litbase

Academic paper reading and research development system for biomedical researchers. Finds papers via Semantic Scholar, reads with structured notes, tracks discussion insights, and synthesizes literature into a Research Foundation Document (RFD) for downstream protocol design skills. 8 commands: /setup /feed /read /discuss /recap /update /sync /propose

Quality

75%

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 ./awesome-med-research-skills/Evidence Insight/litbase/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.

The body is a well-organized, mostly lean overview manifest with concrete setup guidance and a clear command lifecycle, but it leans on deferred files that aren't bundled and lacks explicit in-body validation feedback loops. Tightening the intro and surfacing inline reference pointers would lift it further.

Suggestions

Add explicit validate→fix→retry feedback loops for batch/destructive operations such as /sync and rename_pdfs.py directly in the body, rather than relying on the command files.

Convert file-tree references into inline per-section pointers (e.g. 'See [commands/read.md](commands/read.md) for the 4-section note format') so navigation is direct rather than only via the tree.

Trim the redundant opening paragraph that restates the frontmatter description and drop the '200M+ papers across all disciplines' marketing line to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tables and a file tree that assume Claude's competence, but the opening paragraph restates the frontmatter description and '200M+ papers across all disciplines' is marketing padding that could be trimmed, keeping it just below anchor 5.	4 / 5
Actionability	Provides concrete, copy-pasteable guidance — a config.json snippet and the /setup command — plus a command table specifying what each command does and when, but the core paper-processing code is deferred to (un-bundled) command/script files, leaving minor gaps versus fully executable anchor-5 coverage.	4 / 5
Workflow Clarity	The command 'When to use' column lays out a clear lifecycle sequence (setup → feed → read → discuss → recap → update → sync → propose) with verification via /sync's integrity audit and the Literature Integrity rules, but no explicit validate→fix→retry feedback loop is spelled out in the body.	4 / 5
Progressive Disclosure	Clean overview with one-level-deep references signaled in an annotated file tree, but references are conveyed via the tree and backticks rather than inline per-section hyperlinks ('See [X.md](X.md)'), and the referenced bundle files are not actually present, so it sits just below the anchor-5 example.	4 / 5
	Total	16 / 20 Passed

Description

75%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.

The description is specific and highly distinctive with strong command-based triggers, but it omits an explicit 'Use when...' clause, capping its completeness. Adding trigger scenarios and a few synonyms/extensions would round it out.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger scenarios, e.g. 'Use when a biomedical researcher wants to find papers, build structured reading notes, track discussion insights, or draft a research proposal foundation.'

Include common synonyms and file extensions in the description (e.g. 'articles', 'publications', '.pdf', 'DOIs') to broaden natural trigger-term coverage toward anchor 5.

Tighten the trailing command list into a trigger phrase so it signals when (not just what) — currently '8 commands: ...' reads as a feature list rather than usage guidance.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — 'Finds papers via Semantic Scholar, reads with structured notes, tracks discussion insights, and synthesizes literature into a Research Foundation Document (RFD)' — giving comprehensive coverage of the system's capabilities, matching the anchor-5 example.	5 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' clause or equivalent trigger guidance; per the rubric a missing explicit trigger clause caps completeness at 3, matching the anchor-3 example.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('papers', 'literature', 'reading', 'research') plus eight explicit slash-command triggers users would actually type, but it lacks synonyms ('articles', 'publications') and file extensions ('.pdf') required for an anchor-5 rating.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — biomedical literature research via Semantic Scholar producing an RFD for protocol design — with eight distinct slash-command triggers, giving minimal overlap with other skills.	5 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Evidence Insight/litbase/SKILL.md
Commit: 63c61d3

Reviewed: 12 hours 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.