Loading...
Loading...
Found 8 Skills
Run a gated software development lifecycle for a repo. Use for `/jig init` (understand the codebase and scaffold project memory), `/jig task "<request>"` (start an issue/bug/feature through spec→implement→test→review→ship), `/jig status`, `/jig config` (view/set/validate settings), `/jig memory-refresh`, and `/jig resume`. Triggers on "jig", "run the lifecycle", "start a task", "sdlc", "sdlc init/status".
Create a new git branch and worktree at ../{repo}.worktrees/{slug}. Use when the user wants to start isolated work on a new branch without switching the main checkout. Invoke as /worktree <branch-name>.
Create automatically creates new AI assistant code plugins with proper structure, validation, and marketplace integration when user mentions creating a plugin, new plugin, or plugin from template. specific to AI assistant-code-plugins repository workflow. Use when generating or creating new content. Trigger with phrases like 'generate', 'create', or 'scaffold'.
AI SDLC evidence-backed project context and bounded task-pack workflow. Use when an AI assistant needs to onboard to a repository, detect stack and commands, map ownership and test topology, check context drift, conditionally select task sources, exclude secrets, or allocate a freshness-aware context pack within an explicit token budget. Supports `--quick-flow` for focused evidence and `--full-flow` for stricter repository coverage.
Implement an agreed task incrementally and verify the result.
Reduce avoidable Codex token and context usage in long-running or repository-scale work by minimizing repeated reads, inefficient polling, context drift, and unnecessary high-capability model use. Apply when users ask to save Codex quota, streamline a long task, or make an agent workflow more context-efficient; do not apply to ordinary short tasks that need no optimization.
Read-only router for "which skill should I use?", "what do I do next?", "how do I do X here?". Builds the answer at run time from the repo's AGENTS.md Task Router, the skills actually installed, optional repo workflow data, and knowledge sources — then recommends and hands back control. Never runs the pipeline itself.
Author in-repo SKILL.md files: frontmatter and structure.