跳到正文
cccskills
免费在 GitHub 公开

snapshot-writer

Use when a `research-brief` workspace has a small paper set plus outline and needs a compact reader-facing briefing instead of a full survey.

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(2)

  • SKILL.md2.1 KB
  • scripts/run.py2.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Snapshot Writer

Triggers & routing

  • Trigger: snapshot, literature snapshot, 速览, 48h snapshot, one-page snapshot, SNAPSHOT.md.
  • Use when: 你要在 research-brief 流程里 24-48h 内交付一个“可读的研究速览”(bullet-first,含关键引用),而不是完整 survey。

Transforms a small core set plus a bullets-only outline into the final research-brief deliverable.

Inputs

Required:

  • outline/outline.yml
  • papers/core_set.csv

Optional:

  • GOAL.md
  • DECISIONS.md
  • queries.md
  • papers/papers_dedup.jsonl

Output

  • output/SNAPSHOT.md

Script boundary

scripts/run.py should stay a thin adapter over shared review tooling:

  • read outline/core-set inputs
  • use the concrete Goal and available abstracts instead of copying survey scaffold bullets
  • select bounded method/result sentences from abstracts; never duplicate full abstracts into multiple sections
  • build a compact pointer-heavy briefing
  • write output/SNAPSHOT.md

Do not move topic-specific ranking rules or deep parsing logic into this script.

Contract

The output should:

  • read like a briefing, not a survey draft
  • stay bullets-first and compact
  • define the topic boundary
  • surface key themes
  • include explicit paper pointers in a stable format

Acceptance

  • output/SNAPSHOT.md exists
  • includes ## Scope, ## Key themes, ## What to read first, and ## Open problems / risks
  • includes at least three explicit paper pointers that resolve to papers/core_set.csv
  • grounds Scope in at least one core-set paper, grounds every Key-theme bullet, and covers at least two unique core-set papers across those sections
  • stays within the Workflow evaluator's 100-1200 word compactness band
  • contains no survey-only scaffolding such as citation quotas, chapter plans, or "why this survey" narration

Non-goals

  • full evidence synthesis
  • protocol / screening / extraction
  • monolithic long-form survey writing

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