Fix Stuck Gza Task Inline
Use this skill when an implementation task is stuck in review/improve churn â the same blockers keep reappearing, or a previous improve/fix pass failed to close them. `fix` is escalation: it **diagnoses why the loop is happening** before making any edits, then applies a bounded repair scoped stric
Android Reverse Engineering
Decompile Android APK, XAPK, JAR, and AAR files using jadx and Fernflower/Vineflower, trace call flows through application code and libraries, produce structured documentation of extracted APIs, and escalate to runtime analysis only after static triage shows that it is needed. Two decompiler engines
auto-heal
Detect GPU and container failures, automatically remediate by restarting, migrating, or escalating.
haiku-pilot
Haiku-first execution playbook: through deliberate prompt structure, sub-agent delegation, and quantitative escalation gates, get Haiku 4.5 to produce near-Opus quality on most tasks. Escalate to Sonnet/Opus only when gates trigger. Triggers: "haiku", "Haiku", "Haiku mode", "haiku-pilot". Do NOT use for: cost-only token optimization, file-count cognitive heuristic, agent dispatch table, CLAUDE.md / rules audit, harness health check. This SKILL is a runtime router + escalation gate, not a decision tree or directory.
Agent Workflow Loops
This skill defines the operational loops that implementer agents follow when making code changes and writing tests. Each loop has explicit entry criteria, exit criteria, and escalation rules. If you are an agent, follow these loops exactly.
/align - Force N numbered clarifying questions before doing any work
Manual escalation lever above the default `prompt-refinement.md` rule. When the user invokes `/align N` they are explicitly summoning a clarification gate with exactly N numbered + lettered questions, each carrying a single committed recommendation. Single-shot per invocation - after Phase 3 approva
architecture-lead
Architecture consultation for Conductor orchestrator. Makes decisions about system design, patterns, component boundaries, and technical architecture. Can approve architectural choices within established patterns. Escalates novel patterns or breaking changes to Board of Directors.
sips-delegation-router
Route a task through SIPS commands, agents, scripts, MCP tools, or bounded delegation. Use when asked to route, split, fan out, escalate, or choose the right SIPS path.
resourceful-problem-solving
Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing. Applies to any request where the agent lacks a dedicated tool.
bead-workflow
The mandatory process for every unit of work. Use this skill whenever starting work on a bead, bug, feature, or task. Enforces claim â hypothesize â implement â test â validate â close â pause. Every transition is gated by PreToolUse hooks that block (exit 1) on violations. Ulysses REFLECT escalation activates automatically on 2 consecutive surprises. If you're about to write code, check a bead, close an issue, or start new work â this skill applies.
gastown
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.
Agent Review Panel v3.4.0
A multi-agent adversarial review system based on nine research foundations: ChatEval (ICLR 2024), AutoGen, Du et al. (ICML 2024), MachineSoM (ACL 2024), DebateLLM, DMAD (ICLR 2025), "Talk Isn't Always Cheap" (ICML 2025), CONSENSAGENT (ACL 2025), Trust or Escalate (ICLR 2025 Oral).
WebPeel
Fetch any web page as clean, AI-ready markdown with smart HTTP-to-browser escalation.