Updated 1w ago
by 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.
514 GitHub stars (514)
+3 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | +1 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | +1 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | +1 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 39 forks (39 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add WILLOSCAR/research-units-pipeline-skills
Asks which skills and agents to install. Just one: npx skills add WILLOSCAR/research-units-pipeline-skills --skill _template_reference_first — add -g for every project.
Claude Code
git clone https://github.com/WILLOSCAR/research-units-pipeline-skillscp -r "research-units-pipeline-skills/.codex/skills/_template_reference_first" ~/.claude/skills/
Copies the _template_reference_first skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add WILLOSCAR/research-units-pipeline-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 108 files.
-
_template_reference_first
Internal template for creating or refactoring a skill into the repository's reference-first shape. **Trigger**: reference-first template, blueprint skill, create a reusable skill, refactor a script-heavy skill. **Use when**: you need a lean `SKILL.md`, explicit `references/`, machine-readable `assets/`, and a minimal deterministic `run.py`.
.codex/skills/_template_reference_first/SKILL.md on GitHub (opens in a new tab) -
agent-survey-corpus
Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.
.codex/skills/agent-survey-corpus/SKILL.md on GitHub (opens in a new tab) -
anchor-sheet
Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.
.codex/skills/anchor-sheet/SKILL.md on GitHub (opens in a new tab) -
appendix-table-writer
Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.
.codex/skills/appendix-table-writer/SKILL.md on GitHub (opens in a new tab) -
argument-selfloop
Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.
.codex/skills/argument-selfloop/SKILL.md on GitHub (opens in a new tab) -
artifact-contract-auditor
Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.
.codex/skills/artifact-contract-auditor/SKILL.md on GitHub (opens in a new tab) -
arxiv-search
Retrieve arXiv paper metadata with keyword queries or import an offline arXiv export, and save results as JSONL (`papers/papers_raw.jsonl`).
.codex/skills/arxiv-search/SKILL.md on GitHub (opens in a new tab) -
beamer-compile-qa
Compile the Beamer tutorial deck and write a build report.
.codex/skills/beamer-compile-qa/SKILL.md on GitHub (opens in a new tab) -
beamer-scaffold
Generate a Beamer slide deck from the final tutorial and approved module structure.
.codex/skills/beamer-scaffold/SKILL.md on GitHub (opens in a new tab) -
bias-assessor
Use when `evidence-review` has an extraction table and needs lightweight risk-of-bias fields.
.codex/skills/bias-assessor/SKILL.md on GitHub (opens in a new tab) -
chapter-briefs
Build per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.
.codex/skills/chapter-briefs/SKILL.md on GitHub (opens in a new tab) -
chapter-lead-writer
Write H2 chapter lead blocks (`sections/S<sec_id>_lead.md`) that preview the chapter's comparison lens and connect its H3 subsections, without adding new facts.
.codex/skills/chapter-lead-writer/SKILL.md on GitHub (opens in a new tab) -
chapter-skeleton
Build a retrieval-informed chapter skeleton (`outline/chapter_skeleton.yml`) from taxonomy/core scope before stable H3 decomposition.
.codex/skills/chapter-skeleton/SKILL.md on GitHub (opens in a new tab) -
checkpoint-brief
Project completed stage Artifacts into a concise human-review block in `DECISIONS.md`; use before a Workflow checkpoint, not for Workflow routing or approval.
.codex/skills/checkpoint-brief/SKILL.md on GitHub (opens in a new tab) -
citation-anchoring
Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.
.codex/skills/citation-anchoring/SKILL.md on GitHub (opens in a new tab) -
citation-diversifier
PRODUCES a citation-budget plan/report (`output/CITATION_BUDGET_REPORT.md`); does NOT edit the draft. Allocates an in-scope per-H3 budget (NO NEW FACTS) so drafts stop failing the global unique-citation gate; citation-injector applies it.
.codex/skills/citation-diversifier/SKILL.md on GitHub (opens in a new tab) -
citation-injector
APPLIES/consumes a `citation-diversifier` budget report (`output/CITATION_BUDGET_REPORT.md`) to inject *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate without citation dumps.
.codex/skills/citation-injector/SKILL.md on GitHub (opens in a new tab) -
citation-verifier
Generate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.
.codex/skills/citation-verifier/SKILL.md on GitHub (opens in a new tab) -
claim-evidence-matrix
Seed `outline/claim_evidence_matrix.md` from outline+notes; claim-matrix-rewriter rewrites it later from evidence packs.
.codex/skills/claim-evidence-matrix/SKILL.md on GitHub (opens in a new tab) -
claim-matrix-rewriter
Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl` rather than outline placeholders.
.codex/skills/claim-matrix-rewriter/SKILL.md on GitHub (opens in a new tab) -
claims-extractor
Use when a review workspace has manuscript text and needs a traceable claim ledger.
.codex/skills/claims-extractor/SKILL.md on GitHub (opens in a new tab) -
concept-graph
Use when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning.
.codex/skills/concept-graph/SKILL.md on GitHub (opens in a new tab) -
dedupe-rank
Use when a broad paper candidate pool needs deterministic deduplication and a stable core set.
.codex/skills/dedupe-rank/SKILL.md on GitHub (opens in a new tab) -
deliverable-selfloop
Score an existing reader-facing deliverable and emit a deterministic PASS/FAIL scorecard plus bounded repair plan; use after synthesis, not to rewrite content.
.codex/skills/deliverable-selfloop/SKILL.md on GitHub (opens in a new tab) -
draft-polisher
Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.
.codex/skills/draft-polisher/SKILL.md on GitHub (opens in a new tab) -
evaluation-anchor-checker
Audit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid underspecified model naming.
.codex/skills/evaluation-anchor-checker/SKILL.md on GitHub (opens in a new tab) -
evidence-auditor
Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.
.codex/skills/evidence-auditor/SKILL.md on GitHub (opens in a new tab) -
evidence-binder
Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.
.codex/skills/evidence-binder/SKILL.md on GitHub (opens in a new tab) -
evidence-draft
Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.
.codex/skills/evidence-draft/SKILL.md on GitHub (opens in a new tab) -
evidence-selfloop
Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.
.codex/skills/evidence-selfloop/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
-
khazix-skillsby KKKKhazix 数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
-
AI-Research-SKILLsby Orchestra-Research Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gem…
-
Wazaby tw93 🥷 Engineering habits you already know, turned into skills AI assistants like Claude Code, Codex and Cursor can run.
-
website-rebuild-skillby boyang-hu 复刻网站的 Agent Skill：抓只读镜像、从压缩代码逐行还原、自动比对验收。An agent skill that mirrors a website, rebuilds it from the minified code, and verifies the result…
-
skill-codexby skills-directory A claude code skill to delegate prompts to codex