Browse Skills

Turns a GitHub issue into a triaged and implemented pull request. Classifies bug reports, feature requests, and questions, then follows a structured development chain to produce a reviewed PR.

Applies Hyperflow's orchestration doctrine in single-agent environments like Codex, Antigravity, or Grok. Enables structured multi-phase workflows (plan, dispatch, audit, deploy) for building, refactoring, and debugging by adapting to the host's capabilities.

Manages two-session handoff packages: plan in one session, build in another, and review back in the first. Use for inspecting, picking up, or reviewing committed handoff packages across environments.

Manually flush a deferred-commit queue from a chain that was interrupted before auto-flush. Recovers pending Git commits by fast-forwarding the staging branch onto the user's branch, preserving commit SHAs and order.

Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy.

Systematic, research-grounded product design that avoids generic AI aesthetics. Creates or extends design systems, researches real-world prior art, and produces design specs with accessibility checks.

Runs lint, typecheck, build, test, and security checks before committing, releasing, and pushing code. Requires explicit confirmation for push, never auto-invoked.

Provides CRUD operations for project-scoped hyperflow memory entries, allowing agents to store, search, and maintain knowledge without modifying source code.

Embeds hyperflow's behavioral doctrine (autonomy, intent-routing, commit cadence, role separation) into CLAUDE.md so it applies in Claude Code Desktop, web, or IDE extensions that don't load CLI plugins. Useful for consistent AI agent behavior across surfaces.

Lists, shows, cancels, and prunes background agents fired by Hyperflow skills. Use to inspect agent status, collect results, or clean up old output buffers.

Performs multi-level code review on recent changes, checking syntax, security, performance, and spec compliance. Offers to automatically apply findings via the fix gate that triggers planning and dispatch.

Notion-as-source-of-truth dispatch board that manages AI tasks through a five-stage workflow (Suggestion to Done) and fans out approved To-Do items to parallel agents with per-task model selection.