Grill Me
Clarify plans with a structured interview, adding glossary and architectural records through the Grill with Docs mode when needed.
Read Local Guide →Publisher: Matt Pocock
Agent Skills for Software Development
Clarify a plan, review architecture, preserve context for a handoff, or turn a repeatable task into an Agent Skill. Choose the instruction that supports the current stage of development, then check the decisions and evidence needed to continue.
Use this collection around the code change itself: before implementation when decisions are still open, and after implementation when the application needs realistic verification. For hands-on debugging and test-first coding, see Coding.
Selected Skills and Original Sources
Vercel Composition Patterns
Design clearer React component APIs using compound components, composition, and provider-managed state instead of growing prop combinations.
Read Local Guide →Publisher: Vercel Labs
Vercel React View Transitions
Choose React view-transition patterns that connect animation to navigation, shared elements, and meaningful changes in interface state.
Read Local Guide →Publisher: Vercel Labs
Webapp Testing
Uses Playwright to inspect local web apps, verify frontend behavior, capture screenshots, and examine browser logs.
Publisher: Anthropic
Reverse Engineer Anything
A companion instruction for investigating shipped apps and binaries with the separately configured REA tools.
Publisher: morluto
Find Skills
Find Agent Skills for a specific task by searching the ecosystem and comparing a shortlist of relevant options.
Read Local Guide →Publisher: Vercel Labs
Skill Creator
Create and improve Agent Skills through task definition, representative test prompts, and iterative evaluation.
Read Local Guide →Publisher: Anthropic
Improve Codebase Architecture
Survey concrete architecture friction, compare candidate module improvements, and explore one design before refactoring.
Read Local Guide →Publisher: Matt Pocock
Handoff
Summarize a session into a focused temporary handoff document with references and suggested skills.
Read Local Guide →Publisher: Matt Pocock
Brainstorming
Clarify intent, compare approaches, and agree a design before moving into the Superpowers planning workflow.
Read Local Guide →Publisher: Jesse Vincent
This is an independent directory. Check the publisher's source for installation, tools, and availability.
Choose by the Job
The Plan Is Still Ambiguous
Use Grill Me or Brainstorming to clarify goals and decisions. The merged Grill Me guide also explains the document-aware mode for domain terminology and architecture records.
Components Are Growing Hard to Change
Composition guidance helps separate responsibility and avoid multiplying unclear prop combinations.
The App Needs a Real Check
Webapp Testing focuses on running and inspecting the application, not only reviewing source code.
Explore Other Skill Categories
Choose the next task, not just the next publisher.
Frequently Asked Questions
How is this category different from hands-on Coding Skills?
Development covers decisions around the code change: understanding a system, clarifying a plan, designing components, and checking a running application. Coding focuses more narrowly on implementing, testing, or debugging the change itself.
What should I resolve before asking an agent to implement a plan?
Define the user outcome, constraints, affected interfaces, and how success will be checked. If a consequential decision is still open, surface it explicitly so the implementation does not silently turn an assumption into a requirement.
When is reverse engineering the right approach?
Use it when understanding a shipped application or binary is necessary and authorized, especially when source code is unavailable. Keep the investigation focused on a specific question and separate observed evidence from hypotheses about internal design.
How do component composition instructions help a growing interface?
They help separate responsibilities and make component APIs easier to understand when prop combinations are multiplying. Start from the actual states and usage patterns rather than adding abstractions solely to make the code appear more reusable.
What does a real application check add to source review?
Running the application can reveal broken navigation, missing content, unexpected loading states, and interaction failures that source inspection misses. Confirm the expected user outcome, not just a successful response code or the absence of a compiler error.
How can I keep an agent-led development task from expanding indefinitely?
Write a concrete completion condition and separate necessary changes from follow-up opportunities. Review the changed surfaces against that condition, then stop when the agreed behavior and checks are satisfied.
What belongs in a useful handoff?
Record the goal, relevant files, decisions already made, checks completed, and the next unresolved action. A new agent should be able to distinguish verified progress from assumptions without reconstructing the entire conversation.
When should a development workflow become a reusable Skill?
Consider it when the same task has a stable input, repeatable method, and a result you can evaluate. Start with a small instruction and representative examples, then revise it using observed outcomes instead of packaging every one-off task.
Keep Development Decisions Visible
Work with your files, implementation notes, and verification in one place.