daily-papers-notes

论文笔记生成（3 步流水线的第 3 步）。补充概念库，为推荐论文生成完整笔记，链接回填到推荐文件；目录页默认自动刷新，git 自动化默认关闭。触发词："批量笔记"、"跑一下论文笔记"

Quality

74%

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-notes/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 well-sequenced batch workflow with strong validation and feedback loops, giving it excellent workflow clarity. It is held back by repeated anti-laziness prose and by references to external/missing files rather than a clearly organized one-level-deep bundle.

Suggestions

Consolidate the four anti-laziness/quality-warning sections into one canonical checklist to remove repeated tokens.

Add the referenced files (concept-categories.md template, the _shared scripts) into this skill's references/ bundle and link them once with clear one-level-deep navigation.

If user-config.json and the MOC scripts live in a shared location, document that contract in a short references file instead of inlining the paths repeatedly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the anti-laziness warnings are restated across the 铁律, ⚠️质量硬性要求, 🔍质量验证, and 注意事项 sections, adding repetition that could be consolidated.	3 / 5
Actionability	Provides concrete executable commands and numeric thresholds (行数>=120, >=2 LaTeX formulas, >=1 image, git commit command); minor gaps come from references to external files not present in this bundle.	4 / 5
Workflow Clarity	Steps 0-5 are clearly sequenced with explicit validation checkpoints and feedback loops (delete-and-regenerate on quality failure, context-overflow handoff), which is exactly what a batch operation needs.	5 / 5
Progressive Disclosure	Structure is sectioned, but it repeatedly points to external references (../_shared/user-config.json, ../paper-reader/references/concept-categories.md) while this skill's own bundle has no references/scripts/assets, so navigation is not clearly signaled against an actual bundle.	3 / 5
	Total	15 / 20 Passed

Description

78%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 focused, third-person description that conveys both capabilities and explicit trigger terms for a niche pipeline step. It is concise and distinct, with only minor room to expand action coverage and trigger variety.

Suggestions

Add one or two more natural trigger synonyms (e.g. '记一下今天的论文') to broaden keyword coverage toward a 5.

Optionally restate the trigger list as an explicit 'Use when ...' clause so the 'when' guidance is unmistakable.

Dimension	Reasoning	Score
Specificity	Names the domain (paper-note generation) and several concrete actions — '补充概念库', '为推荐论文生成完整笔记', '链接回填到推荐文件', '目录页自动刷新', 'git 自动化关闭' — close to comprehensive but described slightly tersely.	4 / 5
Completeness	Clearly states what the skill does and supplies explicit '触发词' for when to use it; the 'when' is concrete but could be framed as a fuller 'Use when...' clause.	4 / 5
Trigger Term Quality	Provides two natural spoken phrases users would actually say ('批量笔记', '跑一下论文笔记'); good coverage of natural terms though limited variety, so not a full 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to step 3 of a specific 3-step paper pipeline with distinct Chinese triggers, giving it a clear niche and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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

Reviewed: 3 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.