CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-paper

Paper reader for non-academics. Finds the load-bearing concepts the reader does not yet truly have, rebuilds them through relations and cases, and turns one paper into a bounded model that explains a concrete phenomenon. USE WHEN the user shares an arXiv link OR paper URL OR PDF OR local paper file OR paper title, or asks to read, explain, analyze, or understand a paper. Defaults to a saved org note. NOT FOR experiment reproduction, exhaustive method summaries, formal peer review, benchmark tables, or literature surveys.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ljg-paper/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%Weight 40%Scale 1-3

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

The skill excels at workflow clarity with a sequenced process, model validation checks, and a thorough completion checklist. Its weaknesses are the broken `ReadingGuide.md` reference that undermines both actionability and progressive disclosure, cross-section redundancy that hurts conciseness, and a mix of concrete operational specifics with large amounts of abstract methodology.

Suggestions

Add the missing `ReadingGuide.md` to `references/` (or remove the three '必读 ReadingGuide.md' references) so the core workflow is followable, and delete the leftover `template.org.bak-v6.1.0` so the references directory ships only production files — this fixes both the broken progressive-disclosure reference and the actionability gap.

Consolidate the overlapping restatements across the '概念缺口到解释模型' narrative, the 'Quick Reference' 8 steps, and the 'Completion' checklist into one canonical sequence, then have the others reference it, to cut the redundancy that keeps conciseness at 2.

Move the concrete operational specifics (Denote filename, `date +%Y%m%dT%H%M%S`, the four fixed headings, save path) ahead of the abstract methodology so a reader can begin producing the note without first internalizing the philosophy.

DimensionReasoningScore

Conciseness

The body is dense with novel methodology Claude would not already know (no PDF-style padding), but the '概念缺口到解释模型' narrative, the 8-step 'Quick Reference', and the 'Completion' checklist restate the same concept/model/evidence checks three times, so it could be tightened past anchor 2 toward 3.

2 / 3

Actionability

There are concrete copy-paste specifics (Denote filename '{YYYYMMDDTHHMMSS}--paper-...__paper.org', `date +%Y%m%dT%H%M%S`, the four fixed headings, save path `~/Documents/notes/`, `#+begin_example` ASCII blocks), but the central '必读 `ReadingGuide.md`' directive points at a file absent from the bundle and much of the guidance is abstract methodology, leaving it at anchor 2 rather than fully executable.

2 / 3

Workflow Clarity

The 'Quick Reference' gives a clearly sequenced 8-step workflow, the model's '三次检查' (回到原现象 / 区分邻近情况 / 改变一个条件) act as validation checkpoints, and the 'Completion' section is an explicit end-to-end verification checklist — matching the anchor-3 sequence-with-validation-and-feedback-loops pattern.

3 / 3

Progressive Disclosure

The body is well sectioned and `references/template.org` is a properly signaled one-level reference loaded only when writing org files, but the primary must-read reference `ReadingGuide.md` does not exist in the bundle (a broken reference blocking the core workflow) and a leftover `template.org.bak-v6.1.0` backup clutters the references directory, so it cannot reach anchor 3.

2 / 3

Total

9

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 strong description with explicit what/when structure, natural trigger terms, and a distinctive NOT-FOR boundary that reduces conflict risk. The only weak spot is specificity: the capability verbs are abstract and philosophical rather than concrete operational actions.

DimensionReasoningScore

Specificity

Names the paper-reading domain and several action verbs ('Finds the load-bearing concepts', 'rebuilds them through relations and cases', 'turns one paper into a bounded model'), but the actions are conceptual/philosophical rather than concrete operations like 'extract text, fill forms, merge documents', so it sits at anchor 2 rather than 3.

2 / 3

Completeness

It clearly states what it does ('Finds...rebuilds...turns one paper into a bounded model', 'Defaults to a saved org note') and gives an explicit 'USE WHEN' trigger clause, satisfying both halves required for anchor 3.

3 / 3

Trigger Term Quality

'USE WHEN the user shares an arXiv link OR paper URL OR PDF OR local paper file OR paper title, or asks to read, explain, analyze, or understand a paper' covers the natural terms and verbs a user would actually say, matching the anchor-3 good coverage example.

3 / 3

Distinctiveness Conflict Risk

Triggers are tightly paper-specific (arXiv, paper URL, PDF, paper title) and the 'NOT FOR experiment reproduction, exhaustive method summaries, formal peer review, benchmark tables, or literature surveys' clause carves a clear niche unlikely to conflict with related skills.

3 / 3

Total

11

/

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
lijigang/ljg-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.