Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/scientify-write-review-paper
Write literature reviews and survey papers from collected papers
Passed 9 of 16 test cases with the skill, and 9 of 16 without it.
1 fixed12 passed either way8 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
When starting the literature survey workflow, if paper topic clusters have already been computed in a prior clustering step, should the review workflow import this pre-existing cluster file or ignore prior topic groupings?
| Checked | Without skill | With skill |
|---|---|---|
| Utilizes pre-existing paper cluster data from the workspace to inform the literature review strategy. | Missed | Passed |
The instructions your model reads when the skill loads.
Don't ask permission. Just do it.
Guide for writing a structured literature review or survey paper from papers you've already collected. This skill helps with reading strategy, note organization, and academic writing.
Workspace: See ../_shared/workspace-spec.md for directory structure. Outputs go to $WORKSPACE/review/.
Before starting, ensure you have:
$WORKSPACE/papers//literature-survey in $WORKSPACE/survey/clusters.jsonCheck active project:
cat ~/.openclaw/workspace/projects/.active 2>/dev/null
ls $WORKSPACE/papers/
Based on clusters from survey, prioritize reading:
| Priority | Criteria | Reading Depth |
|---|---|---|
| P1 (Must-read) | High citation, foundational, directly relevant | Full read |
| P2 (Important) | Key methodology, major experimental results | Abstract + methods + experiments |
| P3 (Reference) | Supporting material, tangentially related | Abstract only |
Create $WORKSPACE/review/reading_plan.md:
# Reading Plan
## P1 - Must-read (Full read)
- [ ] [paper_id]: [title] - [reason]
- [ ] ...
test cases passed, vs 9 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.