daily-papers-review

论文点评（3 步流水线的第 2 步）。读取富化后的论文数据，扫描笔记库，生成有态度的推荐点评，保存推荐文件到 Obsidian，更新 history；git 自动化默认关闭。触发词："论文点评"、"跑一下论文点评"

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/daily-papers-review/SKILL.md

Quality

Content

70%Weight 40%Scale 1-5

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

A dense, actionable workflow with strong sequencing and validation, including feedback loops for the batch save/history operations. Its main weaknesses are monolithic structure with no reference files and a verbose tone/persona section that pads the token budget.

Suggestions

Extract the 点评人设, tone rules, and emoji verdict legend into a references/review-persona.md and link to it, improving progressive disclosure and token efficiency.

Move the full output-structure templates into references/output-template.md, keeping only a compact example inline in SKILL.md.

Trim redundant emphasis in the tone section (e.g. repeated "夸要具体/骂要更具体" phrasing) to lift conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly operational and concrete, but the persona/tone section and the emoji verdict legend are lengthy stylistic padding that could be tightened without losing the skill's intent.	3 / 5
Actionability	Provides concrete file paths, variables, copy-paste markdown output templates, and an executable git command, with only minor placeholder gaps (e.g. YYYY-MM-DD) and a few abstract directives like "按主题分类".	4 / 5
Workflow Clarity	Clear sequenced phases (Step 0 → 前置检查 → Phase 4/5/6) with explicit validation checkpoints and a feedback loop — the history 完整性校验 re-scans when counts mismatch, and git is gated by staged-change checks.	5 / 5
Progressive Disclosure	Well-organized into clear sections but monolithic at ~250 lines with no bundle files; the persona spec, emoji legend, and output templates that could live in separate reference files are all inlined.	3 / 5
	Total	15 / 20 Passed

Description

83%Weight 40%Scale 1-5

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

A concise, well-targeted description that states concrete pipeline actions and supplies explicit trigger words, answering both what and when. It could add a couple of synonym triggers and tighten the vague "有态度的推荐点评" phrasing.

Suggestions

Add 1-2 synonym triggers (e.g. "点评今天的论文") to broaden natural keyword coverage.

Replace the abstract "生成有态度的推荐点评" with a more concrete action phrase such as "为每篇论文生成带评级与锐评的推荐条目".

Reaffirm the step boundary explicitly, e.g. "不生成论文笔记、不抓取论文"，to further reduce conflict with sibling pipeline skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "读取富化后的论文数据，扫描笔记库...保存推荐文件到 Obsidian，更新 history" — covering the full pipeline, though "生成有态度的推荐点评" is somewhat abstract compared to the rest.	4 / 5
Completeness	Clearly answers both what (the read→scan→review→save→history pipeline) and when, via an explicit 触发词 clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides natural phrases users would say — "论文点评" and "跑一下论文点评" — giving good keyword coverage, though only two variants with no synonyms.	4 / 5
Distinctiveness Conflict Risk	The "3 步流水线的第 2 步" positioning carves a clear niche with distinct triggers, but sibling pipeline steps (抓取/笔记) are closely related and pose minor overlap risk.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: huangkiki/dailypaper-skills
Path: skills/daily-papers-review/SKILL.md
Commit: b2f29bb

Reviewed: 23 days ago

Table of Contents

Discovery Implementation Validation

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.