'Get PRs a user reviewed on brave/brave-core. Shows PR number, title, author, what did I review, review history.'
npx skills add https://github.com/brave/brave-core --skill prs-reviewed
Query GitHub for pull requests a user has reviewed on brave/brave-core within
a given time window.
The skill receives arguments in the format: <username> <num>d
<username> — GitHub username (e.g., netzenbot)<num>d — Number of days to look back from now (e.g., 3d means last 3 days)Both arguments are required. If missing, ask the user for them.
Calculate the start date by subtracting <num> days from today's date, then use
the GitHub CLI to search for reviewed PRs:
gh api --paginate "search/issues?q=type:pr+repo:brave/brave-core+reviewed-by:<username>+updated:>%3D<YYYY-MM-DD>&per_page=100" --jq '.items[] | {number, title, user: .user.login, state, pull_request: .pull_request.html_url, updated_at}'
Where <YYYY-MM-DD> is the computed start date.
Important: The updated:>= filter is a rough filter. After fetching
results, you must verify each PR was actually reviewed by the user within the
requested window by checking review timestamps:
gh api "repos/brave/brave-core/pulls/<number>/reviews" --jq '[.[] | select(.user.login == "<username>")] | sort_by(.submitted_at) | last | .submitted_at'
Only include PRs where the user's most recent review falls within the requested
time window.
Display results in a markdown table:
| PR | Title | Author | State | Reviewed |
| ------------ | ---------------- | ------ | ------ | ---------- |
| #1234 | Fix crash in ... | author | merged | 2026-02-25 |
#number formatpull_request.merged_at todistinguish merged from closed)
Sort by review date, most recent first.
After the table, show a summary: "N PRs reviewed by @username in the last
Md"
brave/brave-core"
gh is not authenticated, inform the user to run gh auth loginIntegration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take brave/prs-reviewed from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.