with one click
superpower-planning
superpower-planning contains 11 collected skills from SipengXie2024, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Use when designing complex multi-step features, building new components, or planning significant behavior changes that require design exploration before implementation.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when refining design docs and specs through deep questioning. Triggered when user says "help me refine this plan", "ask me about the project", "deep interview", or after brainstorming produces a design doc.
Use when implementing any feature or bugfix, before writing implementation code
Use when delegating coding work — prototyping, debugging, analysis, review, implementation, or generating publication-quality scientific/architecture diagrams — to Codex CLI. Supports multi-turn sessions via SESSION_ID.
Use when starting complex multi-step tasks, research projects, or anything needing >5 tool calls. Provides the persistent .planning/ directory used as on-disk working memory across sessions.
Use when switching to another project, waiting on dependencies, or temporarily setting aside unfinished work.
This skill should be used when the user asks to "ask Hermes", "get a second opinion", "consult another model", or needs independent analysis, research, or code review. It must also run in parallel with Codex for reasoning, analysis, research, and review consultations.
Systematic performance optimization methodology: profile first, fix only the #1 bottleneck, re-profile, repeat. Use when optimizing any program's performance — before writing SIMD, parallelism, caching, or algorithmic rewrites. Also use when someone says 'make it faster', 'this is slow', 'optimize this', 'too slow', 'performance bottleneck', or wants to reduce latency/prove time/build time. Prevents the common trap of guessing bottlenecks (which wastes 10x more code for less speedup). Covers perf record/annotate workflow, A/B testing discipline, contaminated profile diagnosis, and when to stop. NOT for memory leaks (use valgrind/heaptrack) or known algorithmic complexity fixes (O(N^2) → O(N log N)).
Use after completing a plan or when .planning/ has accumulated stale data and needs a clean reset for the next task.
Use when publishing a new version of the plugin.