Loading...
Loading...
Found 10,137 Skills
Use when reviewing pending todos for approval, prioritizing code review findings, or interactively categorizing work items
Xiaohongshu Comment Public Opinion Analysis and Operation Suggestions. Activate this skill when users provide links to Xiaohongshu notes/videos and need to analyze comment public opinion, user feedback, emotional tendencies, or operation suggestions. This skill should also be activated even if users only say "Help me check the comments on this Xiaohongshu note" or "Analyze how this post is performing".
Set up and run an autonomous experiment loop for any optimization target. Use when asked to start autoresearch or run experiments.
Liondesk integration. Manage Leads, Persons, Organizations, Deals, Pipelines, Activities and more. Use when the user wants to interact with Liondesk data.
Weclapp integration. Manage Organizations. Use when the user wants to interact with Weclapp data.
Edit an existing PRD. Use when the user says "edit this PRD".
Conduct domain and industry research. Use when the user says wants to do domain research for a topic or industry
Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures. Use when the user asks to investigate a bug, find the root cause, trace a regression, understand why something broke, or wants a ranked diagnosis with the fastest proof path without making code edits.
Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.
Use Claude Code to simplify the current pull request by safely reducing unnecessary scope, complexity, and noise while preserving the intended outcome.
Run Codex code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Execution plan generation and management — Plan lifecycle as repository artifact