research-units-pipeline-skills
Recoverable research pipelines for surveys, reviews, and theses
All Skills in This Repository (100)
Pure Emerald Level Indicatorstutorial-spec
Generate a TUTORIAL_SPEC.md from STATUS.md, GOAL.md, and DECISIONS.md.
table-schema
Define evidence-first table schemas for research survey tables.
synthesis-writer
Synthesize CSV-extracted study data into a narrative report with bias considerations.
chapter-lead-writer
Generate H2 chapter lead blocks from outline YAML and chapter briefs.
subsection-polisher
Refine H3 subsection markdown files into publication-grade prose with citation integrity.
protocol-writer
Generate systematic review protocol documents with scope, search strategies, and screening plans.
post-merge-voice-gate
Detect generator voice artifacts in merged draft documents and route corrections to source artifacts.
_template_reference_first
Create reusable skills with a reference-first architecture template.
thesis-question-list
Creates a question list document for managing Chinese graduation thesis revisions.
evaluation-anchor-checker
Audit and rewrite numeric claims with task, metric, and constraint context.
survey-visuals
Generate timelines and figure specifications for academic surveys from citation keys.
idea-direction-generator
Generate research directions from signal tables with note indices.
Frequently Asked Questions
FAQPage SchemaHow to install research-units-pipeline-skills?โผ
Run `npx skills add WILLOSCAR/research-units-pipeline-skills --all -g -y` in your terminal to install all skills in this collection globally.
What research tasks can this pipeline handle?โผ
It covers literature surveys with LaTeX delivery, paper peer reviews, systematic evidence reviews, research idea brainstorming, source-based tutorials, and Chinese graduate thesis restructuring.
How does it keep long research runs recoverable?โผ
Every run writes goals, unit plans, decisions, and evidence to workspace files, so work can resume after failures without reconstructing chat history.
Does it work with Claude Code and Codex?โผ
Yes. All skills follow the standard SKILL.md format and run in Claude Code, Codex, and other compatible coding agents.
Can it stop a survey from sounding machine-generated?โผ
Yes. Dedicated quality gates detect template phrasing, narration openers, citation drift, and missing evidence, then route fixes to the exact section that needs repair.
Related Repositories in Education & Research
View All in Education & Researchโlearn-claude-code
Learn to build AI agent harnesses from scratch
ai-agents-for-beginners
Learn to build, deploy, and secure AI agents step by step
33-js-concepts
Master 33 essential JavaScript concepts with tested, verified guides