llm-research-scout
Advanced LLM and AI agents research scout.
Skill by imvladikon
Chalk Labs
Need help deploying llm-research-scout?
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. Read the repository before you give any tool access to your data.
npx agentmarket install skill/imvladikon-llm-research-scout
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: ml, writing, research, agent-building
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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/llm-research-scout
Tools it pre-approves 4
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
WebFetch,WebSearch,Bash(python:*),Bash(pip:*)
What's inside
- Skill name
llm-research-scout- Description
- Advanced LLM and AI agents research scout. Searches, filters, and analyzes cutting-edge research papers and blog posts on LLM internals, training techniques, reasoning, and agent architectures. Delivers comprehensive reports with quality assessment and summaries for expert-level ML engineers. Use for: find latest LLM papers, research scout, deep learning research, reasoning models, agent architectures, post-training techniques, RLHF, alignment research, MoE architectures, survey latest ML research.
- License
- unknown
- Allowed tools
- WebFetch,, WebSearch,, Bash(python:*),, Bash(pip:*)
- Instructions
- 307 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Pre-approves some shell commands
Files (6)
- README.md
- SKILL.md
- evaluation_rubric.md · references/
- quality_venues.md · references/
- top_researchers.md · references/
- search_arxiv.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from imvladikon/dot-claude
- 0.451score
scientific-brainstorming
imvladikon
Research ideation partner.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
lecture-transcribe
imvladikon
Produce a lecture transcript plus a final expert-level lecture_notes.md from a YouTube link or local audio/video file.
SkillDFreshness: D★ 3Claude Code +9 - 0.444score
yt-dlp-mp3
imvladikon
Download a YouTube video as MP3 audio file named "{artist} - {title}.mp3" using yt-dlp.
SkillDFreshness: D★ 3Claude Code +9 - 0.444score
create-anki-hebrew
imvladikon
Convert a Hebrew vocabulary XLSX file into an Anki deck (.apkg).
SkillDFreshness: D★ 3Claude Code +9 - 0.444score
math-compute
imvladikon
Calculate, compute, evaluate mathematical expressions.
SkillDFreshness: D★ 3Claude Code - 0.444score
math-solve
imvladikon
Solve math problems step-by-step with full working.
SkillDFreshness: D★ 3Claude Code - 0.444score
math-verify
imvladikon
Check and verify mathematical proofs, find errors, validate reasoning.
SkillDFreshness: D★ 3Claude Code - 0.441score
clean-scan
imvladikon
Очистка сканов PDF от серого/желтого фона.
SkillDFreshness: D★ 3Claude Code +9 - 0.441score
market-research-reports
imvladikon
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner).
SkillDFreshness: D★ 3Claude Code +9 - 0.441score
djvu-to-pdf
imvladikon
Convert DJVU files to optimized PDF.
SkillDFreshness: D★ 3Claude Code +9 - 0.439score
transcribe-hebrew
imvladikon
Transcribe Hebrew audio/podcast file to SRT subtitles using OpenAI Whisper API.
SkillDFreshness: D★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Feb 26, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/imvladikon/dot-claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from imvladikon
- 0.451score
scientific-brainstorming
imvladikon
Research ideation partner.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
lecture-transcribe
imvladikon
Produce a lecture transcript plus a final expert-level lecture_notes.md from a YouTube link or local audio/video file.
SkillDFreshness: D★ 3Claude Code +9 - 0.444score
yt-dlp-mp3
imvladikon
Download a YouTube video as MP3 audio file named "{artist} - {title}.mp3" using yt-dlp.
SkillDFreshness: D★ 3Claude Code +9 - 0.444score
create-anki-hebrew
imvladikon
Convert a Hebrew vocabulary XLSX file into an Anki deck (.apkg).
SkillDFreshness: D★ 3Claude Code +9 - 0.444score
math-compute
imvladikon
Calculate, compute, evaluate mathematical expressions.
SkillDFreshness: D★ 3Claude Code - 0.444score
math-solve
imvladikon
Solve math problems step-by-step with full working.
SkillDFreshness: D★ 3Claude Code
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 llm-research-scout 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
llm-research-scout skill. Agent Mart. https://agentmart.dev/skills/imvladikon-llm-research-scout (last updated 2026-10-24)