MCP App StoreMCP App Store
from rocm-libraries353
Draft or revise pull request titles and bodies into a concise standard format including summary, risk assessment, testing summary, checklist, and technical chan
This skill helps agents draft and refine GitHub pull request titles and bodies into a clear, consistent format. It enforces a structured output (Summary, Risk Assessment, Testing Summary, Testing Checklist, Technical Changes) and provides rules about references, testing claims, and when to create draft vs ready-for-review PRs. The skill is designed to be used alongside repository diffs/PR views so the agent can inspect changes and populate accurate sections.
Use when preparing a new PR, revising an existing draft or open PR, or when the user supplies a PR URL or branch and asks for a PR summary, risk evaluation, testing notes, or a ready-to-paste PR body. Default behaviour is to create drafts unless the user explicitly requests ready-for-review.
gh pr view, git diff --stat), rules for title/reference placement, and checklist rules for testing entries. The skill includes explicit templates and examples to ensure consistent PR text.Agents with GitHub CLI or repo access (agents that can run gh, read diffs, or access branch data), e.g., Copilot-style or CLI-capable agents.
PR Summary is a pure-instruction skill for drafting and revising pull request text in the ROCm/libraries repo. It has no bundled scripts — the entire skill is the SKILL.md, which defines a detailed PR body format with conventional commit titles, risk assessment, ASIC coverage, testing checklists, and technical changes sections. Well-structured and thorough for its specific domain, but tightly scoped to ROCm/AMD GPU library development.
Clean instruction-only skill with no scripts to audit. The SKILL.md is comprehensive and well-organized. The ASIC coverage and blast radius guidance is unusually detailed and domain-specific. No security concerns whatsoever.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
FastAPI Project Templates
Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.
GraphQL Inspector — Validate
Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
JJ Hunk
Programmatic hunk selection for Jujutsu (jj): list, split, commit, or squash specific hunks to enable partial commits and fine-grained history editing without a