WILLOSCAR/research-units-pipeline-skills
Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. Evidence-first methodology prevents hollow writing through structured intermediate artifacts.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/WILLOSCAR/research-units-pipeline-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 WILLOSCAR/research-units-pipeline-skills/.codex/skills/_template_reference_first .claude/skills/_template_reference_first $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/agent-survey-corpus .claude/skills/agent-survey-corpus $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/anchor-sheet .claude/skills/anchor-sheet $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/appendix-table-writer .claude/skills/appendix-table-writer $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/argument-selfloop .claude/skills/argument-selfloop $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/artifact-contract-auditor .claude/skills/artifact-contract-auditor $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/arxiv-search .claude/skills/arxiv-search $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/beamer-compile-qa .claude/skills/beamer-compile-qa $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/beamer-scaffold .claude/skills/beamer-scaffold $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/bias-assessor .claude/skills/bias-assessor $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/chapter-briefs .claude/skills/chapter-briefs $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/chapter-lead-writer .claude/skills/chapter-lead-writer $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/chapter-skeleton .claude/skills/chapter-skeleton $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/checkpoint-brief .claude/skills/checkpoint-brief $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/citation-anchoring .claude/skills/citation-anchoring $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/citation-diversifier .claude/skills/citation-diversifier $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/citation-injector .claude/skills/citation-injector $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/citation-verifier .claude/skills/citation-verifier $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/claim-evidence-matrix .claude/skills/claim-evidence-matrix $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/claim-matrix-rewriter .claude/skills/claim-matrix-rewriter $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/claims-extractor .claude/skills/claims-extractor $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/concept-graph .claude/skills/concept-graph $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/dedupe-rank .claude/skills/dedupe-rank $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/deliverable-selfloop .claude/skills/deliverable-selfloop $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/draft-polisher .claude/skills/draft-polisher $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/evaluation-anchor-checker .claude/skills/evaluation-anchor-checker $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/evidence-auditor .claude/skills/evidence-auditor $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/evidence-binder .claude/skills/evidence-binder $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/evidence-draft .claude/skills/evidence-draft $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/evidence-selfloop .claude/skills/evidence-selfloop $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/exercise-builder .claude/skills/exercise-builder $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/extraction-form .claude/skills/extraction-form $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/front-matter-writer .claude/skills/front-matter-writer $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/global-reviewer .claude/skills/global-reviewer $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/grad-paragraph .claude/skills/grad-paragraph $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/human-checkpoint .claude/skills/human-checkpoint $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/idea-brief .claude/skills/idea-brief $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/idea-direction-generator .claude/skills/idea-direction-generator $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/idea-memo-writer .claude/skills/idea-memo-writer $ npx degit WILLOSCAR/research-units-pipeline-skills/.codex/skills/idea-screener .claude/skills/idea-screener
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (108)
_template_reference_firstagent-survey-corpusanchor-sheetappendix-table-writerargument-selfloopartifact-contract-auditorarxiv-searchbeamer-compile-qabeamer-scaffoldbias-assessorchapter-briefschapter-lead-writerchapter-skeletoncheckpoint-briefcitation-anchoringcitation-diversifiercitation-injectorcitation-verifierclaim-evidence-matrixclaim-matrix-rewriterclaims-extractorconcept-graphdedupe-rankdeliverable-selfloopdraft-polisherevaluation-anchor-checkerevidence-auditorevidence-binderevidence-draftevidence-selfloopexercise-builderextraction-formfront-matter-writerglobal-reviewergrad-paragraphhuman-checkpointidea-briefidea-direction-generatoridea-memo-writeridea-screeneridea-shortlist-curatoridea-signal-mapperkeyword-expansionlatex-compile-qalatex-scaffoldlimitation-weaverliterature-engineermanuscript-ingestmodule-plannermodule-source-coveragenovelty-matrixopener-variatoroutline-budgeteroutline-builderoutline-refinerpaper-notesparagraph-curatorpdf-text-extractorpipeline-auditorpipeline-routerpost-merge-voice-gateprose-writerprotocol-writerredundancy-prunerresearch-pipeline-runnerrubric-writerschema-normalizerscreening-managersection-bindingssection-briefssection-logic-polishersection-mappersection-mergersnapshot-writersource-ingestsource-manifestsource-tutorial-specsource-tutorial-writerstyle-harmonizersubsection-briefssubsection-polishersubsection-writersurvey-seed-harvestsurvey-visualssynthesis-writertable-fillertable-schemataxonomy-builderterminology-normalizerthesis-chapter-reconstructorthesis-citation-enhance-reviewthesis-compile-reviewthesis-frontmatter-syncthesis-markdown-alignerthesis-question-listthesis-source-role-mapperthesis-style-polisherthesis-tex-writebackthesis-visual-layout-plannerthesis-workspace-inittransition-weavertutorial-context-packtutorial-selfloopunit-executorunit-plannerworkspace-initwriter-context-packwriter-selfloop
Similar rigs
DougTrajano/pydantic-ai-skills
This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.
Pragmatist 2.3k tok ·
patricio0312rev/workspaces
Multi-repo workspace management for Claude Code. Clone, setup, and coordinate multiple related repositories.
Pragmatist 503 tok ·
waqas1412/claude-harness
Portable, self-adapting Claude Code harness: advisor agents, profile-driven /pr and /ticket skills, enforcement hooks, and /harness-init that tailors any repo.
Pragmatist 3.8k tok ·
Eflarus/claude-dotfiles
Opinionated Claude Code dotfiles — global standards, custom agents, RFC workflow, skills, hooks & statusline
Skill Collector 2.1k tok ·