od-contribute
One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD;…
Safely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review before committing or pushing follow-up changes.
$ npx -y skills add nexu-io/open-design --skill pr-feedback-quality-gate --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/pr-feedback-quality-gateContext preview
The summary Claude sees to decide when to auto-load this skill.
Safely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review before committing or pushing follow-up changes.
name: pr-feedback-quality-gate description: | Safely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review before committing or pushing follow-up changes. triggers: - "PR feedback" - "review comments" - "merge conflicts" - "cross-review" - "Claude CLI review" - "monitor PR" od: mode: utility
Use this when a PR has review feedback, merge conflicts, pending checks, or needs a monitored follow-up after a fix.
1. Inspect PR state first: comments, reviews, mergeability, checks, branch, and local worktree status. Keep unrelated local changes out of the PR. 2. Use an isolated worktree for review fixes or conflict resolution when the main checkout is dirty, behind remote, or being used by another agent. 3. Make the smallest safe fix. Preserve the original bug invariant and any newer upstream structure introduced by `main`. 4. Run the narrow validation first, then the repository-required gates. For this repo, include `pnpm guard`; add package typechecks/builds/tests when touched files require them. 5. Before commit or push, run a read-only cross-review of the staged or proposed diff. Forbid file edits and git write or coordination commands. 6. Treat cross-review as evidence, not authority. Accept only findings grounded in the diff, repository rules, user goal, or validation results. Downgrade or reject style preferences, broad scope expansion, and suggestions that conflict with safety or ownership boundaries; record the reason briefly. 7. If accepted blockers remain, fix them, rerun validation, and repeat the review. Commit and push only after validation passes and there are no accepted blockers.
regression signals, and stop making code changes unless asked.
Always report PR state, actions taken, cross-review verdict, accepted or rejected findings, validation run, commits pushed, skipped checks with reasons, remaining risks, and next step.
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.
Repo: nexu-io/open-design
One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD;…
Hyperframes-based video template for retro pixel deck motion design. Use when users want a high-fidelity, multi-scene HTML-to-video composition with advanced…
Generate and iterate ad creative including headlines, descriptions, and primary text. Useful for paid social and search ad iteration.
Luxury dark-editorial HyperFrames template for three-page cinematic storyboards, inspired by haute couture title cards and magazine chapter spreads. Use when…
Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages, filling forms, clicking…
Full-lifecycle AI music album production — concept, lyric drafting, track sequencing, and export. Useful for indie album experiments and brand soundtracks.