Agent skill

unit-executor

Execute exactly one runnable unit from `UNITS.csv` (first TODO whose dependencies are DONE), then update unit status and artifacts. **Trigger**: unit executor, run one unit, next unit, step-by-step pipeline, 逐条执行, UNITS.csv. **Use when**: 需要严格“一次只做一个 unit”（可审计、可中断），并遵守 checkpoints/HUMAN 阻塞逻辑。 **Skip if**: 要端到端自动跑（用 `research-pipeline-runner`）或 workspace 不存在。 **Network**: none. **Guardrail**: 只执行一个 unit；满足验收且输出存在才可标 `DONE`；遇到 HUMAN checkpoint 必须停下。

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/unit-executor

SKILL.md

Skill: unit-executor

Goal

  • Execute one unit end-to-end and leave the workspace in a consistent state.

Inputs

  • UNITS.csv
  • Unit inputs listed in the row (files)

Outputs

  • Unit outputs listed in the row (files)
  • Updated UNITS.csv status (TODO → DOING → DONE/BLOCKED)
  • Optional: STATUS.md updated

Procedure (MUST FOLLOW)

  1. Load UNITS.csv and find the first unit with:
    • status=TODO
    • all depends_on units are DONE
  2. Set its status to DOING and persist UNITS.csv.
  3. Run the referenced skill (by following that skill’s SKILL.md).
  4. Check the unit’s acceptance against produced artifacts.
  5. If acceptance passes, set status to DONE; otherwise set to BLOCKED with a short note in STATUS.md.
  6. Stop after one unit (do not start the next unit automatically).

Acceptance criteria (MUST CHECK)

  • Exactly one unit changes from TODO to DONE/BLOCKED (via DOING).
  • Output files exist (or acceptance explicitly allows otherwise).

Side effects

  • Allowed: edit workspace artifacts (UNITS.csv, STATUS.md, unit outputs).
  • Not allowed: modify .codex/skills/ content.

Script

Quick Start

  • python .codex/skills/unit-executor/scripts/run.py --help
  • python .codex/skills/unit-executor/scripts/run.py --workspace <workspace_dir>

All Options

  • --strict: enable quality gate (blocks on scaffolds; writes output/QUALITY_GATE.md)

Examples

  • Run exactly one unit (strict):
    • python .codex/skills/unit-executor/scripts/run.py --workspace <ws> --strict
  • Equivalent repo wrapper:
    • python scripts/pipeline.py run-one --workspace <ws> --strict

Notes

  • Returns 0 on DONE/IDLE, 2 on BLOCKED/ERROR (useful for automation).

Troubleshooting

Issue: no runnable unit is found

Fix:

  • Check UNITS.csv for unmet dependencies, missing outputs, or owner=HUMAN units waiting on approvals in DECISIONS.md.

Issue: a unit is marked DONE but outputs are missing

Fix:

  • Fix the status to TODO/BLOCKED and re-run; only mark DONE when acceptance criteria and outputs are satisfied.

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