From dfrysinger-skills
Guardrails for agent-initiated, externally-visible GitHub writes — filing issues, opening pull requests, posting comments, and pushing to repos the user does not own. Use when about to create or mutate anything visible to other people on GitHub (especially upstream/third-party repos), or when an offered menu option bundles such an action.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dfrysinger-skills:autonomous-github-actionsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Externally-visible GitHub writes are **not free background actions**. Filing an
Externally-visible GitHub writes are not free background actions. Filing an issue, opening a PR, posting a comment, or pushing to a repo the user does not own is visible to other people and is often hard to cleanly undo. Treat every such action as requiring explicit, specific user approval — not implied consent from a broad "go ahead."
upstream/project is a separate action that needs its own yes.gh search prs --owner <org> ...,
not just gh search issues --repo <one-repo>).gh issue create, gh pr create, gh ... comment, or push to a
remote you don't own.If any answer is unclear, stop and ask, quoting the exact text you would post and the exact target repo.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub dfrysinger/skills