Run a GitHub issue end-to-end in this repository using the committed isolated-worktree workflow. Use when the user invokes $gh-task, asks to run a GitHub task, or provides a GitHub issue number, #issue, or issue URL that should be implemented, verified, PR'd, merged, commented, closed, and cleaned up.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add MercurieVV/ScalaSemantic --skill gh-task --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Gh Task?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/mercurievv-gh-task)More formats (shields.io, HTML) on the badges page.
---
name: gh-task
description: Run a GitHub issue end-to-end in this repository using the committed isolated-worktree workflow. Use when the user invokes $gh-task, asks to run a GitHub task, or provides a GitHub issue number, #issue, or issue URL that should be implemented, verified, PR'd, merged, commented, closed, and cleaned up.
---
# GitHub Task
## Overview
Run one GitHub issue through the repository workflow in `docs/commands/gh-task.md`.
Treat that file as the canonical procedure and load it before doing task work.
## Input
Accept a GitHub issue URL, `#123`, or `123`.
Resolve the numeric issue id and use that exact id as the worktree and branch name.
## Workflow
1.Follow `docs/commands/gh-task.md` exactly unless the current user gives a newer conflicting instruction.
2.Keep all implementation work inside `.worktrees/<issue-id>` after the worktree is created.
## Guardrails
- Do not delete or revert unrelated user changes.
- Stop with the exact blocker and current branch/worktree state if credentials, external services, or ambiguous requirements prevent completion.
- Use ScalaSemantic MCP tools for Scala source analysis after compiling, when available.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
