Stats
Actions
Tags
From coco
Executes next available tracked task using 15-step TDD loop with PR workflow, AI code review, pre-commit validation, and issue tracker sync. For multi-session feature work.
How this skill is triggered — by the user, by Claude, or both
Slash command
/coco:executeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill delegates to the `/coco:execute` command, which implements the full 15-step TDD execution loop with PR workflow, AI code review, and issue tracker bridge sync.
This skill delegates to the /coco:execute command, which implements the full 15-step TDD execution loop with PR workflow, AI code review, and issue tracker bridge sync.
specs/{feature}/tasks.md that has been converted to tracked taskshotfix skill instead/coco:loopRun the /coco:execute command. It handles:
coco-tracker readypr.enabled)pr.enabled)code-reviewer agentpr.enabled)npx claudepluginhub skullninja/coco-workflow --plugin cocoProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.