claudecode-orchestrator

Demo pipeline state machine — 7-phase autonomous sequence with delegation context templates, phase transition logic, BLOCKED recovery strategies, and demo-state.json schema. Used exclusively by demo-conductor.

Cinematic narration style guide for demo-conductor — ANSI-coloured banner formats, live pipeline scoreboard, audience-facing language, phase summaries, and error narration patterns. Keeps the demo presentation-quality throughout.

Standardized completion and escalation protocol for subagent responses. Ensures the conductor can machine-parse every subagent return. Use when reporting completion status back to the orchestrator.

Cross-session learnings lifecycle — schema, storage, retrieval, and pruning of lessons learned during orchestrator sessions. Use when managing learnings via the /learn command.

Agent Teams assembly and task injection — selects appropriate team, validates prerequisites, estimates cost, injects tasks into the shared task list, and manages team lifecycle.

Token and cost tracking with model tier enforcement

Complexity-based task routing with model tier selection

Brief description of what this skill does and when to use it. Include keywords that match user requests.

Publishes code review findings to Confluence as a structured review page.

Publishes orchestrator plan artifacts to Confluence as structured pages.

Searches Confluence for existing documentation, architecture decisions, and prior art.

Issue classification, prioritization, and management patterns for GitHub integration.

Pull request creation, review, and merge workflow patterns for GitHub integration.

Traces requirements through Jama's relationship graph — upstream to stakeholder needs, downstream to test cases and design items.

Maps test execution results from Jama test cycles to requirements, showing coverage gaps and pass/fail status.

Pull Jira issue details into the current session as working context. Use before starting implementation to understand requirements.

Convert orchestrator plan phases into Jira stories with acceptance criteria. Use after plan approval to create trackable work items.

Session artifact lifecycle — creation, indexing, retention, and compaction of plans, reviews, decisions, and session state.

Universal code quality standards for any language

Complexity assessment and agent routing — classifies tasks by complexity tier and selects the optimal agent roster and model tier. Use when routing tasks, assessing complexity, or selecting agents.

Confidence-based scoring system for review findings — calibrates issue severity with evidence strength to filter false positives. Use when reviewing code, analyzing findings, or scoring issues.

Deployment readiness verification — pre-deploy checklist, CI/CD validation, environment config, and rollback planning.

Domain-specific customization overlays — provides tailored conventions, patterns, and safety rules for embedded systems, semiconductor testing, safety-critical, edge AI, enterprise applications, web frontend, and UI/UX domains.

Incident investigation protocol — structured debugging with 5-why analysis, evidence gathering, and post-mortem documentation.

Structured planning methodology for multi-phase implementation

Pull request review workflow — orchestrates multi-agent review with confidence scoring, parallel analysis, and PR comment formatting.

Code review methodology with severity tagging

Security analysis checklist aligned with OWASP Top 10

Cross-session state management and recovery

Structured requirements elicitation through interactive dialogue — guides the spec-builder agent through 5 phases of discovery, scoping, behavior definition, risk analysis, and assembly.

Context compaction strategy for long sessions

Test-Driven Development with Red-Green-Refactor cycle

Build-test-lint-typecheck verification cycle

Azure Bicep coding standards with severity-tiered rules. Use when writing, reviewing, or generating Bicep code.

C coding standards with severity-tiered rules. Use when writing, reviewing, or generating C code.

C++ coding standards with severity-tiered rules. Use when writing, reviewing, or generating C++ code.

C# coding standards with severity-tiered rules. Use when writing, reviewing, or generating C# code.

Domain overlay for edge AI and ML deployment. Extends language standards with model lifecycle, inference optimization, and data pipeline rules.

Domain overlay for embedded and firmware development. Extends language standards with memory-constrained, real-time, and hardware-interface rules.

Domain overlay for enterprise application development. Extends language standards with architecture patterns, observability, and operational readiness rules.