CtrlK
BlogDocsLog inGet started
Tessl Logo

daily-papers-fetch

论文抓取(3 步流水线的第 1 步)。抓取 arXiv + HuggingFace 最新论文,打分筛选,富化信息, 输出到 /tmp/daily_papers_enriched.json 供后续 skill 使用。 触发词:"论文抓取"、"跑一下论文抓取" 支持多天模式:"过去3天论文推荐"、"过去一周论文推荐"、"过去一周的论文"、"抓 3 天的论文"、"最近5天"

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, actionable orchestration guide: executable commands, a clear phased workflow with validation checkpoints, and well-organized one-level-deep references to scripts. The main weakness is redundancy between the config sections.

Suggestions

Merge 'Step 0: 读取共享配置' and '配置来源' into a single section — both explain reading ../_shared/user-config.json with local override, so the duplication can be removed to tighten the document.

Trim '注意事项' of items that restate earlier guidance (e.g., '使用 fetch_and_score.py 脚本…零 token 消耗' repeats Phase 1+2), keeping only genuinely new caveats.

The '解析天数' trigger mappings largely repeat the description's multi-day examples; reference them once to avoid carrying the same phrase list in two places.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and structured lists, but the 'Step 0: 读取共享配置' and '配置来源' sections duplicate the same config-source explanation, and '注意事项' partly restates earlier points. Not a 3 because it could be tightened by merging the redundant config sections.

2 / 3

Actionability

Provides fully executable commands with concrete paths — 'python3 ../daily-papers/fetch_and_score.py > /tmp/daily_papers_top30.json' and 'python3 ../daily-papers/enrich_papers.py /tmp/...top30.json /tmp/...enriched.json' — copy-paste ready with the --days N substitution clearly explained. Not a 2 because the guidance is concrete and complete rather than pseudocode.

3 / 3

Workflow Clarity

Clear phased sequence (Step 0 → 解析天数 → Phase 1+2 → Phase 3 → 输出) with explicit validation checkpoints ('**检查输出**:确认 /tmp/daily_papers_top30.json 存在且包含有效 JSON 数组') and error-recovery guidance (stderr diagnosis, arXiv fallback, <20 papers, weekend strategy). Not capped at 2 because validation is present rather than missing for this batch operation.

3 / 3

Progressive Disclosure

Well-organized into clear sections with one-level-deep references to the implementation scripts (fetch_and_score.py, enrich_papers.py) and shared config; no nested document chains. Not a 2 because content is appropriately split and references are clearly signaled.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: concrete multi-action capability statement in third person, explicit natural trigger words with multi-day variations, and a clear, distinct niche within a pipeline. It answers both what and when with no fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '抓取 arXiv + HuggingFace 最新论文,打分筛选,富化信息,输出到 /tmp/daily_papers_enriched.json' — naming the domain and specific pipeline steps. It is not the level below (2), which only names a domain and some actions without being comprehensive.

3 / 3

Completeness

Answers both 'what' (fetch + score + enrich + output to file) and 'when' via explicit trigger guidance ('触发词' and multi-day examples), the equivalent of a 'Use when…' clause. Not capped at 2 because the when-clause is explicit rather than implied.

3 / 3

Trigger Term Quality

Explicit trigger words '论文抓取'、'跑一下论文抓取' plus multi-day variations ('过去3天论文推荐'、'最近5天'、'抓 3 天的论文') give good coverage of phrases a user would naturally say. Not a 2 because common variations are present rather than missing.

3 / 3

Distinctiveness Conflict Risk

Clear niche (arXiv + HuggingFace paper fetching, '3 步流水线的第 1 步') with distinct triggers, unlikely to overlap with unrelated skills. Not a 2 because the niche and triggers are specific enough to avoid overlap.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
huangkiki/dailypaper-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.