po4yka

Use this skill to generate well-branded interfaces and assets for RIPDPI (an Android-native, Compose-first VPN and DPI-bypass app), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, brand-ship icons, and an interactive UI kit of every public composable from the live ui/components tree.

Use when managing the Rust workspace, adding/removing crates, editing workspace dependencies, running cargo nextest/audit/deny, configuring Cargo profiles for Android cross-compilation, debugging Cargo.lock churn, migrating crate edition, or wiring Gradle to cargo via the ripdpi.android.rust-native plugin.

Use when modifying the diagnostics scan pipeline, ScanRequest/ScanReport types, ProbeTask families, ripdpi-monitor-engine / ripdpi-diagnostics-* crates, strategy-probe candidates, the diagnostics catalog (packs/profiles), wire-schema contracts between Rust and Kotlin, DIAGNOSTICS_ENGINE_SCHEMA_VERSION, golden contract tests, or adding a new probe type / profile. Triggers on diagnostics scans, strategy probes, automatic audit, dpi-detector profiles, or anything in core/diagnostics or native/rust/crates/ripdpi-monitor-*.

Android-specific Rust build, verification, and packaging — per-target 16 KiB page alignment, size-optimized release profile, ELF symbol allowlist, .so size budgets, NDK 29 specifics. Use when modifying .cargo/config.toml for Android targets, the workspace [profile.release] / [profile.android-jni] block, or when verifying a built .so before release.

Telemetry and observability discipline for the RIPDPI Android Rust stack — control-plane vs data-plane logging, bounded flume event queues, atomic counters, snapshot polling, readiness callbacks, and deterministic JSON contracts. Use when authoring or modifying telemetry emission code, the bounded event ring, the Kotlin-side telemetry consumer, or any per-packet logging.

Custom detekt rules, DI/privacy/suppression guardrails, detekt.yml configuration, and false-positive triage.

Edge-to-edge and window-inset handling for Compose screens, scaffolds, sheets, and system bars.

Gradle dependencies, modules, convention plugins, and Android build failure triage.

Recover and maintain decision provenance in an LLM-Wiki. Use when the user asks why a technical/product decision was made, wants ADRs generated or connected, or needs PRs, issues, discussions, commits, and docs distilled into decision memory.

Decide what belongs in LLM-Wiki versus agent memory, AGENTS.md, CLAUDE.md, Auto Memory, Codex project memory, or other runtime memories. Use when instruction files are bloated, domain facts live in agent memory, or the user wants clean memory boundaries.

Prepare an LLM-Wiki for long-term durability and archival. Use when the user wants a wiki to remain readable in 5-10+ years, export opaque stores, preserve raw sources, rebuild indexes, vendor key references, or create an archive manifest.

Design cross-channel capture architecture and named connector runbooks for LLM-Wiki. Use when the user wants an inbox/raw topology, metadata contract, dedupe boundary, triage handoff, privacy defaults, capture-to-ingestion flow, or Telegram/email/Slack/PDF/GitHub/voice connector rules.

Help a user choose between ready-made LLM-Wiki tools, a local-first workflow, a team rollout, retrieval/GraphRAG systems, or a custom implementation. Use when the user asks what solution fits their needs, whether to use OpenWiki/Obsidian/qmd/GraphRAG, or whether to build their own.

Insert deterministic claim and source anchor IDs after evidence has been inspected. Use when the user wants stable claim IDs, source anchor IDs, support-label formatting, anchor validation, or reproducible claim references; route missing-evidence investigation to llm-wiki-provenance.

Map company/team information flows into an LLM-Wiki adoption plan. Use when the user asks where team knowledge lives, which streams can be automated, how Confluence/Jira/Slack/Drive changes stay synced, how fragile review is, how confidential data is handled, or whether maintenance cost is worth the benefit.

Help resolve contradictions found by wiki-lint, provenance checks, or user review. Use when LLM-Wiki pages disagree about facts, recommendations, tool status, decisions, definitions, or stale claims and the agent should mediate rather than auto-fix truth.

Debug the LangGraph summarize graph (the sole summarize path) -- node walk, validate/repair retry loop, and the LLM attempt trail. Trigger keywords -- LangGraph, summarize graph, graph node, retry, repair loop, attempt_trigger, attempt_index, graph_node, validation failure, self-correction, summarization agent.

Build, ship, and restart the Ratatoskr container on the Raspberry Pi via cross-platform Docker image streaming. Trigger keywords -- pi deploy, raspi, raspberry pi, pi-deploy, ship to pi, deploy production, build-and-deploy-pi.

Coordinate Ratatoskr backend web integration with the external React + TypeScript + Vite frontend. Trigger keywords -- web, frontend, React, Vite, TypeScript, ratatoskr-web, app/static/web, Frost, UI change.

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: @ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

Test bot functionality locally using CLI runner, message simulation, and workflow validation. Trigger on "test", "CLI runner", "message simulation", "bot testing", "workflow validation", "pytest".

Validate summary JSON contracts against strict schema requirements. Trigger keywords: summary validation, summary contract, JSON schema, character limits, summary fields, validate summary.