Safer agent skills

List the contents of an npm package tarball before publishing.

Score basis：Clear source · Risk needs review · Claude

Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before rele

Score basis：Clear source · High risk signals · Claude

Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.

Score basis：Clear source · Risk needs review · Claude

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Score basis：Clear source · High risk signals · Claude

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code.

Score basis：Clear source · High risk signals · Claude

Perform language and framework specific security best-practice reviews and suggest improvements.

Score basis：Clear source · High risk signals · Claude

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean s

Score basis：Clear source · High risk signals · Claude

Transcribe audio files to text with optional diarization and known-speaker hints.

Score basis：Clear source · Risk needs review · Claude

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses,

Score basis：Clear source · High risk signals · Claude

Generate a Codex Super Bowl merch redemption URL (tokenized) and open it.

Score basis：Clear source · Risk needs review · Claude

Audit and improve CLAUDE.md files in repositories.

Score basis：Clear source · Risk needs review · Claude

Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt.

Score basis：Clear source · Risk needs review · Claude

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settin

Score basis：Clear source · Risk needs review · Claude

Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling.

Score basis：Clear source · Risk needs review · Claude

Write structured product requirements documents (PRDs) with problem statements, user stories, requirements, and success metrics.

Score basis：Clear source · Risk needs review · Claude

Profile and explore datasets to understand their shape, quality, and patterns before analysis.

Score basis：Clear source · Risk needs review · Claude

Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing.

Score basis：Clear source · High risk signals · Claude

Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.).

Score basis：Clear source · Risk needs review · Claude

Write and maintain knowledge base articles from resolved support issues.

Score basis：Clear source · Risk needs review · Claude

Prepare for a sales call with account context, attendee research, and suggested agenda.

Score basis：Clear source · High risk signals · Claude

Research a prospect then draft personalized outreach.

Score basis：Clear source · Risk needs review · Claude

Customize or personalize a Claude Code plugin for a specific organization's tools and workflows.

Score basis：Clear source · High risk signals · Claude

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, P

Score basis：Clear source · High risk signals · Claude

Find, connect, and use MCP tools and skills via the Smithery CLI.

Score basis：Clear source · High risk signals · Claude