fsearch
Search local evidence and external sources (arXiv) in one command, with ingested annotation.
Skill by UynajGI
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/uynajgi-fsearch
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/fsearch
What's inside
- Skill name
fsearch- Description
- Search local evidence and external sources (arXiv) in one command, with ingested annotation. Use when the user wants to search their library plus external sources, check if arXiv papers are already ingested, or discover new papers. Trigger on "federated search", "search arXiv and my library", "find papers everywhere", "cross-search", "check if paper is in my library".
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Federated search `drbrain search --source` retrieves local evidence rows and/or external rows in one result set, with an automatic "already ingested" annotation for external hits. ## Quick start ```bash drbrain search "attention mechanism" # local evidence only (default) drbrain search "graph neural network" --source all # local evidence + arXiv drbrain search "transformer" --source arxiv # arXiv only ``` ## How it works - **Local** (`--source local`, default): the same retrieval chain as `ask` (bm25/vector/tree), returning evidence rows with sources, text locators, route and index generation. - **arXiv** (`--source arxiv|all`): Atom API search with automatic dedup — results already in your library are annotated with `ingested: true`. External rows are marked `source="arxiv"` and carry `url` / `doi` / `arxiv_id`, but deliberately no local locator. - **Cross-reference**: matches by DOI and normalized arXiv ID. ## CLI reference | Command | What it does | |---------|--------------| | `drbrain search "<query>"` | Local evidence retrieval | | `drbrain search "<query>" --source all` | Local evidence + arXiv rows | | `drbrain search "<query>" --source arxiv` | arXiv rows only | | `drbrain search "<query>" --limit <n> --json` | JSON payload (`route`, `generations`, `legs`, `evidence`) | | `drbrain fsearch "<query>" --arxiv` | Historical federated command (hidden compatibility alias) |
From UynajGI/drbrain, MIT.
More from UynajGI/drbrain
- 0.529score
neat-freak
UynajGI
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots.
SkillBFreshness: BClaude Code +9 - 0.524score
kg-build
UynajGI
Build the knowledge graph from ingested papers — 5-stage LLM extraction, TransE graph embeddings, and rule-based closure inference.
SkillBFreshness: BClaude Code +9 - 0.524score
audit
UynajGI
Scan the entire library for data quality issues across 15 severity-graded rules.
SkillBFreshness: BClaude Code +9 - 0.524score
graph
UynajGI
Direct knowledge graph operations — traverse neighbors, find shortest paths, and analyze shared concepts across papers.
SkillBFreshness: BClaude Code +9 - 0.524score
index
UynajGI
Prepare, inspect and verify the searchable index.
SkillBFreshness: BClaude Code +9 - 0.524score
ingest-link
UynajGI
Ingest web URLs and online PDFs by extracting rendered content via an external qt-web-extractor service.
SkillBFreshness: BClaude Code +9 - 0.524score
kg-reason
UynajGI
Reason over the knowledge graph using LLM agents — natural language Q&A and tool-calling iterative reasoning with bidirectional LLM↔KG validation.
SkillBFreshness: BClaude Code +9 - 0.474score
backup
UynajGI
Create and manage backups of DrBrain data — local tar.gz archives and rsync remote sync.
SkillCFreshness: CClaude Code +9 - 0.474score
citation-tracking
UynajGI
Track and analyze citation relationships between papers.
SkillCFreshness: CClaude Code +9 - 0.474score
document
UynajGI
Inspect Office documents (DOCX, PPTX, XLSX) and output structured text summaries.
SkillCFreshness: CClaude Code +9 - 0.474score
enrich
UynajGI
Enrich paper metadata by backfilling missing fields from CrossRef and detecting records that need cleanup.
SkillCFreshness: CClaude Code +9 - 0.474score
explore
UynajGI
Manage explore silos — lightweight literature discovery collections separate from the main library.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 16, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/UynajGI/drbrain
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from UynajGI
- 0.529score
neat-freak
UynajGI
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots.
SkillBFreshness: BClaude Code +9 - 0.524score
index
UynajGI
Prepare, inspect and verify the searchable index.
SkillBFreshness: BClaude Code +9 - 0.524score
kg-build
UynajGI
Build the knowledge graph from ingested papers — 5-stage LLM extraction, TransE graph embeddings, and rule-based closure inference.
SkillBFreshness: BClaude Code +9 - 0.524score
graph
UynajGI
Direct knowledge graph operations — traverse neighbors, find shortest paths, and analyze shared concepts across papers.
SkillBFreshness: BClaude Code +9 - 0.524score
audit
UynajGI
Scan the entire library for data quality issues across 15 severity-graded rules.
SkillBFreshness: BClaude Code +9 - 0.524score
ingest-link
UynajGI
Ingest web URLs and online PDFs by extracting rendered content via an external qt-web-extractor service.
SkillBFreshness: BClaude Code +9
Cite this page
fsearch skill. Agent Mart. https://agentmart.dev/skills/uynajgi-fsearch (last updated 2026-10-24)