research-lit

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.

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 ./skills/research-lit/SKILL.md

Quality

Content

62%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 highly actionable with an excellent validated workflow, but it is significantly over-long due to repeated resolver boilerplate and inlined policy prose that already has a referenced home. Factoring the shared resolver and D2 contract into a bundled reference would lift both conciseness and progressive disclosure.

Suggestions

Factor the repeated $ARIS_REPO / $*_FETCHER resolver block into a single sourced helper or a references/ script invoked once, instead of inlining it six times.

Move the inlined D2 tracking-discipline and integration-contract prose into the already-referenced shared-references/integration-contract.md and keep only the operative rule plus the link in SKILL.md.

Add a references/ (or scripts/) bundle file for the verify-papers and wiki-ingest workflows so the SKILL.md body can point to them rather than carrying the full bash blocks inline.

Dimension	Reasoning	Score
Conciseness	The ~750-line body repeats the same 12-line $ARIS_REPO/$FETCHER resolver boilerplate verbatim across six source blocks and inlines lengthy D2 policy prose that has a home in integration-contract.md, which is noticeable padding rather than the "some" that would warrant a 3.	2 / 5
Actionability	Provides concrete, mostly-executable bash blocks, named helper scripts (arxiv_fetch.py, verify_papers.py, research_wiki.py), and an exact MCP call example; minor gaps come from unsubstituted placeholders (QUERY, ARXIV_ID) and prompt-template text.	4 / 5
Workflow Clarity	A clearly sequenced Step 0a–0c/1/1.5/2–6 workflow with explicit validation checkpoints, a mandatory anti-hallucination verification feedback loop (verify → [UNVERIFIED] fallback → surface), a D2 empty-aggregate gate, and a Step-6 checklist for the batch wiki-ingest operation.	5 / 5
Progressive Disclosure	References to shared-references/*.md are one level deep and clearly signaled, but substantial policy content (D2 tracking discipline, integration-contract details, repeated resolver logic) that belongs in those separate files is inlined, and no bundle files exist under references/scripts/assets to offload it.	3 / 5
	Total	14 / 20 Passed

Description

87%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 strong: it states concrete capabilities, provides explicit "Use when" triggers with natural phrasings, and carves out a distinct academic-papers niche. Minor gains are available by adding a few more synonyms and sharpening the generic verbs.

Dimension	Reasoning	Score
Specificity	Names the research-papers domain and lists several concrete actions — "Search and analyze research papers, find related work, summarize key ideas" — but the verbs (analyze, summarize) are somewhat generic, so it sits just below the comprehensive-coverage anchor.	4 / 5
Completeness	Explicitly answers both what (search, analyze, find related work, summarize) and when ("Use when user says …") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases ("find papers", "related work", "literature review", "what does this paper say") with good synonym coverage, though a few common variants (e.g. "survey the literature", "summarize this paper") are missing.	4 / 5
Distinctiveness Conflict Risk	The academic-literature-review niche with its specific triggers ("related work", "literature review") is clearly distinct from other skills and has minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (757 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 7 suspicious	Warning

	Total	12 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/research-lit/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.