Sciverse
opendatalab/Sciverse-Agent-Tools
A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original…
Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section.
Install RAG Cite Sources
$ npx skills add lyonzin/knowledge-rag --skill rag-cite-sources -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lyonzin/knowledge-rag rag-cite-sources --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/lyonzin/knowledge-rag.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/foundation/rag-cite-sources .claude/skills/rag-cite-sources && 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 "rag-cite-sources" agent skill from https://github.com/lyonzin/knowledge-rag/tree/master/skills/foundation/rag-cite-sources into .claude/skills/rag-cite-sources/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-cite-sources", 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/lyonzin/knowledge-rag/tree/master/skills/foundation/rag-cite-sourcesType 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 lyonzin/knowledge-rag --skill rag-cite-sources -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lyonzin/knowledge-rag rag-cite-sources --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lyonzin/knowledge-rag.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/foundation/rag-cite-sources .agents/skills/rag-cite-sources && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rag-cite-sources" agent skill from https://github.com/lyonzin/knowledge-rag/tree/master/skills/foundation/rag-cite-sources into .agents/skills/rag-cite-sources/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-cite-sources", 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 lyonzin/knowledge-rag --skill rag-cite-sources -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lyonzin/knowledge-rag rag-cite-sources --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lyonzin/knowledge-rag.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/foundation/rag-cite-sources .cursor/skills/rag-cite-sources && 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 "rag-cite-sources" agent skill from https://github.com/lyonzin/knowledge-rag/tree/master/skills/foundation/rag-cite-sources into .cursor/skills/rag-cite-sources/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-cite-sources", 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/lyonzin/knowledge-rag.git --path skills/foundation/rag-cite-sources--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 lyonzin/knowledge-rag --skill rag-cite-sources -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lyonzin/knowledge-rag rag-cite-sources --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lyonzin/knowledge-rag.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/foundation/rag-cite-sources .gemini/skills/rag-cite-sources && 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 "rag-cite-sources" agent skill from https://github.com/lyonzin/knowledge-rag/tree/master/skills/foundation/rag-cite-sources into .gemini/skills/rag-cite-sources/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-cite-sources", 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 lyonzin/knowledge-rag rag-cite-sourcesInstalls 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 lyonzin/knowledge-rag --skill rag-cite-sources -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lyonzin/knowledge-rag.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/foundation/rag-cite-sources .github/skills/rag-cite-sources && 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 "rag-cite-sources" agent skill from https://github.com/lyonzin/knowledge-rag/tree/master/skills/foundation/rag-cite-sources into .github/skills/rag-cite-sources/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-cite-sources", 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 lyonzin/knowledge-rag --skill rag-cite-sources -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lyonzin/knowledge-rag rag-cite-sources --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lyonzin/knowledge-rag.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/foundation/rag-cite-sources .opencode/skills/rag-cite-sources && 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 "rag-cite-sources" agent skill from https://github.com/lyonzin/knowledge-rag/tree/master/skills/foundation/rag-cite-sources into .opencode/skills/rag-cite-sources/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-cite-sources", 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
rag-cite-sources- GitHub stars
- 292
- Token cost
- ~1.4k tokens
- SKILL.md length
- 361 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section.
- Works in 5 steps: When you call search_knowledge or… → When you draft the response, mark every… → If quoting verbatim, use fenced… → …
- Ever the response quotes
- SKILL.md covers When to use this skill, What this skill commits to, Steps and Examples, plus 2 more sections
- Reaches datatracker.ietf.org
What it does
RAG Cite Sources is an agent skill from lyonzin/knowledge-rag. Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section. Trigger whenever the response quotes, paraphrases, or acts on knowledge that came from a searchknowledge or getdocument call. Makes answers auditable and lets the user jump to source in one click.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Citation management and Retrieval-augmented generation. It works with Model Context Protocol. The repository describes itself as: Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys. The licence is MIT.
When your agent uses it
- Ever the response quotes
- Acts on knowledge that came from a searchknowledge
- Getdocument call
Example prompts
- “/rag-cite-sources”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- When you call search_knowledge or get_document, capture
- When you draft the response, mark every fact-carrying sentence with its source. Preferred inline syntax
- If quoting verbatim, use fenced blockquote + citation
- If synthesizing across multiple sources, cite each
- When a claim is NOT from the corpus (general knowledge, external doc, your own reasoning), mark it explicitly
What it can do on your machine
Read from SKILL.md and the folder at commit df9cccb. 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 (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
datatracker.ietf.org
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
RAG Cite Sources loads about 1.4k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 361 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 lyonzin/knowledge-rag at commit df9cccb, republished under its MIT licence (© lyonzin). 361 words, ~1,420 tokens.
Download SKILL.mdSave it as
.claude/skills/rag-cite-sources/SKILL.md (or your agent's skills folder).- name
- rag-cite-sources
- description
- Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section. Trigger whenever the response quotes, paraphrases, or acts on knowledge that came from a search_knowledge or get_document call. Makes answers auditable and lets the user jump to source in one click.
- metadata.type
- rag-workflow
- metadata.kind
- foundation
- metadata.target
- any-mcp-client
rag-cite-sources — every claim traces to a source
When to use this skill
Whenever an answer contains any of these:
- A specific number, threshold, config value, or version taken from the corpus
- A statement about how the system currently works, was designed, or was decided
- A code snippet, function signature, or API contract quoted from indexed files
- A "the runbook says", "the ADR says", "the RFC decided", "we agreed" claim
- A recommendation grounded in prior team practice
Basically: if a curious reader would want to double-check where you got that, cite.
What this skill commits to
Every technical claim in the response carries a citation of the form:
[path/to/file.md:42]— line-anchored (fromsearch_knowledgeresult'ssourcefield)[path/to/file.md#section-heading]— section-anchored for Markdown[path/to/file.md]— file-only, when line/section is not available
Citations are inline at the point of the claim, not batched at the end. One claim = one citation.
Steps
When you call
search_knowledgeorget_document, capture:- The
sourcefield (usually the file path) - The
filename(short name for display) - Any
chunk_idor line hint in the metadata - The actual
contentyou are about to quote or paraphrase
- The
When you draft the response, mark every fact-carrying sentence with its source. Preferred inline syntax:
markdown Per ADR-0018 [docs/adr/0018-auth.md], the payment service uses mTLS between services. The retry policy is 3 attempts with exponential backoff [services/payment/retry.py].If quoting verbatim, use fenced blockquote + citation:
markdown > "All external API calls must timeout after 30 seconds." > — [docs/architecture/http-contracts.md#timeouts]If synthesizing across multiple sources, cite each:
markdown The service uses OAuth2 [docs/adr/0018-auth.md] with a 15-minute access token TTL [config/auth.yaml:12] and refresh-token rotation on every use [docs/security/oauth-flow.md].When a claim is NOT from the corpus (general knowledge, external doc, your own reasoning), mark it explicitly:
markdown Per [docs/adr/0018-auth.md] we use OAuth2. Note that OAuth2 spec (RFC 6749, external) also allows client-credentials flow, which the ADR does not mention.
Show full SKILL.md (177 more words)Show less
Examples
Example 1 — Answering a config question
User: "What is our default request timeout?"
Agent:
search_knowledge(query="default request timeout") →
1 hit: config/http.yaml (line 8, score 0.87)
Reply: "The default request timeout is 30 seconds [config/http.yaml:8].
This is enforced globally by the HTTP client middleware [services/common/http_client.py:45]."Example 2 — Code review
User: "Is this retry logic correct?"
Agent:
search_knowledge(query="retry policy exponential backoff") →
2 hits: docs/adr/0031-retries.md (0.79), services/common/retry.py (0.65)
Reply: "Per our retry ADR [docs/adr/0031-retries.md], the policy is
'3 attempts, exponential backoff starting at 1s, max 30s'. Your code
retries 5 times which exceeds the standard. Adjust to match
services/common/retry.py:12–28 or open a new ADR to document
the exception."Example 3 — Explicit no-source note
User: "Should we use gRPC instead of REST for the new service?"
Agent:
search_knowledge(query="grpc rest choice") → 0 hits
Reply: "The corpus does not have a decision on gRPC vs REST for new services
(no ADR indexed on this). Answering from general considerations [not from corpus]:
gRPC gives you… [reasoning]. Recommend: open an ADR with the tradeoffs before
committing."Edge cases
- Chunk mid-sentence — if
search_knowledgereturns a chunk that starts mid-paragraph, callget_document(filepath=<source>)to fetch context before quoting. - Very long paths — abbreviate for readability, keep the full path in a footnote:
markdown Per the retry ADR [ADR-0031¹], we use exponential backoff. ¹ docs/architecture/decisions/0031-retries-and-timeouts.md - Non-file sources (URL-ingested content) — cite the original URL from the document's metadata:
markdown Per RFC 9110 §15.5.9 [https://datatracker.ietf.org/doc/html/rfc9110, indexed via add_from_url on 2026-05-14], 425 Too Early is idempotent-safe. - The corpus contradicts itself — cite both sources and flag the conflict explicitly:
markdown Conflicting sources: [docs/adr/0018-auth.md] says 15-min TTL, but [config/auth.yaml:12] shows 30-min. Recommend resolving the ADR vs config drift before answering with certainty.
Related skills
rag-check-first— the prerequisite: search happens first, citations follow.rag-deep-dive— chained citations across a full drill-down.rag-code-review— code review is where citation discipline pays off most.
© lyonzin, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/foundation/rag-cite-sources of lyonzin/knowledge-rag.
Open the folder on GitHubat commit df9cccb
Compare with similar skills
RAG Cite 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| RAG Cite Sources this skilllyonzin/knowledge-rag | 292 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Sciverseopendatalab/Sciverse-Agent-Tools | 120 | — | ~3k | Automated safety check: Pass | Custom licence | |
| Tw Legal RAGaa0101181514/tw-legal-rag | 328 | — | ~580 | Automated safety check: Pass | Custom licence | |
| Scholar RAGjoshzyj/open-scholar-skill | 168 | — | ~7.4k | Automated safety check: Notes | Custom licence | |
| Local RAG Searchnkapila6/mcp-local-rag | 134 | 1 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Gnogmickel/gno | 115 | 1 repos | ~1.6k | Automated safety check: Pass | MIT |
Similar skills
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.
Scholar RAG
joshzyj/open-scholar-skill
Build and query a local vector database + GraphRAG over your entire reference library (Zotero or a PDF folder) for literature review.
Local RAG Search
nkapila6/mcp-local-rag
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking.
Gno
gmickel/gno
Search local documents, files, notes, and knowledge bases. An agent skill from gmickel/gno.
Gno
gmickel/gno
Search local documents, files, notes, and knowledge bases. An agent skill from gmickel/gno.
More from lyonzin/knowledge-rag
All 10 skills in this repoRAG Check First
lyonzin/knowledge-rag
Before answering any technical question, code request, architecture decision, or factual claim, call searchknowledge to check the local corpus.
RAG Code Review
lyonzin/knowledge-rag
When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files.
RAG Deep Dive
lyonzin/knowledge-rag
Three-step multi-tool workflow — search the corpus, fetch the most relevant document in full, then find similar documents.
RAG Troubleshoot
lyonzin/knowledge-rag
When the user reports a bug, error message, stack trace, unexpected behavior, or "why is this broken" question, search the corpus first for prior occurrences, known fixes, or related runbooks.
RAG Evaluate Quality
lyonzin/knowledge-rag
Measure retrieval quality using evaluateretrieval (MRR@5 and Recall@5) and getindexstats.
RAG Index Decisions
lyonzin/knowledge-rag
After making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next…
Related
Works with
Categories
Questions about RAG Cite Sources
What does RAG Cite Sources do?
Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section. RAG Cite Sources is an agent skill from lyonzin/knowledge-rag. Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section.
When should I use RAG Cite Sources?
RAG Cite Sources fits situations like: ever the response quotes; acts on knowledge that came from a searchknowledge; getdocument call.
How do I install RAG Cite Sources in Claude Code?
Run `npx skills add lyonzin/knowledge-rag --skill rag-cite-sources -a claude-code`. Or copy the skill folder (skills/foundation/rag-cite-sources in lyonzin/knowledge-rag) into .claude/skills/rag-cite-sources in your project. Claude Code loads it when a task matches its description.
How do I install RAG Cite Sources in Codex?
Run `npx skills add lyonzin/knowledge-rag --skill rag-cite-sources -a codex`. Or copy the skill folder (skills/foundation/rag-cite-sources in lyonzin/knowledge-rag) into .agents/skills/rag-cite-sources in your project. Codex loads it when a task matches its description.
Can I use RAG Cite 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 lyonzin/knowledge-rag --skill rag-cite-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/rag-cite-sources, .gemini/skills/rag-cite-sources, .github/skills/rag-cite-sources and .opencode/skills/rag-cite-sources in your project.
What does RAG Cite Sources need to run?
SKILL.md names no scripts, command-line tools or credentials: RAG Cite Sources is instructions for the agent only.
Does RAG Cite Sources access the network?
SKILL.md names 1 domain. In commands or code: datatracker.ietf.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is RAG Cite 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 RAG Cite Sources use?
RAG Cite Sources 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 RAG Cite Sources use?
About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to RAG Cite Sources?
Skills that share tags, products or a category with RAG Cite Sources: Sciverse (opendatalab/Sciverse-Agent-Tools, 120 stars), Tw Legal RAG (aa0101181514/tw-legal-rag, 328 stars), Scholar RAG (joshzyj/open-scholar-skill, 168 stars) and Local RAG Search (nkapila6/mcp-local-rag, 134 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains RAG Cite Sources?
lyonzin (a GitHub user) maintains it in lyonzin/knowledge-rag, which has 292 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.
Source: lyonzin/knowledge-rag on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.