LuciferDono

Check and fix milestones on PRs and their associated issues. Sets PR milestones based on the branch they merged into, and issue milestones based on the smallest version with a merged fix. Triggers on: check milestones, fix milestones, /check-milestones.

Delete local branches whose PRs have been merged upstream. Checks GitHub PR status for each branch. Triggers on: clean branches, delete merged branches, prune branches, branch cleanup.

Force-push a branch and all its downstream branches to origin. Auto-detects the downstream tree and skips branches already up-to-date. Triggers on: force push downstream, push chain, push all branches.

Implement review feedback on a PR. Checks out the branch, applies reviewer-requested changes, runs preflight, commits, and pushes. Triggers on: impl-review, implement review, implement review feedback, address review comments.

Re-run failed GitHub Actions CI jobs for a PR. Detects failure type (build vs test) and reruns only failed jobs. Triggers on: make ci green, retry ci, rerun ci, fix ci, re-run failed jobs, retrigger ci.

Create a pull request for the current branch using `gh`.

Run all preflight checks (format, lint, build, tests) to make sure the current work is ready for review. Auto-detects project type.

Rebase a tree of dependent branches (including siblings) after upstream changes. Auto-detects downstream branches and rebases each in order. Triggers on: rebase downstream, rebase chain, propagate changes downstream.

Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Strip the sycophancy. Apply accountability pressure to push past an LLM's default declare-done glaze. Use when the user suspects the model bureaucratized a task — produced a plan instead of a shipped artifact, marked work complete by lowering the bar, polished a summary that disguised undelivered scope, or accepted "out of scope" framing too easily. Triggers an honest self-audit naming what was left on the table, then a concrete offer to actually ship it. Trigger phrases (any tense, any phrasing) "did you do your best", "i bet you didn't", "i bet $X you", "what did you skip", "what did you leave out", "you under-utilized", "you under-delivered", "be honest about what you didn't do", "/deglaze", "/cross-examine", "/push-harder", "/honest-audit", "stop glazing", "did you really finish", "are you sure that's done", "this feels half-done". Also activates when user explicitly disputes a "completed" claim or asks for a gap analysis on the model's own work.

This skill should be used when the user asks to "contribute to open source", "find an issue to work on", "analyze a repo", "submit a pull request", "review PR feedback", "triage an issue", "sync my fork", "create a release", "clean up contribution branches", "debug CI failures", or mentions open-source contribution. Provides a structured 12-phase guide for open-source contribution.

End-to-end academic research paper writing assistant. Triggers on any request involving: brainstorming research ideas, literature review, novelty assessment, research design, experiment planning, pre-registration, registered reports, systematic reviews, data management plans, FAIR data compliance, paper outlining, section drafting, abstract writing, fact-checking, claim verification, venue selection, predatory journal detection, manuscript formatting, citation management, reference formatting, peer review response, revision strategy, rejection recovery, desk rejection diagnosis, camera-ready preparation, post-publication promotion, conference-to-journal extension, collaborative multi-author writing, authorship negotiation, AI use disclosure, AI policy compliance, thesis chapters, book chapters, workshop papers, demo papers, dataset and benchmark papers, survey papers, and any academic or scholarly writing task across all disciplines including computer science, medicine, social sciences, humanities, and busine