Loading...
Loading...
Found 3,846 Skills
Get completed research task result by run ID
Migrate memory blocks from an existing agent to the current agent. Use when the user wants to copy or share memory from another agent, or during /init when setting up a new agent that should inherit memory from an existing one.
Launch a new OpenSpec change using an experimental artifact workflow. Use this when users want to create new features, fixes or modifications through a structured step-by-step approach.
通过创建下一个产出物继续处理 OpenSpec 变更。当用户想要推进其变更、创建下一个产出物或继续其工作流程时使用。
Clean up local branches after PR merges. Syncs main with origin, identifies branches with merged PRs, and proposes safe deletion. Use when the user asks to 'clean up branches', 'delete merged branches', 'sync branches', or mentions branch cleanup.
Stream-backup active recordings to GitHub. TRIGGERS - backup recording, sync cast, streaming backup.
Manage and analyze Edge tabs and groups with tabctl. Use when asked to list, search, analyze stale or duplicate tabs, generate reports, or organize tabs. Prefer read-only commands and only run mutating actions with explicit targets and confirmation.
Generate infographics from text. Extracts key info, renders SVG, exports PNG. Uses Claude Code (no API costs).
Analyze JIRA tickets to determine priority and dependency order. Outputs an ordered JIRA ID list. Use before implement/forge, or when asked to "prioritize tickets", "order these JIRAs", "what should I work on first".
Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.
Open interactive code review for current changes using Plannotator UI
Retrieve code review results from DeepSource — issues, vulnerabilities, report cards, and analysis runs. Use when asked about code quality, security findings, dependency CVEs, coverage metrics, or analysis status.