535 skills · sorted by relevance
Manage payment permissions for AI agents with spending caps, expiration dates, and merchant rules. Use cryptographic signatures to verify authorization, coordinate approval from multiple agents for high-value purchases, and track or revoke payment permissions.
Scan code that handles sign-in, access permissions, payments, or user data for security weaknesses. The skill provides commands for a full security analysis and focused checks of input validation, which checks whether incoming values are acceptable.
Connect Claude to external apps to send emails, create GitHub issues, post Slack messages, and add notes to Notion. Composio Tool Router selects the appropriate tool and executes the requested action after authorization.
Study Model Context Protocol (MCP), which connects AI applications with external tools, through guided lessons and exercises. Inspect requests and responses, practice implementation and security checks, and record progress alongside observed results.
Research purchases and gifts against needs, budget, fit, and delivery deadlines. Compare exact products, stock, full costs, and return terms, then prepare a cart or complete an order within the user’s authorization.
Review documents before signing or prepare a signing packet with checked recipients, fields, and signing order. Keep sending and signing separately authorized, and verify whether the document is drafted, sent, opened, or fully signed.
Search and work with GitHub repositories through GitHub’s official MCP server, which connects agents to available tools. The skill guides account authorization, repository access selection, and tool use, with separate controls for reading and making changes.
Read and create Evernote notes through its official MCP server, which connects the agent to Evernote tools. The workflow checks connection status, discovers available operations, and requires the relevant approval before creating notes.
Review pending code changes for newly introduced security vulnerabilities with clear exploitation paths. Focus on concrete, significant risks and filter likely false alarms, then report affected files, line numbers, severity, attack scenarios, and recommended fixes in Markdown.
Reviews Cherry Studio code and documentation against product decisions, architecture rules, implementation checks, and conventions. It selects a review approach based on scope and available agents, then reports findings with guidance for fixes.
Implement or review login and access controls for applications and APIs. Helps define token lifetimes, session handling, and permissions for specific resources, with checks for user identity, organization boundaries, credential storage, and authentication failures.
Guide authorized API security assessments from endpoint discovery to documented findings. Use a staged workflow to examine authentication, access permissions, input handling, data exposure, and request limits across REST, GraphQL, WebSocket, and SOAP APIs.
Implement and review API security within an application's existing authentication and data model. Covers token verification, resource permissions, input validation, request limits, secrets, and logging, with concrete checks for unauthorized access and invalid requests.
Assess REST and GraphQL API security through checks of authentication, access permissions, input validation, and request limits. The workflow guides endpoint discovery, testing, and documentation of findings and remediation within an authorized scope.
Create logo concepts from a brand name, industry, or reference image using Beatra’s paid service. The skill guides verified package installation, account authorization, cost approval, and review of the generated artwork.
Document the tools an AI agent may call, including input rules, caller permissions, execution limits, and retry conditions. Produce a tool register and verification plan for reviewing registrations or MCP routing designs.
Organize feedback on an open GitHub pull request, make scoped code fixes, and verify the results. Prepare evidence-backed replies and, when authorized, post responses or resolve individual review threads.
Review authorized source code or pull request changes for security flaws. Combine automated static analysis, which checks code without running it, with manual validation to document affected locations, data flows, reproduction examples, and suggested fixes.
Assess authorized APIs through a ten-stage workflow covering endpoint discovery, authentication, access permissions, input handling, and request limits. Collect reproducible evidence and turn findings into regression checks that can run in a development pipeline.
Organize authorized bug bounty investigations from scope review through reconnaissance, asset discovery, vulnerability testing, and reporting. Use vulnerability-specific guides to prioritize checks and prepare reproducible findings with evidence, impact, and remediation advice.
Set up human approval for Claude Code actions such as PR reviews, merges, and CI changes. Configure Cedar authorization rules and signed records of allowed actions that can be checked offline with a public key.
Plan and implement user login and access permissions using sessions, JWT tokens, or OAuth2. Apply role-based permissions, protect APIs, and review common weaknesses in password handling, cookies, token expiration, and server-side checks.
Identify a project's existing test tools and conventions, then run the smallest useful test suite for a specific change. Add or update tests when authorized, and report commands, results, and remaining gaps without overstating coverage.
Carry a clear, authorized coding request or approved plan through focused changes and appropriate checks. The workflow confirms acceptance criteria, keeps edits small, and reports what changed, what was verified, and what remains unresolved.