Skip to content
Agentmart
Submit a tool

research

Autonomous ML research loop for a "research lab" repo — survey, hypothesize, pre-register, run matched-compute experiments with seeds and a negative control…

Skill by siinghd

IndexedLicense unknown
Write a review

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/siinghd-research

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.

We use your email only for this newsletter. Privacy

About

Autonomous ML research loop for a "research lab" repo — survey, hypothesize, pre-register, run matched-compute experiments with seeds and a negative control, hostile review, log, decide, repeat. Use for any request to run an experiment, test a hypothesis, try a variant or ablation, reproduce a paper or a number, build a scaling ladder, profile and optimize a training/inference bottleneck, explain why a model behaves some way, or continue research from STATE.md. Also use when the user says "research", "experiment", "ablate", "reproduce", "baseline", "sweep", or drops a note in INBOX.md. Invoke as /research <topic> or bare /research to continue.

Use cases: testing, ml, research, productivity

Reviews

Write a review

No 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/research

What's inside

Skill name
research
Description
Autonomous ML research loop for a "research lab" repo — survey, hypothesize, pre-register, run matched-compute experiments with seeds and a negative control, hostile review, log, decide, repeat. Use for any request to run an experiment, test a hypothesis, try a variant or ablation, reproduce a paper or a number, build a scaling ladder, profile and optimize a training/inference bottleneck, explain why a model behaves some way, or continue research from STATE.md. Also use when the user says "research", "experiment", "ablate", "reproduce", "baseline", "sweep", or drops a note in INBOX.md. Invoke as /research <topic> or bare /research to continue.
License
unknown
Instructions
69 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (24)

  • README.md
  • SKILL.md
  • checklists.md · reference/
  • hypothesis-moves.md · reference/
  • loop.md · reference/
  • templates.md · reference/
  • _common.py · scripts/
  • budget.py · scripts/
  • collect.sh · scripts/
  • finish.sh · scripts/
  • init_lab.sh · scripts/
  • ladder.py · scripts/
  • launch.sh · scripts/
  • log_run.py · scripts/
  • new_experiment.sh · scripts/
  • predict.py · scripts/
  • prereg.sh · scripts/
  • report.py · scripts/
  • session_start.sh · scripts/
  • verify_result.py · scripts/
  • CLAUDE.md · templates/
  • PLAN.md · templates/
  • RESULT.md · templates/
  • settings.json · templates/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from siinghd/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 23, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/siinghd/skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from siinghd

Cite this page

research skill. Agent Mart. https://agentmart.dev/skills/siinghd-research (last updated 2026-10-24)