Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Expert in decision-making frameworks - systematic approaches to making better decisions under uncertainty. Covers decision criteria, reversibility assessment, stakeholder alignment, and decision documentation. Knows when to decide fast and when to deliberate. Use when "decision framework, how to decide, making a choice, tradeoff, should we, pros and cons, decision matrix, weighing options, " mentioned.
Founders face unique challenges in how they work. Maker vs manager schedule conflicts. Default alive vs dead math. Time and money slowly leaking away. Effective founders develop systems for navigating these challenges. This skill synthesizes PG's essays on founder productivity and decision-making into an operating system for founder effectiveness. Use when "keywords, contexts, " mentioned.
Expert in protecting projects from scope creep. Covers requirement management, stakeholder negotiation, saying no diplomatically, and keeping projects focused. Understands that scope creep kills more projects than technical debt. Use when "scope creep, feature request, can we also, while you're at it, one more thing, requirements changed, scope management, " mentioned.
Expert in actually finishing and shipping side projects. Covers MVP scoping, motivation management, perfectionism killing, and the art of "good enough." Understands why side projects die and how to keep them alive long enough to ship. Use when "side project, ship it, just launch, weekend project, finish my project, perfectionism, MVP, " mentioned.
Strategic technical debt management - understanding the debt metaphor, knowing when to take on debt, when to pay it down, and how to communicate debt decisions to stakeholdersUse when "tech debt, technical debt, legacy code, should we fix, cleanup backlog, maintenance, when to refactor, debt prioritization, shortcuts, tech-debt, technical-debt, legacy, maintenance, prioritization, stakeholder-communication" mentioned.
Use when approving, rejecting, or marking implemented Herald GEPA pending approval items, including requests like "approve GEPA changes", "approve all pending GEPA", or approval of a specific queue key from docs/superpowers/gepa-pending-approvals.md.
Use when a complex, long-running task risks polluting one conversation — research, implementation, review, planning, or learning that should be split into dependency-aware branches while keeping the master session clean. The Claude Code-native Conductor, where branches are separate user-driven sessions, raw content is quarantined in subagents, and the protocol is enforced by hooks rather than only guidance. Pairs with grill-me-style requirement work.
Turn a free-form brain-dump into a clean, ordered set of `notes/issues/*.md` work items. The user tags `/dev-issues` and writes a long stream of everything in their head — features, refactors, bugs, half-formed ideas, product direction. This skill decomposes that stream into discrete, well-shaped, individually-actionable issue files, asks clarifying questions only where a decision is genuinely the user's, collision-checks against the existing `notes/` inbox so it updates rather than duplicates, then commits the batch. The end state: every thought is captured as an issue a downstream agent (or `/dev-loop`) can pick up and execute. USE WHEN the user types `/dev-issues`, says "let me brain-dump", "capture all of this into issues", "break this into issues", "I have a bunch of ideas", "distribute these thoughts", or pastes a long unstructured list of things they want done to Ralphy. DO NOT FIRE for a single scoped change (just do it), for content/video work (that is the routing table), or to capture a one-off idea / decision into the `notes/` inbox (that is `dev-tasks`). See body for ALSO FIRE / DO NOT FIRE / HARD INVARIANTS.
Manage Ralphy's `notes/` capture inbox (`ideas/`, `issues/`, `decisions/`) — the only dev tracker for Ralphy itself; there is no separate roadmap board. Two jobs: (1) CAPTURE — turn a tagged thought into a correctly-shaped, correctly-placed note (an idea, an issue, or a decision); (2) COLLISION-CHECK — before filing anything new, search the inbox for an existing entity that already covers it, and update that instead of spawning a duplicate. For the `notes/issues/` backlog itself — decomposing a brain-dump into issues, executing them, moving them across `done/`/`deprecated/` — defer to the `dev-issues` skill (filing/shaping) and `dev-loop` (execution); this skill keeps `ideas/` + `decisions/` capture plus the cross-inbox collision check. USE WHEN the user types `/dev-tasks`, says "log this idea", "file a note", "capture this", "record this decision", "what's in the inbox", "is there already a note/idea for X", "promote this note", or drops a half-formed idea mid-dev-session for safekeeping. See body for ALSO FIRE / DO NOT FIRE / HARD INVARIANTS.