agentrigs
+ submit rig
~ / rigs / hsigstad / research-kit

hsigstad/research-kit

Shared infrastructure for AI-assisted research workflows: Claude Code skills, conventions, methodology docs, and tools.

↗ GitHub ★ 0 mit updated 14d ago collection Claude Code
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~2.7k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit hsigstad/research-kit/skills ./rig-research-kit/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit hsigstad/research-kit/skills/anecdotes .claude/skills/anecdotes
$ npx degit hsigstad/research-kit/skills/backup .claude/skills/backup
$ npx degit hsigstad/research-kit/skills/check .claude/skills/check
$ npx degit hsigstad/research-kit/skills/cite-sync .claude/skills/cite-sync
$ npx degit hsigstad/research-kit/skills/data .claude/skills/data
$ npx degit hsigstad/research-kit/skills/diarios .claude/skills/diarios
$ npx degit hsigstad/research-kit/skills/distill-style .claude/skills/distill-style
$ npx degit hsigstad/research-kit/skills/drive .claude/skills/drive
$ npx degit hsigstad/research-kit/skills/dropbox .claude/skills/dropbox
$ npx degit hsigstad/research-kit/skills/fetch-annotations .claude/skills/fetch-annotations
$ npx degit hsigstad/research-kit/skills/findings-audit .claude/skills/findings-audit
$ npx degit hsigstad/research-kit/skills/findings .claude/skills/findings
$ npx degit hsigstad/research-kit/skills/gmail .claude/skills/gmail
$ npx degit hsigstad/research-kit/skills/handoff .claude/skills/handoff
$ npx degit hsigstad/research-kit/skills/howto .claude/skills/howto
$ npx degit hsigstad/research-kit/skills/hypothesis .claude/skills/hypothesis
$ npx degit hsigstad/research-kit/skills/iat .claude/skills/iat
$ npx degit hsigstad/research-kit/skills/idea .claude/skills/idea
$ npx degit hsigstad/research-kit/skills/inbox .claude/skills/inbox
$ npx degit hsigstad/research-kit/skills/institutions .claude/skills/institutions
$ npx degit hsigstad/research-kit/skills/literature .claude/skills/literature
$ npx degit hsigstad/research-kit/skills/llmkit .claude/skills/llmkit
$ npx degit hsigstad/research-kit/skills/meet .claude/skills/meet
$ npx degit hsigstad/research-kit/skills/memory-audit .claude/skills/memory-audit
$ npx degit hsigstad/research-kit/skills/new-pipeline .claude/skills/new-pipeline
$ npx degit hsigstad/research-kit/skills/new-project .claude/skills/new-project
$ npx degit hsigstad/research-kit/skills/next .claude/skills/next
$ npx degit hsigstad/research-kit/skills/otter .claude/skills/otter
$ npx degit hsigstad/research-kit/skills/outlook .claude/skills/outlook
$ npx degit hsigstad/research-kit/skills/questions .claude/skills/questions
$ npx degit hsigstad/research-kit/skills/referee-panel .claude/skills/referee-panel
$ npx degit hsigstad/research-kit/skills/site .claude/skills/site
$ npx degit hsigstad/research-kit/skills/style-check .claude/skills/style-check
$ npx degit hsigstad/research-kit/skills/style-review .claude/skills/style-review
$ npx degit hsigstad/research-kit/skills/style-revise .claude/skills/style-revise
$ npx degit hsigstad/research-kit/skills/tactiq .claude/skills/tactiq
$ npx degit hsigstad/research-kit/skills/theory .claude/skills/theory
$ npx degit hsigstad/research-kit/skills/validate-section .claude/skills/validate-section
$ npx degit hsigstad/research-kit/skills/whatsapp .claude/skills/whatsapp
$ npx degit hsigstad/research-kit/skills/zoom .claude/skills/zoom

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (40)

anecdotesbackupcheckcite-syncdatadiariosdistill-styledrivedropboxfetch-annotationsfindings-auditfindingsgmailhandoffhowtohypothesisiatideainboxinstitutionsliteraturellmkitmeetmemory-auditnew-pipelinenew-projectnextotteroutlookquestionsreferee-panelsitestyle-checkstyle-reviewstyle-revisetactiqtheoryvalidate-sectionwhatsappzoom

Similar rigs

itsOmidKarami/kraft
A local orchestrator that takes your coding agent from spec to pull request, stopping only when a decision is yours.
★ 1 project Claude CodeCodex 1 mcp 27 skills 1 hooks today
Skill Collector 7.9k tok ·
warrendeanlangeveldt/code-kit
Keeps AI coding agents inside your project's rules: lanes, layer rules, protected paths and proof before finish, enforced by Claude Code hooks and in CI
★ 0 project Claude CodeCodex 8 skills today
Pragmatist 1.2k tok ·
pablobfonseca/dotfiles
my dotfiles
★ 8 setup Claude CodeCodex 18 skills today
Skill Collector 3.3k tok ·
xnyzer/coding-kit
Claude Code plugin + marketplace with generic workflow skills, a project-detecting stop hook, and a shareable Renovate preset
★ 0 project Claude Code 18 skills today
Skill Collector 2.1k tok ·
copied ✓