irahardianto

Runs a multi-dimensional code quality, security, and integrity review with parallel subagents. User-invoked entry point via /audit; not for autonomous or subagent use.

Fixes bugs of any size from hotfixes to complex debugging sessions using root cause diagnosis and TDD. User-invoked entry point via /bugfix; not for autonomous or subagent use.

Structured code review protocol for inspecting code quality against the full rule set. Use when auditing code written by yourself or another agent, during the /audit skill, or when the user asks for a code review.

Comprehensive protocol for validating root causes of software issues. Use when you need to systematically debug a complex bug, flaky test, or unknown system behavior by forming hypotheses and validating them with specific tasks.

Profile-driven performance optimization protocol. Use when profiling data (CPU, heap, trace) is available or when the user requests performance analysis. Covers methodology (Profile → Analyze → Opportunity Scan → Prioritize → Optimize → Benchmark),…

Runs profile-driven performance optimization using multi-dimensional parallel analysis and sequential TDD fixes. User-invoked entry point via /perf-optimize; not for autonomous or subagent use.

Safely restructures existing code while preserving behavior through impact analysis and TDD. User-invoked entry point via /refactor; not for autonomous or subagent use.

Runs a security-focused audit and multi-dimensional vulnerability assessment with parallel subagents. User-invoked entry point via /security-audit; not for autonomous or subagent use.

Session bootstrap + workflows for Pathfinder semantic navigation tools. Covers: discovery protocol, tool chaining patterns (explore, impact, audit, debug), search optimization, LSP degraded mode, and error recovery.

Playwright browser automation via MCP. Covers E2E testing, UI review, web scraping, screenshot capture, and general browser interaction. MCP-first — CLI is fallback only.

Safe command execution: input sanitization, timeout handling, output capture, error propagation. For spawning processes, shell commands, system calls.

Git conventions: conventional commits, branch naming, PR hygiene, release tagging.

Structured incident workflow: severity classification, triage, diagnosis, mitigation, postmortem, and prevention. Template-driven with blameless review.

Constructs, validates, and traverses a Directed Acyclic Graph (DAG) from scope cards for safe level-based parallel dispatch. Determines execution order via topological sort. Detects cycles and invalid dependencies.

Decomposes broad tasks into MECE, parallelizable sub-tasks with explicit scope cards. Core skill for intra-domain parallel dispatch. Produces scope cards consumed by parallel-dispatch-dag, parallel-dispatch-ownership, and parallel-dispatch-merge skills.

Safe, sequential merge protocol for integrating N parallel worktree branches back into main. Defines merge ordering, quality gates between merges, conflict classification, and the updated worktree naming convention for multi-instance dispatches.

Execute a structured code review protocol that inspects code quality against the full rule set. Use when auditing code written by yourself or another agent, during code audit workflows, or when the user asks for a code review. Produces a findings document…

Generates distinctive, production-grade frontend interfaces and artifacts (React, Vue, HTML/CSS). Prioritizes bold aesthetics, unique typography, and motion to avoid generic designs. Use when building websites, landing pages, dashboards, posters, or when the…

Structured research protocol for investigating technologies, patterns, and APIs before implementation. Use when exploring unfamiliar technologies, evaluating library options, or documenting technical findings. Covers multi-tool search strategy, research log…

Apply WCAG accessibility standards when building UI components, forms, interactive elements, or any user-facing interface. Covers semantic HTML, ARIA attributes, keyboard navigation, color contrast, and screen reader support.

Document significant architectural decisions using the ADR (Architecture Decision Record) format. Use during research phases when choosing between approaches, when introducing new dependencies or patterns, or when the user asks to document a technical…

Apply REST/HTTP API design conventions when implementing endpoints, handlers, middleware, request validation, or response formatting. Covers resource naming, status codes, error formats, versioning, and pagination.

Apply Kubernetes deployment and GitOps patterns when configuring container orchestration, deployment strategies (rolling, blue-green, canary), ArgoCD/Flux manifests, or Kubernetes secrets management. Supplement to ci-cd-principles.

Apply CI/CD pipeline design patterns when configuring build pipelines, deployment processes, release strategies, Dockerfiles, or GitHub Actions workflows. Covers pipeline stages, artifact management, environment promotion, and rollback strategies.

WCAG accessibility: semantic HTML, ARIA, keyboard nav, contrast, screen readers. For all user-facing interfaces.

Document architectural decisions using ADR format. Use during research when choosing approaches, introducing deps/patterns, or changing arch.

REST/HTTP API design: resource naming, status codes, error formats, versioning, pagination.

Kubernetes deployment and GitOps patterns: rolling/blue-green/canary strategies, ArgoCD/Flux manifests, K8s secrets management. Supplement to ci-cd-principles.

CI/CD pipeline patterns: stages, Dockerfile, GitHub Actions, artifact management, environment promotion, rollback. Layered by deployment complexity.

Structured code review protocol: inspect against full rule set. Use for audit workflows, code reviews, or when user requests review. Produces findings document with severity tags.

Safe command execution: input sanitization, timeout handling, output capture, error propagation. For spawning processes, shell commands, system calls.

Concurrency/parallelism patterns: race prevention, deadlock avoidance, message passing, async/channels/mutexes/worker pools.

Go stdlib, error wrapping, interfaces, goroutines, table-driven tests, gofumpt.

Angular components, signals, DI, RxJS, standalone architecture. For TypeScript see typescript-idioms.

Axum HTTP framework patterns — routing, extractors, middleware, state management. For Rust see rust-idioms.

CI/CD pipeline design: GitHub Actions, GitLab CI, multi-stage Docker builds, image scanning, SBOM attestation (Cosign keyless), and environment promotion. Layered by complexity — Level 0 (all projects), Level 1 (containerized), Level 2 (Kubernetes). GitOps…

Django ORM, class-based views, DRF serializers, migrations, pytest-django. For Python see python-idioms.

Feature flag implementation: release flags, ops kill switches, experiment flags, and permission gating. PRD-gated — only load when PRD or technical architecture explicitly requires gradual rollout, A/B testing, or kill switches. Includes lifecycle rules…

Flutter Riverpod 3, freezed, go_router, const widgets, repository pattern.

Hono HTTP framework patterns — routing, middleware, Zod validation, RPC client. For TypeScript see typescript-idioms.

Profile-driven performance optimization workflow — multi-dimensional analysis with parallel subagents, an approval gate, then one TDD-verified, benchmarked fix per commit. Use when the user provides profiling data, asks to optimize performance, or benchmarks…

Orchestration reference for the /audit workflow. Contains dimension scope cards for parallel subagent dispatch, subagent prompt template, and code audit report template.

Structured code review protocol for inspecting code quality against the full rule set. Use when auditing code written by yourself or another agent, during the /audit workflow, or when the user asks for a code review.

Comprehensive protocol for validating root causes of software issues. Use when you need to systematically debug a complex bug, flaky test, or unknown system behavior by forming hypotheses and validating them with specific tasks.

Profile-driven performance optimization protocol. Use when profiling data (CPU, heap, trace) is available or when the user requests performance analysis. Covers methodology (Profile → Analyze → Opportunity Scan → Prioritize → Optimize → Benchmark),…

Orchestration reference for the /security-audit workflow. Contains dimension scope cards for parallel subagent dispatch, subagent prompt template, and security audit report template.

Comprehensive protocol for validating root causes of software issues. Use when you need to systematically debug a complex bug, flaky test, or unknown system behavior by forming hypotheses and validating them with specific tasks.

Generate high-quality, "All-Star" README files for open-source repositories. Use this skill when a user asks to create, update, or improve a README.md file for their project.

Generates distinctive, production-grade frontend interfaces and artifacts (React, Vue, HTML/CSS). Prioritizes bold aesthetics, unique typography, and motion to avoid generic designs. Use when building websites, landing pages, dashboards, posters, or when the…

Retrieves implementation knowledge, code examples, and documentation references. Use to inform technical decision-making when the user requires specific library usage, framework patterns, or syntax details. Trigger on requests to 'search docs', 'find code…

Generates technical implementation plans and architectural strategies that enforce the Project Constitution. Use when designing new features, starting implementation tasks, refactoring code, or ensuring compliance with critical standards like…

Structured code review protocol for inspecting code quality against the full rule set. Use when auditing code written by yourself or another agent, during the /audit workflow, or when the user asks for a code review.

Comprehensive protocol for validating root causes of software issues. Use when you need to systematically debug a complex bug, flaky test, or unknown system behavior by forming hypotheses and validating them with specific tasks.

Comprehensive guide for creating brand identity guidelines. Use this skill when a user wants to define, create, or document a brand's identity, including mission, vision, values, personality, and visual elements.

Create distinctive, production-grade mobile interfaces with high design quality using Flutter. Use this skill when the user asks to build mobile apps, screens, widgets, animations, or UI components. Generates creative, polished Flutter code that avoids…

Workflows and protocols for Pathfinder v6 semantic navigation tools (locate, trace, inspect). Covers: semantic addressing, dual-channel response model, tri-state evidence, budget controls, and error recovery.