nature-literature-pipeline

Complete automated literature discovery pipeline: multi-source search → six-dimension scoring → fine reading → formatted delivery → archival. Combines a configurable engine with daily cron-driven application layer. Works with Feishu, Telegram, or any messaging platform.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/nature-literature-pipeline/SKILL.md

Quality

Content

75%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-organized overview that sequences the pipeline clearly, delegates detail to real one-level-deep reference files, and includes genuine safeguards. The main fixable issues are a broken template reference, a slightly promotional intro sentence, and validation expressed as safeguards rather than in-flow checkpoints.

Suggestions

Fix or remove the dangling reference to `templates/literature-push-template.md` — the file does not exist in the bundle (either ship the template in a `templates/` directory or point to an existing reference).

Trim the promotional opener ("A complete, production-tested... Not just 'search for papers'") — the frontmatter description and pipeline diagram already convey this.

Fold the Built-in Safeguards validation checks (score cap recalculations, triple de-dup) into the ①–⑤ pipeline diagram as explicit per-stage checkpoints rather than a separate properties list.

Dimension	Reasoning	Score
Conciseness	The body is dense and efficient — ASCII pipeline diagram, tables, and terse pitfalls — but the opening line "A complete, production-tested automated literature pipeline. Not just 'search for papers'..." is marketing-flavored redundancy with the frontmatter and diagram that could be trimmed.	4 / 5
Actionability	Quick Start gives copy-paste-ready prompts ("My research area is [X], keywords: [Y]...", "Set up a daily literature push at 08:30...") and the config knobs are concretely listed, but the referenced config template "templates/literature-push-template.md" does not exist in the bundle, leaving a gap in executable guidance.	4 / 5
Workflow Clarity	The five stages are clearly sequenced (①–⑤) and validation mechanisms are named in Built-in Safeguards ("Each dimension capped, total recalculated — no 11/10 allowed", "Triple de-duplication"), but these are stated as properties rather than explicit validate→fix→retry checkpoints embedded in the flow, so it sits just below the top anchor.	4 / 5
Progressive Disclosure	Clean overview body with two tables mapping each reference file to its purpose, and all six `references/*.md` files exist with real content one level deep. The one gap is the broken `templates/literature-push-template.md` reference, which is referenced in Configuration but absent from the bundle.	4 / 5
	Total	16 / 20 Passed

Description

63%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 specific, well-structured description that clearly communicates the five-stage pipeline and its automation character. Its main weaknesses are the absence of an explicit 'Use when...' trigger clause and missing natural keywords like 'papers', 'arXiv', and 'research' that users would actually say.

Suggestions

Append an explicit trigger clause, e.g.: 'Use when the user wants automated daily paper tracking, a literature digest, or scheduled research-paper push notifications.'

Add natural synonyms users would say — 'papers', 'research papers', 'publications', 'arXiv', 'literature digest' — so the skill triggers for users who don't use the word 'literature'.

Dimension	Reasoning	Score
Specificity	The description enumerates five concrete pipeline stages — "multi-source search → six-dimension scoring → fine reading → formatted delivery → archival" — giving comprehensive, specific coverage of what the skill does rather than generic language.	5 / 5
Completeness	The "what" is clear (full pipeline with named stages), but there is no "Use when..." clause or equivalent trigger guidance — "Works with Feishu, Telegram..." describes platform support, not when to invoke the skill, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Terms like "literature discovery", "daily cron", "Feishu", and "Telegram" are relevant, but the description never mentions "papers", "publications", "arXiv", or "research alerts" — natural phrases and synonyms users would say when needing this skill.	3 / 5
Distinctiveness Conflict Risk	The automated daily-pipeline framing ("daily cron-driven application layer") carves a distinct niche vs. ad-hoc search skills, with only minor overlap risk against generic literature-search or search-automation skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Yuan1z0825/nature-skills
Path: skills/nature-literature-pipeline/SKILL.md
Commit: 50851ef

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.