scdenney/open-science-skills
Agentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experimental design, computational text analysis, manuscript QA, and transparent reporting.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/scdenney/open-science-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 scdenney/open-science-skills/plugin/skills/advisor .claude/skills/advisor $ npx degit scdenney/open-science-skills/plugin/skills/beamer .claude/skills/beamer $ npx degit scdenney/open-science-skills/plugin/skills/citation-check .claude/skills/citation-check $ npx degit scdenney/open-science-skills/plugin/skills/conjoint-cleaning .claude/skills/conjoint-cleaning $ npx degit scdenney/open-science-skills/plugin/skills/conjoint-design .claude/skills/conjoint-design $ npx degit scdenney/open-science-skills/plugin/skills/conjoint-diagnostics .claude/skills/conjoint-diagnostics $ npx degit scdenney/open-science-skills/plugin/skills/cross-national-design .claude/skills/cross-national-design $ npx degit scdenney/open-science-skills/plugin/skills/deliverable-intake .claude/skills/deliverable-intake $ npx degit scdenney/open-science-skills/plugin/skills/deliverable-lint .claude/skills/deliverable-lint $ npx degit scdenney/open-science-skills/plugin/skills/deliverable-open .claude/skills/deliverable-open $ npx degit scdenney/open-science-skills/plugin/skills/diverge .claude/skills/diverge $ npx degit scdenney/open-science-skills/plugin/skills/doc-to-markdown .claude/skills/doc-to-markdown $ npx degit scdenney/open-science-skills/plugin/skills/fact-check .claude/skills/fact-check $ npx degit scdenney/open-science-skills/plugin/skills/figure-table-audit .claude/skills/figure-table-audit $ npx degit scdenney/open-science-skills/plugin/skills/figures .claude/skills/figures $ npx degit scdenney/open-science-skills/plugin/skills/finished .claude/skills/finished $ npx degit scdenney/open-science-skills/plugin/skills/hypothesis-building .claude/skills/hypothesis-building $ npx degit scdenney/open-science-skills/plugin/skills/journal-review .claude/skills/journal-review $ npx degit scdenney/open-science-skills/plugin/skills/list-experiment .claude/skills/list-experiment $ npx degit scdenney/open-science-skills/plugin/skills/literature-review .claude/skills/literature-review $ npx degit scdenney/open-science-skills/plugin/skills/llm-calibration-logprobs .claude/skills/llm-calibration-logprobs $ npx degit scdenney/open-science-skills/plugin/skills/methods-reporting .claude/skills/methods-reporting $ npx degit scdenney/open-science-skills/plugin/skills/model-committee .claude/skills/model-committee $ npx degit scdenney/open-science-skills/plugin/skills/narrative-building .claude/skills/narrative-building $ npx degit scdenney/open-science-skills/plugin/skills/orchestrate .claude/skills/orchestrate $ npx degit scdenney/open-science-skills/plugin/skills/paper-review-lite .claude/skills/paper-review-lite $ npx degit scdenney/open-science-skills/plugin/skills/paper-tex .claude/skills/paper-tex $ npx degit scdenney/open-science-skills/plugin/skills/pre-registration-writing .claude/skills/pre-registration-writing $ npx degit scdenney/open-science-skills/plugin/skills/presubmit .claude/skills/presubmit $ npx degit scdenney/open-science-skills/plugin/skills/qualtrics-ops .claude/skills/qualtrics-ops $ npx degit scdenney/open-science-skills/plugin/skills/referee-response .claude/skills/referee-response $ npx degit scdenney/open-science-skills/plugin/skills/replication-package .claude/skills/replication-package $ npx degit scdenney/open-science-skills/plugin/skills/research-grill .claude/skills/research-grill $ npx degit scdenney/open-science-skills/plugin/skills/research-repo .claude/skills/research-repo $ npx degit scdenney/open-science-skills/plugin/skills/research-wayfinder .claude/skills/research-wayfinder $ npx degit scdenney/open-science-skills/plugin/skills/sitrep .claude/skills/sitrep $ npx degit scdenney/open-science-skills/plugin/skills/survey-data-audit .claude/skills/survey-data-audit $ npx degit scdenney/open-science-skills/plugin/skills/survey-design .claude/skills/survey-design $ npx degit scdenney/open-science-skills/plugin/skills/tables .claude/skills/tables $ npx degit scdenney/open-science-skills/plugin/skills/text-classification .claude/skills/text-classification
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 (42)
advisorbeamercitation-checkconjoint-cleaningconjoint-designconjoint-diagnosticscross-national-designdeliverable-intakedeliverable-lintdeliverable-opendivergedoc-to-markdownfact-checkfigure-table-auditfiguresfinishedhypothesis-buildingjournal-reviewlist-experimentliterature-reviewllm-calibration-logprobsmethods-reportingmodel-committeenarrative-buildingorchestratepaper-review-litepaper-texpre-registration-writingpresubmitqualtrics-opsreferee-responsereplication-packageresearch-grillresearch-reporesearch-wayfindersitrepsurvey-data-auditsurvey-designtablestext-classificationtopic-modelingvlm-ocr
Similar rigs
Nowely/agent-skills
Run Codex as a Claude Code subagent with rights declared per call — read-only analysis, or writing and running tests inside a git worktree — and an exit code that reflects what actually ran.
Skill Collector 110 tok ·
snaplyze/claude-orchestration
Claude Code plugin for orchestration: five specialist subagents with explicit model and effort, subscription profiles, user-scope install, and runtime verification
Pragmatist 3.2k tok ·
ChristianBlevens/RaiGolmi
A computer you build by talking to an AI.
Pragmatist 2.7k tok ·
drader/researcher_agent
An LLM-driven research assistance framework for Claude Code (CC BY-NC 4.0)
Pragmatist 1.9k tok ·