nextc-claude

Build Flutter APK/IPA, generate changelog, update buildlog, and commit version bump. Handles platform selection, build mode, and artifact renaming.

Build Unity APK/IPA on macOS with Unity 6.x — pre-flight checks, version bump, iOS signing params, post-build verification, buildlog, and commit.

Evidence-driven bug investigation and fix pipeline. Use when something is broken, not working, or the root cause is ambiguous.

Two independent reviewers must both approve high-stakes output before it ships, breaking the single-reviewer blind-spot problem.

Team-orchestrated feature development with parallel specialist agents. Use when building a feature that benefits from multiple agents working concurrently. You act as Product Director coordinating the team.

Interactive agent picker for composing and dispatching parallel teams. Browse available agents across domains, pick a roster, dispatch in parallel.

ASO optimization pipeline for an app store listing. Use when optimizing an App Store or Play Store listing.

Find cross-cutting principles repeated across skills and promote them into rule files, with user approval per candidate.

Author or revise a skill by pressure-testing it against real agent behavior before deploying, so the skill actually changes what agents do.

Turn a one-line objective into a cold-start-executable, multi-PR construction plan for work that spans several sessions or agents.

Full feature pipeline — idea to committed code. Use when building a new feature, adding functionality, or implementing from specs.

Decide how to integrate completed branch work via a structured merge / PR / keep / discard menu, with safe worktree cleanup.

Apply concrete design-engineering details that make a web UI feel polished — radius, type, motion, hit areas, states.

Self-rate your own output on five evidence-backed axes before handing it back, catching omissions and overconfidence.

Verify a deployed URL after a release by checking health, errors, assets, streams, and performance against a baseline.

Generate a persona-targeted CodeTour `.tour` walkthrough anchored to real, verified file and line locations.

Prepare a private project for safe public open-source release.

Local-evidence production-readiness audit that scores ship/block risk before a launch without sending repo data anywhere.

Deep multi-framework analysis of a problem or product concept, broader than the proposal pipeline.

Turn a raw product idea into a validated proposal with a recommended scope decision.

Build, typecheck, and lint verification loop — confirms the build is green before handoff, commit, or PR.

Audit an app's ASO surface against the 8 highest-leverage moves and the 2025–2026 algorithm shifts. Produces a prioritized gap report separating metadata gaps from engineering gaps from operational gaps.

Turn a product concept into ranked Title + Subtitle candidates using the Brand+Keyword formula, 4 angles, safety/collision checks, and a 12-point rubric. Use before launch, before a rename, or for naming a sister-SKU.

Scaffold a production-grade Flutter project from docs/proposal.md. Use when starting a new Flutter app or going from proposal to code. Creates project with deps and docs/architecture.md that guides /feature-dev.

Scaffold a production-grade Unity C# game project from docs/proposal.md. Use when starting a new Unity game or going from proposal to code. Creates project with packages and docs/architecture.md that guides /feature-dev.

Translate untranslated ARB keys via ChatGPT API with parallel agents. Use when adding translations for new locales, translating new strings, or running translations as part of the l10n pipeline. Incremental.

Deep audit of skill quality against current skill-creator best practices. Flags missing when_to_use, imperative density, missing evals/, and description budget overflow.

Socratic requirements gathering with ambiguity scoring. Use when the user has a vague idea, wants help thinking through requirements, or when a task is too unclear to implement directly. Interviews the user to produce a clear spec.

Bounded, regression-safe code cleanup with deletion-first workflow. Use after a coding session that left dead code, duplicates, over-abstraction, or bloat. Also use when the user says "clean up", "simplify", or "remove cruft".

Sync project docs with current codebase state — CLAUDE.md, tasks.md, specs, design.md, changelog, glossary, api.md.

Structured self-debugging workflow for AI agent failures — capture, diagnose, contained recovery, introspection report.

Answer a quick side question mid-task without losing context, then resume work automatically.

Analyze an unfamiliar codebase and produce a structured onboarding guide — architecture map, key entry points, conventions, starter CLAUDE.md.

Audit Claude Code context-window consumption across agents, skills, MCP servers, and rules. Identifies bloat, duplication, and surfaces a prioritized token-savings list.

Convene a four-voice council (Claude + Skeptic + Pragmatist + Critic) for ambiguous decisions, tradeoffs, and go/no-go calls.

Extract reusable patterns from the current session, self-evaluate quality, and place the result in the right scope (Global vs Project).

Load the most recent session file from ~/.claude/session-data/ and orient fully before resuming work.

Prevent destructive operations on production systems and during autonomous agent runs. Sets ask/deny rules around `rm`, `git reset/clean`, force-push, drops, and infra changes.

Capture current session state — what was built, tried, failed, and is left — to a dated file so the next session can pick up exactly where this one ended.

Research-before-coding workflow. Search Context7, GitHub, and registries for existing tools, libraries, and patterns before writing custom code.