai/awesome-legal-skills.

    836 GitHub stars~3.7k tokensUpdated 5 days ago
    Legal & ComplianceAuto-check passed
  • Scholar Ethics

    joshzyj/open-scholar-skill

    Research ethics toolkit for social scientists. An agent skill from joshzyj/open-scholar-skill.

    168 GitHub stars~9.6k tokensUpdated 19 days ago
    Legal & ComplianceAuto-check passed
  • C15t

    c15t/c15t

    Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.

    1.9k GitHub starsUsed in 1 repo~1.6k tokens
    Legal & ComplianceAuto-check passed
  • Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.

    5.5k GitHub stars~1.7k tokensUpdated today
    Legal & ComplianceAuto-check passed
  • 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.

    327 GitHub stars~580 tokensUpdated 3 days ago
    Legal & ComplianceAuto-check passed
  • Korean Privacy Terms

    kimlawtech/korean-privacy-terms

    처리방침·이용약관 자동 생성 스킬 패키지 (v4.0). An agent skill from kimlawtech/korean-privacy-terms.

    586 GitHub stars~2.9k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

More from stella/stella

All 24 skills in this repo
  • Plan

    stella/stella

    Create a concise, evidence-backed implementation plan in the repository planning area when the user explicitly asks for a plan.

    258 GitHub stars~917 tokensUpdated today
    Auto-check passed
  • Check Against Rules

    stella/stella

    Reviews a non-disclosure agreement against the firm's NDA checklist and reports findings with citations.

    258 GitHub stars~856 tokensUpdated today
    Auto-check passed
  • Intake To Draft

    stella/stella

    Collects the facts of an unpaid invoice, then drafts a payment demand letter.

    258 GitHub stars~537 tokensUpdated today
    Auto-check passed
  • Conventions Perf

    stella/stella

    Apply when a performance-guard check (network baseline, bundle baseline, DB query count, loader-prefetch lint, RC bailouts) fails or when touching a hot route/endpoint.

    258 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Apply when writing or reviewing React effects in apps/web. An agent skill from stella/stella.

    258 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Dev

    stella/stella

    Start, drive and measure the local stack. An agent skill from stella/stella.

    258 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Answer From Sources

What does Answer From Sources do?

Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim. Answer From Sources is an agent skill from stella/stella. Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim.

When should I use Answer From Sources?

Answer From Sources fits situations like: questions about personal data; data-subject rights.

How do I install Answer From Sources in Claude Code?

Run `npx skills add stella/stella --skill answer-from-sources -a claude-code`. Or copy the skill folder (packages/skills/blueprints/answer-from-sources in stella/stella) into .claude/skills/answer-from-sources in your project. Claude Code loads it when a task matches its description.

How do I install Answer From Sources in Codex?

Run `npx skills add stella/stella --skill answer-from-sources -a codex`. Or copy the skill folder (packages/skills/blueprints/answer-from-sources in stella/stella) into .agents/skills/answer-from-sources in your project. Codex loads it when a task matches its description.

Can I use Answer From Sources 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 stella/stella --skill answer-from-sources -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/answer-from-sources, .gemini/skills/answer-from-sources, .github/skills/answer-from-sources and .opencode/skills/answer-from-sources in your project.

What does Answer From Sources need to run?

SKILL.md names no scripts, command-line tools or credentials: Answer From Sources is instructions for the agent only.

Does Answer From Sources 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 Answer From Sources 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 Answer From Sources use?

Answer From Sources is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Answer From Sources use?

About 735 tokens (SKILL.md is roughly 2.9k 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 530 tokens, read only when the agent opens those files.

What are the alternatives to Answer From Sources?

Skills that share tags, products or a category with Answer From Sources: Legal Design Assessment (lawve-ai/awesome-legal-skills, 836 stars), Scholar Ethics (joshzyj/open-scholar-skill, 168 stars), C15t (c15t/c15t, 1.9k stars) and HIPAA Safe Harbor Coverage Audit (maziyarpanahi/openmed, 5.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Answer From Sources?

stella (a GitHub organization) maintains it in stella/stella, which has 258 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

Source: stella/stella on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.