Agent skill

pipeline-router

Select the most appropriate pipeline for a user goal, lock it in `PIPELINE.lock.md`, and route checkpoint questions into `DECISIONS.md`. **Trigger**: pipeline router, choose pipeline, workflow selection, PIPELINE.lock.md, 选择流程. **Use when**: 用户目标/交付物不清晰，需要在 snapshot/survey/tutorial/systematic-review/peer-review/idea-brainstorm 中选一个并设置最小 HITL 问题集。 **Skip if**: pipeline 已锁定（`PIPELINE.lock.md` 存在）且所需问题已回答/签字完成。 **Network**: none. **Guardrail**: 尽量一次性提问；信息不足就写 `DECISIONS.md` 并停下等待。

View SKILL.md on GitHub Repository
Stars 377
Forks 25

Install this agent skill to your Project

npx add-skill https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/pipeline-router

SKILL.md

Pipeline Router

“Routing” usually means two different things:

  • Pipeline selection + lock: choose a single pipeline and write PIPELINE.lock.md.
  • Checkpoint routing: keep the run auditable by drafting/updating checkpoint blocks in DECISIONS.md (and, for C0, seeding queries.md from GOAL.md).

This skill supports both, but keeps the semantic choice LLM-first and the repetitive checkpoint scaffolding scriptable.

Inputs

Workspace context (when available):

  • GOAL.md
  • STATUS.md
  • DECISIONS.md
  • PIPELINE.lock.md

Optional template:

  • assets/pipeline-selection-form.md

Outputs

  • PIPELINE.lock.md (Mode A; selection + lock)
  • Updates to DECISIONS.md (all modes; checkpoint blocks + approvals checklist)
  • queries.md (best-effort for C0; seeded from GOAL.md)
  • Optional: updates to STATUS.md

Decision tree (selection)

User goal → choose:

  • “survey / 综述 / 调研” → pipelines/arxiv-survey.pipeline.md
  • “survey + PDF / LaTeX / 可编译” → pipelines/arxiv-survey-latex.pipeline.md
  • “tutorial / 教程” → pipelines/tutorial.pipeline.md
  • “systematic review / PRISMA / 系统综述” → pipelines/systematic-review.pipeline.md
  • “peer review / 审稿” → pipelines/peer-review.pipeline.md
  • “idea / ideation / brainstorm / 找 idea / 选题 / 点子” → pipelines/idea-brainstorm.pipeline.md
  • “snapshot / 速览” → pipelines/lit-snapshot.pipeline.md

Workflow

Mode A — selection + lock (LLM-first)

  1. Read the goal from GOAL.md (or the user message).
  2. If key details are missing, use assets/pipeline-selection-form.md to draft a concise question list into DECISIONS.md and stop.
  3. Select exactly one pipeline under pipelines/*.pipeline.md.
  4. Write PIPELINE.lock.md with:
    • pipeline: <path>
    • units_template: <path from pipeline front matter>
    • locked_at: <YYYY-MM-DD>
  5. Update STATUS.md (“Current pipeline” + checkpoint).

Mode B — checkpoint blocks (script helper)

Use the helper to keep DECISIONS.md in sync with checkpoints:

  • Kickoff questions + seed queries (C0):
    • python .codex/skills/pipeline-router/scripts/run.py --workspace <ws> --checkpoint C0
  • Scope/outline approval summary (C2):
    • python .codex/skills/pipeline-router/scripts/run.py --workspace <ws> --checkpoint C2
  • Other checkpoints:
    • python .codex/skills/pipeline-router/scripts/run.py --workspace <ws> --checkpoint C1

Quality checklist

  • DECISIONS.md has a checkpoint block for the active C*.
  • Approvals checklist exists and includes Approve C* checkboxes.
  • If selection was needed, PIPELINE.lock.md points to exactly one pipeline file.
  • If the run is retrieval-based, queries.md is non-empty after C0 seeding.

Side effects

  • Allowed: create/update PIPELINE.lock.md; edit STATUS.md; append/update DECISIONS.md; seed queries.md.
  • Not allowed: modify files under .codex/skills/ assets/templates.

Script

Quick Start

  • python .codex/skills/pipeline-router/scripts/run.py --help
  • python .codex/skills/pipeline-router/scripts/run.py --workspace <workspace_dir> --checkpoint C0

All Options

  • --checkpoint <C0|C1|C2|...>: which checkpoint block to draft/update (unknown checkpoints get a generic template)

Examples

  • Kickoff questions + seed queries:
    • python .codex/skills/pipeline-router/scripts/run.py --workspace <ws> --checkpoint C0
  • Generic protocol approval block (systematic review C1):
    • python .codex/skills/pipeline-router/scripts/run.py --workspace <ws> --checkpoint C1
  • Scope/outline approval summary:
    • python .codex/skills/pipeline-router/scripts/run.py --workspace <ws> --checkpoint C2

Notes

  • python scripts/pipeline.py kickoff|init writes PIPELINE.lock.md and then (best-effort) runs this script for C0.
  • The script reads PIPELINE.lock.md (if present) to display the pipeline in the kickoff block; it does not choose the pipeline.

Troubleshooting

Issue: PIPELINE.lock.md points to one pipeline but UNITS.csv looks like another

Cause:

  • Workspace was initialized from one pipeline and later re-pointed without updating UNITS.csv.

Fix:

  • Re-run python scripts/pipeline.py init --workspace <ws> --pipeline <name> --overwrite-units, or copy the correct templates/UNITS.*.csv into UNITS.csv.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

WILLOSCAR/research-units-pipeline-skills

thesis-compile-review

对中文毕业论文进行编译、warning 分级、模板模式检查、数据与引用复查，并把问题回写成可继续迭代的 review checklist。 **Trigger**: 毕业论文编译检查, thesis compile review, warning 分级, 终稿复查, main.pdf 检查. **Use when**: 论文已经回写到 TeX 交付层，需要确认是否真正达到“可提交”的质量，而不是只做到能编译。 **Skip if**: 还处于中间层重构阶段，`chapters/*.tex` 尚未形成稳定交付稿。 **Network**: none. **Guardrail**: 不在这里重构章节主线；如果发现结构问题，明确回退到上游修复。

377 25
Explore
WILLOSCAR/research-units-pipeline-skills

front-matter-writer

Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation density and a single evidence-policy paragraph. **Trigger**: front matter writer, introduction writer, related work writer, abstract writer, discussion writer, conclusion writer, 引言, 相关工作, 摘要, 讨论, 结论. **Use when**: you are in C5 (prose allowed) and need the paper-like shell to stop the draft reading like stitched subsections. **Skip if**: `Approve C2` is missing in `DECISIONS.md`, or `citations/ref.bib` is missing. **Network**: none. **Guardrail**: no invented facts/citations; no pipeline jargon in final prose; no repeated evidence disclaimers; only use keys present in `citations/ref.bib`.

377 25
Explore
WILLOSCAR/research-units-pipeline-skills

thesis-question-list

维护中文毕业论文的 `codex_md/question_list.md`：把本轮问题、边界、优先级、协作方案和验收口径结构化，作为整条 thesis pipeline 的控制面。 **Trigger**: 毕业论文问题清单, thesis question list, 论文修改清单, 本轮目标, 结构问题梳理, review问题整理. **Use when**: 你已经有一批材料或上一轮 review 结果，需要明确这一轮到底修什么、不修什么，并给后续重构与编译复查提供统一入口。 **Skip if**: 当前只是在做一次性局部措辞修改，且没有形成新一轮结构/证据/编译问题。 **Network**: none. **Guardrail**: 不在这里写正文；不把问题单写成长篇散文；每条问题必须可执行、可验收。

377 25
Explore
WILLOSCAR/research-units-pipeline-skills

novelty-matrix

Create a novelty/prior-work matrix comparing the submission’s contributions against related work (overlaps vs deltas). **Trigger**: novelty matrix, prior-work matrix, overlap/delta, 相关工作对比, 新颖性矩阵. **Use when**: peer review 中评估 novelty/positioning，需要把贡献与相关工作逐项对齐并写出差异点证据。 **Skip if**: 缺少 claims（先跑 `claims-extractor`）或你不打算做新颖性定位分析。 **Network**: none (retrieval of additional related work is out-of-scope unless provided). **Guardrail**: 明确 overlap 与 delta；尽量给出可追溯证据来源（来自稿件/引用/作者陈述）。

377 25
Explore
WILLOSCAR/research-units-pipeline-skills

protocol-writer

Write a systematic review protocol into `output/PROTOCOL.md` (databases, queries, inclusion/exclusion, time window, extraction fields). **Trigger**: protocol, PRISMA, systematic review, inclusion/exclusion, 检索式, 纳入排除. **Use when**: systematic review pipeline 的起点（C1），需要先锁定 protocol 再开始 screening/extraction。 **Skip if**: 不是做 systematic review（或 protocol 已经锁定且不允许修改）。 **Network**: none. **Guardrail**: protocol 必须包含可执行的检索与筛选规则；需要 HUMAN 签字后才能进入 screening。

377 25
Explore
WILLOSCAR/research-units-pipeline-skills

rubric-writer

Write a rubric-based peer review report (`output/REVIEW.md`) using extracted claims and evidence gaps (novelty/soundness/clarity/impact). **Trigger**: rubric review, referee report, peer review write-up, 审稿报告, REVIEW.md. **Use when**: peer-review pipeline 的最后阶段（C3），已有 `output/CLAIMS.md` + `output/MISSING_EVIDENCE.md`（以及可选 novelty matrix）。 **Skip if**: 上游产物未就绪（claims/evidence gaps 缺失）或你不打算输出完整审稿报告。 **Network**: none. **Guardrail**: 给可执行建议（actionable feedback），并覆盖 novelty/soundness/clarity/impact；避免泛泛而谈。

377 25
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results