Back to search
Claude-skill-research-
SkillWorks with Claude CodeGitHub
Claude skill: PRISMA systematic review → engineering manuscript
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/oussamachr--claude-skill-research)HTML
<a href="/listings/oussamachr--claude-skill-research"><img src="/api/listings/oussamachr--claude-skill-research/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
- **Claude Code**: copy `prisma-engineering-review/` to `~/.claude/skills/` (personal) or `.claude/skills/` (project). - **Claude.ai**: upload `prisma-engineering-review.skill` under Settings → Capabilities → Skills.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 32 lines
- # Claude skill: PRISMA systematic review → engineering manuscript
- `prisma-engineering-review/` is a Claude skill. It carries out a **PRISMA 2020 systematic literature review** in any engineering field and writes it up as a **manuscript ready to submit to a journal or conference**.
- ## What it does
- 1. **Scoping**: PICOC research questions, a check for existing reviews, the choice of review type (systematic, scoping or mapping), adapted to the subfield (12 engineering profiles).
- 2. **Protocol** (PRISMA-P) with eligibility criteria that have IDs, ready to register on OSF.
- 3. **Search**: database-specific Boolean strings (Scopus, WoS, IEEE Xplore, Compendex, ACM, ScienceDirect), live searches of OpenAlex, Crossref, arXiv and Semantic Scholar, and import of Scopus, WoS and IEEE exports.
- 4. **Deduplication**, **two-stage screening** with logged reason codes, and an inter-rater **Cohen's κ**.
- 5. **Quality appraisal** with engineering checklists (experimental, simulation, ML, optimisation, case study) and adapted GRADE.
- 6. **Data extraction** template and **synthesis**: taxonomy, SWiM narrative, or meta-analysis when it's justified.
- 7. **PRISMA 2020 flow diagram** (SVG + TikZ) generated from the logs, with arithmetic checks, and the 27-item checklist.
- 8. **LaTeX manuscript** (IEEE, Elsevier, Springer, ASME, ACM or MDPI), BibTeX built only from records actually retrieved, and **reference verification** against Crossref.
- 9. **Pre-submission audit.**
- It keeps the work honest: it never fabricates references, takes every number in the flow diagram from the logs, and discloses AI-assisted screening.
- ## Install
- - **Claude Code**: copy `prisma-engineering-review/` to `~/.claude/skills/` (personal) or `.claude/skills/` (project).
- - **Claude.ai**: upload `prisma-engineering-review.skill` under Settings → Capabilities → Skills.
- ## Scripts (Python 3 standard library only)
- | Script | Purpose |
- |---|---|
- | `search.py` | API search, import of database exports, BibTeX export |
- | `dedup.py` | DOI and fuzzy-title deduplication |
- | `screening.py` | PRISMA counts, Cohen's κ, audit samples |
- | `prisma_flow.py` | PRISMA 2020 flow diagram (SVG + TikZ) |
- | `bibliometrics.py` | Charts of publications per year, venues and keywords |
- | `verify_refs.py` | Crossref DOI and title check, cite-key consistency |
- Example prompt: *"Do a PRISMA systematic review on machine-learning fatigue-life prediction for additively manufactured metals and write it as a review paper for the International Journal of Fatigue."*
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.