com um clique
arcanum
arcanum contém 14 skills coletadas de darthjee, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Monitors a given PR for merge/close/approval/new owner comments, blocking until one of those occurs, then reports the outcome. Tracks each owner comment's open/addressed lifecycle with :eyes:/:+1: reactions on the comment itself, but leaves deciding how to address a comment to the caller. Usage: /auto-monitor-pr <pr_number>
Autonomously runs the full pipeline (new issue → plan → fix → monitor) for a queue of issue IDs, one at a time, forever — waiting for new IDs to be pushed onto the queue whenever it runs dry — with no user interaction except when a PR is closed without merging. Usage: /auto-fix-all <id1> <id2> ...
Autonomously implements a planned issue with no user interaction. Discovers the specialist agents involved in the plan, dispatches them in parallel, reviews and re-dispatches until correct, then opens or marks ready a pull request. Usage: /auto-fix-issue <id> or /auto-fix-issue #<id>
Discusses and refines an existing GitHub issue through an iterative dialogue, optionally spawning specialist agents to deepen understanding, then saves a structured markdown issue file and, on confirmation, kicks off planning on a committed branch. Usage: /discuss-issue #19
Resolves the PR for an issue's currently checked-out branch, then monitors it for merge/close/approval/new owner comments, blocking until one of those occurs. Used by auto-fix-all. Usage: /auto-monitor-issue-pr <id>
Configures CLAUDE.md and .github/copilot-instructions.md for a project, creating or updating them to point to a shared AGENTS.md file. Handles multiple scenarios depending on which files already exist. Usage: /init-claude
Creates a implementation plan for a given issue. Reads the issue file, analyzes the codebase, asks clarifying questions, and writes a structured plan in the plans folder. Usage: /plan-issue 99 or /plan-issue #99
Autonomously creates a new issue file in the project's issues folder, without asking the user anything. Parses an optional ID and title, infers a structured description (pre-populating from GitHub when a numeric ID is given), saves the file, commits it, and syncs it to GitHub. Usage: /auto-new-issue #19 - Title or /auto-new-issue Title
Autonomously creates an implementation plan for an existing issue, without asking the user anything. Explores the codebase freely, splits the plan across specialist agents when the target project defines any in .claude/agents/, and commits the result. Usage: /auto-plan-issue <id> or /auto-plan-issue #<id>
Polls GitHub once per cycle for issues created by the current user, writes parsed metadata and tags to a shared JSON state file, and loops — either inline or with a fresh context via ScheduleWakeup when clear_context is enabled. Usage: /monitor-issues (or /loop /monitor-issues for context-clearing mode)
Autonomously drains the monitor-issues rewrite queue, rewriting each queued GitHub issue's body (no user interaction) and removing its pencil2 tag once pushed. Usage: /auto-rewrite-issue
Toggles the clear_context setting for the monitor-issues skill. When enabled and invoked via /loop, the monitor clears its conversation context between polling cycles using ScheduleWakeup. Usage: /toggle-monitor-clear-context
Toggles the clear_context setting for auto-fix-all. When enabled and invoked via /loop, auto-fix-all clears its conversation context between issues using ScheduleWakeup. Usage: /toggle-clear-context
Pushes one or more issue IDs onto the end of the auto-fix-all queue, to be processed later. Usage: /push-issue-to-queue <id1> <id2> ...