mobissh

Use when the user says "delegate", "assign bot work", "dispatch issues", "triage open issues", "send to bot", or explicitly "/delegate". Scans open GitHub issues, classifies which are bot-delegatable, enriches them with design direction and context, and assigns via @claude comments. Analyzes prior bot failures and decomposes large issues.

Use when the user says "crystallize", "compact", "compile", "distill", or asks to reduce a skill's reliance on LLM prose reasoning. Phase-transitions deterministic operations out of skill docs into real scripts with real test data. Rewrites the SKILL.md to be shorter and call the scripts instead of describing the logic. Aggressive about the boundary: LLM does judgment, prose, ambiguity resolution. Scripts do math, time comparison, parsing, counting, aggregation, schema validation.

This skill should be used when the user asks to "test on device", "test on emulator", "run emulator", "launch AVD", "test PWA", "test on Android", "test on mobile", "verify on real device", "check on phone", or discusses testing a feature on an actual device or emulator rather than headless Playwright. Also use when validating features that headless browsers cannot cover (biometric, PWA install, Chrome autofill, touch gestures, password managers). Use proactively when a feature has been implemented that touches any of these capabilities.

Protocol for capturing a complete development arc (TRACE). Includes telemetry, strategy pivots, logs, and performance metadata. Use this to record the "how and why" of an objective, especially for performance-critical or non-deterministic tasks.

Use when the user says "cycle", "pump", "sdlc", "next cycle", or "/cycle". Runs one full SDLC cycle — discover, prioritize, cluster, delegate, develop, gate — filtered by theme.

Use when the user says "develop", "work on issue", "implement issue", "fix issue N", or explicitly "/develop N". Spawns a local develop agent in a worktree to implement one or more GitHub issues. Supports batch mode ("/develop 3,9,16") with max 4 parallel agents. Without arguments, auto-proposes bot-labeled issues ranked by risk and relevance.

Use when the user says "integrate", "review bot PRs", "merge bot fixes", "check bot work", "triage PRs", or explicitly "/integrate". Reviews Claude bot PRs, validates them with available test infrastructure, and merges or rejects.

Use when the user says "release", "tag a release", "cut a release", "bump version", "ship it", "publish", or "/release". Handles version bumping, changelog generation, validation, tagging, and GitHub release creation.

Use when tests need writing for existing code, after a code change that lacks coverage, or explicitly "/test N" or "write tests for X". Spawns an Opus agent focused purely on test design. Does NOT modify application code.

Use when the user says "bug:", "feature:", "feat:", "fix:", "issue:", "chore:", or explicitly "/issue". File a GitHub issue without interrupting the current workflow. Run as a background Task so the main conversation continues unblocked.

This skill should be used when the user asks to "start the server", "restart the server", "check server status", "is the server running", "server health", "server version", "rebuild container", or when the agent needs to ensure the server is running before testing. Use proactively before any manual or emulator testing, before asking the user to verify something in the browser. Also use when the user reports stale behavior or says "it's not showing my changes".

Use when debugging touch/gesture issues on Android emulator, when a gesture feature is added or modified, when emulator tests pass but device testing fails, or when the user says "diagnose gestures", "debug touch", "gesture audit", "why aren't touches working", "scroll not working", "pinch broken", or "gesture interaction".