ancplua-claude-plugins

Unified qyl AI observability platform plugin. Ground truth authority, dead API blocker, architectural audit, parallel agent swarm, observability orchestration.

Interactive live demos of all marketplace plugins with version-gated features.

LSP code intelligence surface for qyl. SessionStart hook detects missing LSP tools in qyl.mcp and injects implementation guidance.

Cognitive amplification stack: epistemic hooks, competitive review, commit integrity checks, CI verification scripts, and deep-thinking agents.

OpenTelemetry documentation with auto-sync. Semantic conventions, collector config, .NET instrumentation.

Enforces .NET build patterns: Version.props symlinks, CPM, and single-owner imports. Prevents AI agents from breaking centralized version management.

User-configurable hooks from .local.md files. Define blocking, warning, and execute rules for Bash commands, file edits, and session events.

Guided feature development with specialized agents for codebase exploration, architecture design, code review, and quality assurance.

Auto-routes to specialist agents, commands, and skills based on current project. Injects cross-repo dependency graph for the ancplua .NET ecosystem.

Five-agent council using Teams API: Opus captain orchestrates, researcher + synthesizer cross-pollinate via SendMessage, clarity asks live follow-ups, Haiku janitor flags bloat. Reactive collaboration instead of fire-and-forget subagents.

Multi-agent workflow orchestration (9 commands + 2 skills: eight-gates, hades): fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review, baryon-mode. Hades, eight-gates, and red-blue-review use Teams API for reactive collaboration.

Teams API observability orchestration for qyl: 1 Opus captain + 4 Sonnet specialists. Captain pre-reads otelwiki semconv docs, dispatches servicedefaults, collector, genai, and platform specialists. Zero runtime web search.

Design intelligence studio: creative direction + data-driven recommendations. 50 styles, 97 palettes, 57 font pairings, 99 UX guidelines, 25 chart types, 13 stacks. BM25 search engine with design system generator.

Multi-agent code-elegance workflow: 4 scouts (sonnet), 2 judges (opus), 1 planner, 1 verifier, 1 gated implementer. Persistent state with stage gates.

Code simplification agent tuned to qyl engineering principles. Measures elegance as problem-complexity / solution-complexity. Zero suppression, compile-time over runtime, less code is better code.

Smart auto-continuation for Claude Code. Heuristic pre-filter eliminates ~80% of unnecessary Haiku calls; improved judge prompt handles the rest. Based on double-shot-latte (MIT).

Agent operating system — leaderless swarms with Playwright oracle. Code is opaque weights; correctness inferred exclusively from externally observable behavior.

Carlini-style parallel agent teams for qyl AI observability platform. 8 specialized agents with file ownership boundaries and git-based coordination.