跳到正文
cccskills
免费在 GitHub 公开

idea-shortlist-curator

Converge the screened direction pool into a small, discussion-ready shortlist, writing `output/trace/IDEA_SHORTLIST.md`.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(5)

  • SKILL.md1.9 KB
  • assets/rationale_templates.json2.0 KB
  • references/overview.md1.5 KB
  • references/ranking_rubric.md1.2 KB
  • scripts/run.py10.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Idea Shortlist Curator

Triggers & routing

  • Trigger: idea shortlist, shortlist directions, brainstorm shortlist, 方向 shortlist.
  • Use when: you already have a direction pool and screening table and want the strongest 3-5 directions for the final memo.

Load Order

Always read:

  • references/overview.md

Read by task:

  • references/ranking_rubric.md when customizing risk notes or deferral reasons
  • assets/rationale_templates.json when changing deterministic shortlist rationale wording or rule order

Script Boundary

Use scripts/run.py only for:

  • diversity-aware greedy selection from screened rows
  • deterministic ranking record assembly and JSONL/Markdown output

Do not treat run.py as the place for:

  • domain-specific risk narratives that should be inspectable from references
  • reader-facing prose templates for the final memo (those belong in idea-memo-writer)

Goal: turn a direction pool into a small shortlist that is:

  • explicitly ranked with a real why-#1>#2>#3 argument,
  • diverse in program shape rather than just cluster labels,
  • specific about why deferred directions are not in the lead set,

and remains:

  • academically interesting,
  • distinct enough to compare,
  • grounded enough to discuss,
  • and not yet overfrozen into project plans.

Script

Quick Start

  • uv run python .codex/skills/idea-shortlist-curator/scripts/run.py --workspace <workspace>

All Options

  • --workspace <dir> (required)
  • --unit-id <U###>
  • --inputs <semicolon-separated>
  • --outputs <semicolon-separated>
  • --checkpoint <C#>

Examples

  • Curate a shortlist for a brainstorm workspace:
    • uv run python .codex/skills/idea-shortlist-curator/scripts/run.py --workspace workspaces/brainstorm-llm-agents

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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`.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

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.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

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.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

查看 WILLOSCAR 的全部技能

报告此技能的问题