pk-speak-extension

Pointer skill for pk-speak / pi-pk-speak. Use when the user wants spoken replies, wake-word listening, session-manager control, deterministic short voice routes like `PK one` / `PK1` vs `PK two` / `PK2`, Telegram control, QR-based Android setup via `/pk-remote`, or the browser remote. Start from the bridge doc and then jump to README and source as needed.

How agents execute work for Kade. Use when starting substantive or multi-step work, discovering workspace and repository instructions, selecting skills or tools, assembling minimal context, delegating or handing off work, verifying results, or synchronizing state. Do not use for simple direct answers, Kade's profile or governance (use kade-hq), or repository-specific implementation truth (use repo-local instructions).

Canonical human-context and governance skill for working with Kade (pk). Selects relevant communication, attention, autonomy, session-state, decision, commitment, and memory rules without forcing planning behavior onto ordinary execution.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Use when a CLI agent should speak naturally with pk-speak, wrap a command with spoken lifecycle notices, start the phone gateway/tray, print Android setup QR codes, or explain the current realtime voice options. Keep normal replies concise and speak only useful status, questions, approvals, and completion summaries.

Use the multimodalart/higgs-audio-v3-tts Gradio Space via API. Provides Python, JavaScript, and cURL usage examples.

Use when the task should consult, capture, validate, evolve, or retire reusable workflow shortcuts through the local `llm-wiki-skills` MCP server or its CLI. This packet-owned wrapper explains the full tool lifecycle in depth and is installable into ~/.agents/skills, ~/.codex/skills, ~/.claude/skills, and ~/.pi/agent/skills.

Repo-local gstack workflow surface layered on top of the llm-wiki-memory packet.

Use this skill when the repo is an llm-wiki-memory vault and the task is to ingest a source, answer from the persistent wiki, create or review reusable skills, use pk-qmd for repo-local evidence retrieval, consult brv for durable memory, or lint and maintain the wiki.

Use the local llm-as-a-verifier tool to collect and rank evidence-aware coding-agent trajectories. Trigger when a user asks to use llm-as-a verifier, verify a coding-agent run, compare candidate runs, capture objective command/diff/final-answer evidence, or gate completion on a verifier result using the tool at C:\dev\Desktop-Projects\llm-as-a-verifier.

Android development standards for AI agent implementation. Kotlin-first, Jetpack Compose UI, MVVM + Clean Architecture, Hilt DI, comprehensive security, testing, and performance patterns. Use when building or reviewing Android applications...