Claude's training data goes stale within weeks of major releases. This skill provides a current reference for Claude AI (web/app) and Claude Code (terminal/IDE) capabilities. Consult these references before making claims about features, limits, or availability.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionclaude-capabilitiesExecute the skills CLI command in your project's root directory to begin installation:
Fetches claude-capabilities from jezweb/claude-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate claude-capabilities. Access via /claude-capabilities in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
697
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
697
stars
Claude's training data goes stale within weeks of major releases. This skill provides a current reference for Claude AI (web/app) and Claude Code (terminal/IDE) capabilities. Consult these references before making claims about features, limits, or availability.
| Capability | Claude AI | Claude Code |
|---|---|---|
| File system | Container sandbox (/mnt/user-data/outputs/) |
Full local filesystem |
| Shell access | None | Bash tool |
| Skills location | Settings > Capabilities (zip upload) | ~/.claude/skills/ or .claude/skills/ |
| MCP connection | UI connectors | claude mcp add / settings.json |
| Subagents | None | Explore, Plan, custom agents, Agent Teams |
| Artifacts | HTML, React, Mermaid, SVG, MD (render inline) | Not available |
| Interactive Apps | Slack, Canva, Figma, Box + 5 more | Not available |
| Web search | Built-in with citations | WebSearch tool |
| File creation | DOCX, PPTX, XLSX, PDF, code files | Any file via Write tool |
| Memory | Cross-conversation (automatic) | CLAUDE.md hierarchy + rules/ |
| Conversation search | conversation_search tool (internal) |
Not available |
| Git integration | Not available | Full git access |
| Deployment | Not available | wrangler, vercel, etc. |
| Question | Read |
|---|---|
| What can Claude AI do? Features, limits, container | references/claude-ai.md |
| What can Claude Code do? Agent Teams, Cowork, hooks | references/claude-code.md |
| Model names, pricing, context windows | references/models.md |
| What changed recently? New features by date | references/changelog.md |
Each reference file has a "Last verified" date at the top. When information seems wrong or outdated:
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
jezweb/claude-skills
jezweb/claude-skills
jezweb/claude-skills
anthropics/skills
aradotso/trending-skills
anthropics/skills
claude-capabilities is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
claude-capabilities fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Keeps context tight: claude-capabilities is the kind of skill you can hand to a new teammate without a long onboarding doc.
claude-capabilities has been reliable in day-to-day use. Documentation quality is above average for community skills.
I recommend claude-capabilities for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Solid pick for teams standardizing on skills: claude-capabilities is focused, and the summary matches what you get after install.
Registry listing for claude-capabilities matched our evaluation — installs cleanly and behaves as described in the markdown.
Solid pick for teams standardizing on skills: claude-capabilities is focused, and the summary matches what you get after install.
Useful defaults in claude-capabilities — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
claude-capabilities has been reliable in day-to-day use. Documentation quality is above average for community skills.
showing 1-10 of 30