Loading...
Loading...
Found 696 Skills
Generate concise PR descriptions by analyzing the diff against a base branch
Optimizes algorithms via autoresearch loop: benchmark, research, hypothesize, keep/discard
Implement a single user story or task from a GitHub Issue backlog. Executes a single Ralph Loop iteration by fetching the next open issue, assigning it, implementing the code, creating a branch and PR, and moving on. You MUST use this skill when asked to "implement a user story", "run one iteration", "do the next task", "execute a ralph loop iteration", or "complete a task from the backlog".
Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.
Generate clear, conventional commit messages from staged changes. Use when the user asks to commit or needs a commit message.
Create an appropriate git commit from the working tree and session history. Default commit messages are in Japanese unless the repo says otherwise (e.g. AGENTS.md).
Execute work efficiently while maintaining quality and finishing features
Commit, push, and open a pull request in Azure DevOps. Use whenever the user wants to open, update, or draft a PR and the project is hosted on Azure DevOps (`dev.azure.com`, `visualstudio.com`, or explicit mentions of ADO, Azure Repos, or work item IDs like `AB#1234`). Links work items to the PR, sets reviewers, and supports draft-by-default.
Detect new or modified skills in .agents/skills/ by comparing git hashes against ai-skills, snapshot for rollback, review, publish to ai-skills, install locally, and cherry-pick lockfile to TARGET. Replaces /elevate-skill.
Use when creating a GitHub pull request or merge request from the current branch, especially when a project PR template may exist.
Take an Azure Boards work item from "read it" to "PR open, Pipelines green, review comments addressed, work item updated" with maximum autonomy. Reads the work item and its discussion through either the Azure DevOps MCP server or the `az` CLI; grills you on the design decisions the item left open; explores the repo; drafts a plan and puts it through a three-lens adversarial review; asks for your approval through plan mode when the change warrants it and skips it when it doesn't; then implements test-first, runs your repo's own gates, opens an Azure Repos PR, and babysits it to green. Stack-agnostic — assumes no particular architecture. Invoke with `/arkandia:ado-plan-build [work item id | URL] [skip-checkpoint]`.
Implement one GitHub Issue at a time — tests, review, gates, commit. Never mirror tickets to disk.