tavily-background
Gather and synthesize external context for a research paper using Tavily Search, Tavily Research, or cached web artifacts, including concept definitions…
Skill by Siris2314
Chalk Labs
Need help deploying tavily-background?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/siris2314-tavily-background
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, productivity
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/tavily-background
What's inside
- Skill name
tavily-background- Description
- Gather and synthesize external context for a research paper using Tavily Search, Tavily Research, or cached web artifacts, including concept definitions, official paper pages, code, project pages, related work, benchmark pages, and follow-up papers. Use when the user asks for web context, opens an enriched concept card, or the task needs external verification.
- License
- MIT
- Instructions
- 20 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Tavily Background Use external sources only when paper-only context is insufficient or explicitly requested. ## Workflow 1. Use Tavily Research `mini` for a narrow concept definition; use `pro` only for genuinely multi-part research. 2. Poll non-streaming research tasks until completion and cache the synthesized content plus sources. 3. Fall back to Tavily Search with `include_answer=True` only when Research is unavailable, and label the fallback. 4. Search official sources first for paper metadata, code, and benchmark claims. 5. Use external context to explain background, not to overwrite paper evidence. 6. Cache term research under `web/tavily_term_research/` and concept cards under `concepts/cards/`. 7. Record source URLs and synthesis provenance. ## Gotchas - Do not use web search for paper-only answers. - If search fails, say so.
From Siris2314/deep-paper-reader, MIT.
More from Siris2314/deep-paper-reader
- 0.603score
math-walkthrough
Siris2314
Parse, typeset, explain, and evaluate research-paper equations, notation, symbols, derivations, losses, objectives, tensor shapes, assumptions, and…
SkillAFreshness: A★ 2Claude Code +9 - 0.512score
figure-table-analysis
Siris2314
Analyze research-paper figures, diagrams, plots, tables, ablations, metrics, benchmark evidence, captions, and surrounding text.
SkillCFreshness: C★ 2Claude Code +9 - 0.512score
concept-card
Siris2314
Create compact, provenance-labeled concept cards for terms, acronyms, benchmarks, methods, prerequisites, model families, or UI concept popups.
SkillCFreshness: C★ 2Claude Code +9 - 0.512score
paper-term-highlighter
Siris2314
Identify and highlight significant research-paper terms from parsed paper artifacts and user-confirmed long-term term memory, especially main-method concepts…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
research-lineage
Siris2314
Trace how an uploaded research paper builds on, modifies, adopts, compares with, or evaluates against earlier work using its bibliography and exact citation…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
chat-answer
Siris2314
Interactive research-paper Q&A for a parsed paper workspace.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
paper-evaluator
Siris2314
Evaluate final reports, serious chat answers, concept cards, or math explanations using deterministic checks and independent LLM-as-a-judge rubrics for…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
implementation-reconstructor
Siris2314
Reconstruct implementation details from a research paper, including algorithms, architecture, pseudocode, data structures, training/runtime phases, missing…
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 23, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Siris2314/deep-paper-reader
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Siris2314
- 0.603score
math-walkthrough
Siris2314
Parse, typeset, explain, and evaluate research-paper equations, notation, symbols, derivations, losses, objectives, tensor shapes, assumptions, and…
SkillAFreshness: A★ 2Claude Code +9 - 0.512score
figure-table-analysis
Siris2314
Analyze research-paper figures, diagrams, plots, tables, ablations, metrics, benchmark evidence, captions, and surrounding text.
SkillCFreshness: C★ 2Claude Code +9 - 0.512score
concept-card
Siris2314
Create compact, provenance-labeled concept cards for terms, acronyms, benchmarks, methods, prerequisites, model families, or UI concept popups.
SkillCFreshness: C★ 2Claude Code +9 - 0.512score
paper-term-highlighter
Siris2314
Identify and highlight significant research-paper terms from parsed paper artifacts and user-confirmed long-term term memory, especially main-method concepts…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
research-lineage
Siris2314
Trace how an uploaded research paper builds on, modifies, adopts, compares with, or evaluates against earlier work using its bibliography and exact citation…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
chat-answer
Siris2314
Interactive research-paper Q&A for a parsed paper workspace.
SkillCFreshness: C★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get tavily-background running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
tavily-background skill. Agent Mart. https://agentmart.dev/skills/siris2314-tavily-background (last updated 2026-10-24)