개발 스킬

Helps users set up pstack, understand model settings, and choose skills or task procedures. It answers questions with a usable example prompt and a source link, leaving the user to start the actual work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting help with pstack installation and setup
• Writing a task prompt for /poteto-mode
• Choosing a skill for a specific task

Design stateful code around data structures that reflect real rules. The skill helps choose state machines, typed models, or lookup tables to reduce scattered conditions, duplicated assumptions, and combinations of values that should never occur.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organizing growing chains of conditions
• Designing state transitions and lifecycle rules
• Consolidating rules repeated across files

Configure which AI models pstack uses for each role, along with reasoning effort, the level of reasoning applied. Detects available models, writes settings for the current environment, and controls the session startup hook where supported.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assigning AI models to pstack roles
• Updating settings to match available models
• Setting default and per-role reasoning effort

Design a reviewable workflow for large migrations or complex changes without an existing playbook. Define testable completion criteria, verify small changes against real results, and record decisions so someone returning later can assess what worked and what remains open.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a large migration without an existing playbook
• Breaking a complex change into verifiable steps
• Keeping decisions reviewable during extended work

Review a branch against main and clean up unnecessary AI-generated code, including excess comments, unusual defensive checks, type workarounds, and deep nesting. Make focused edits that match surrounding code while preserving behavior unless fixing a clear bug.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clean up a branch after AI-assisted coding
• Remove unnecessary comments and defensive checks
• Review any casts used to bypass type issues

Investigate what a code change could break beyond the edited files. Trace downstream effects, identify the key assumption behind its safety, and test that assumption with real code while clearly reporting unresolved risks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking the wider impact of a small code change
• Verifying assumptions about existing code before design
• Testing the safety assumption before merging a change

Monitor an open pull request, fix failing automated checks and merge conflicts, and address straightforward review feedback. Recheck after updates, report the resulting status, and hand decisions requiring design judgment back to the user.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Following up on an open PR without repeated prompts
• Fixing failed automated checks and rechecking results
• Addressing straightforward review comments

Guide an AI agent through development work with clear prose, simple code, deliberate delegation, and checks against real outputs. Task-specific workflows cover investigation, implementation, review, and delivery, with decision records for longer autonomous work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keep an agent's development approach consistent
• Compare design options before implementation
• Verify fixes against actual behavior

Review code by examining how many layers readers must follow and how much changing state they must remember. Identify unnecessary wrappers and overly broad state, making values and the places that change them easier to trace.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review code whose behavior is hard to trace
• Reconsider wrappers that have only one caller
• Reduce the scope of mutable state

Guide refactoring and code changes toward the smallest solution that addresses the problem. Centralize repeated decisions, pass their results as simple flags, and reconsider extra layers or boilerplate that increase the amount of code changed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reduce the size of a code change
• Consolidate decisions repeated across multiple places
• Reconsider whether an abstraction is needed

Plan types, function inputs and outputs, and module boundaries before implementation. Compare structurally different designs from multiple AI models, document the chosen approach, and guide coding while tracking changes to the agreed design.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a complex feature before coding
• Comparing alternative module structures
• Keeping implementation aligned with design decisions

Guide code design before implementation by choosing core types, matching data structures to access patterns, and checking shared state risks. Organize work from removing dead code through shared foundations and features, while avoiding premature abstractions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose core types and data structures before coding
• Review state shared by concurrent tasks
• Plan infrastructure work before feature development

Review code changes with several AI models working independently. Combine overlapping findings, highlight disagreements, and sort issues by whether they need action, further consideration, or no change, producing a reasoned review without automatically editing the code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a feature branch before merging
• Finding blind spots in recent code changes
• Comparing findings from multiple AI models

Guide debugging from reproducing a failure to finding the first incorrect decision in the code. Distinguish valid states that need handling from invalid states that reveal earlier faults, and look for the same defect elsewhere.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing a failure to its root cause
• Reviewing whether a guard hides a bug
• Investigating failures after a restart

Guide validation and error handling toward system boundaries, where external data enters the application. Keep business rules in functions independent of frameworks, use validated types internally, and avoid repeating checks throughout the code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organizing configuration validation
• Separating business rules from framework code
• Reviewing repeated internal checks

Guide an internal API refactor by moving callers to the new interface and removing the old one in the same round of changes. Update tests for the new contract and remove tests tied only to obsolete implementation details.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Move internal callers to a replacement API
• Remove legacy APIs during a coordinated refactor
• Update tests to reflect a new API contract

Review concurrent work that writes to the same files or state. Separate each writer’s storage where possible, and use locks or exclusive ownership only when a single shared object is genuinely required.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preventing conflicting file writes by multiple agents
• Separating state storage for independent processes
• Reviewing whether shared state really needs a lock

Revisit an existing design as though a new requirement had been present from the start. Examine affected files, plan the overall redesign, and carry changes through types, documentation, examples, and design rationale in incremental steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Integrating a new requirement into an existing design
• Rethinking structure before adding another workaround
• Updating types, documentation, and examples together

Reviews the current conversation from three perspectives to find reusable lessons and propose concrete skill improvements. It separates findings into accepted, rejected, and backlog items, with user approval required before applying accepted edits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing lessons from a completed agent session
• Turning repeated mistakes into skill improvements
• Separating skill edits from structural fixes

Prepare a pull request for review by checking its description, commits, and changed files. Clarify intent, highlight important files and risks, and organize history when authorized, while verifying that cleanup preserves the intended code content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Updating a PR description to match the actual changes
• Organizing commits into a reviewable order
• Highlighting key files and risks for reviewers

Review code comments in selected files or changes with a dedicated agent, remove accepted findings, and fix underlying problems. It also proposes ways to enforce documented constraints through types, runtime checks, tests, or automated checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing comments in a code change
• Fixing workarounds explained by comments
• Turning documented constraints into automated checks

Guides additions, refactors, and rewrites by removing unnecessary complexity first. It prioritizes deleting dead code, redundant checks, empty references, and repetitive prompt instructions, then building around observed usage and explicit requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Cleaning up code before adding a feature
• Planning removal steps before a refactor or rewrite
• Reviewing checks added for speculative edge cases

Resolve Git merge conflicts with minimal edits that preserve public behavior. Regenerate lockfiles using package manager tools, run compilation, lint checks, and relevant tests, then stage resolved files and summarize decisions and verification results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resolving conflicts after merging branches
• Checking that both sides of a change are preserved
• Regenerating conflicted lockfiles

Address repeated instructions or recurring corrections by turning rules into automated checks, metadata flags, or scripts. When a rule requires human judgment, make the instruction more prominent and add an example showing the failure to avoid.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning repeated corrections into automated checks
• Encoding rules in metadata flags
• Handling recurring issues with runtime checks or scripts