BubbleBuffer
19 verified skills17 total stars
using-git-branches
Use when starting feature work that needs git isolation or before writing committed spec, plan, or code artifacts
development2
brainstorming
Use when defining or changing behavior and the work has not yet been designed, approved, and scoped
data-ai2
using-superpawers
Use when deciding which SuperPawers skill should govern a new task or workflow step, before taking any other action
development2
finishing-a-development-branch
Use when implementation is complete and you need to handle branch completion - merge, PR, keep, or discard
development2
writing-plans
Use when a request involves multiple steps or files, or when an approved design must be turned into a detailed implementation plan
data-ai2
subagent-driven-development
Use when a task list exists or is being created for multi-step implementation work, whether from a formal plan or an ad-hoc breakdown
development2
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
development1
finishing-a-workspace
Use when implementation is complete and you need to handle workspace completion - merge, PR, keep, or discard
tools1
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
testing1
use-superpawers-subagents
Use when about to research, review, implement, or verify — before dispatching generic subagents (explore, general) or doing subagent-worthy work inline. Always dispatch superpawers subagents instead.
testing1
using-workspaces
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated workspace with smart base branch detection
tools1
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
development
root-cause-tracing
Use when an error appears deep in the call stack, when invalid data reaches a function and the source is unclear, or when you need to find which test or code path triggers a problem
development
dispatching-parallel-agents
Use when facing 2+ independent tasks or investigations that can be worked on without shared state or sequential dependencies
testing
condition-based-waiting
Use when tests have race conditions, timing dependencies, or pass and fail inconsistently, especially when tests use arbitrary delays like setTimeout or sleep
testing
defense-in-depth
Use when a fix validates at only one point in the data flow, when a bug could recur through different code paths, or when the same invalid data could reach internal functions from multiple callers
development
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
development
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
development
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
data-ai