SKILLEMALL.ai
GitHub ↗ RU Sign in

AF deep-literature-review-agent

Run a multi-source, agentic literature review with real citations. Searches arXiv, Semantic Scholar Open, OpenAlex, and Crossref; deduplicates; screens abstracts against user-defined inclusion criteria; extracts findings + methods per paper; synthesizes a thematic review.md with BibTeX. Trigger when the user asks for a "literature review", "lit review", "survey the field on X", "systematic review", or "find me N papers on Y".

genspark Agent Skills author: Genspark 1 file body ≈ 1 838 tokens Open the sourcegenspark.ai↗ analyzed 3 d ago

As a process F 70/100 · Will not run — References files that are not bundled: assets/review_template.md, scripts/search_multi.py, scripts/dedupe.py

AnalyzerResearchAI and agentstype and topics are labelled automatically from the skill text
Runs in: Genspark Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
F
70/100
Will not run
References files that are not bundled: assets/review_template.md, scripts/search_multi.py, scripts/dedupe.py
Tools and files w 18
0
Result and completion w 14
60
When it triggers w 12
70
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: assets/review_template.md
  • warning missing-ref reference to a missing file: scripts/search_multi.py
  • warning missing-ref reference to a missing file: scripts/dedupe.py
  • warning missing-ref reference to a missing file: scripts/extract.py

Process rating: all ten parameters 70/100

Will not run. References files that are not bundled: assets/review_template.md, scripts/search_multi.py, scripts/dedupe.py
  • 0Tools and files. 4 referenced file(s) missing: assets/review_template.md, scripts/search_multi.py, scripts/dedupe.py
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 38 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1838 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 5 example trigger phrases
  • +3Description length 429: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 38 items
  • +3Output format is stated explicitly
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.