eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
8,939 agents across 675 plugins.
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including…
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via `npm run…
Reviews an evo benchmark in two modes. mode=audit -- pre-flight harness audit before the first run (per-task instrumentation, leakage, gates, plumbing);…
Generates ranked experiment proposals for the evo orchestrator. Runs ONE brief per invocation (`failure_analysis`, `literature`, or `frontier_extrapolation`)…
Read-only audit of one evo experiment for design-time cheating (pre-phase) or result-time validity (post-phase). Catches test-set leakage in training data,…
Selects required BitLesson entries for a specific sub-task. Use before execution for every task or sub-task.
Checks if a draft document is relevant to the current repository. Use when validating draft content for gen-plan command.
Checks plan relevance and compliance before RLCR loop. Use when validating plan files for start-rlcr-loop command.
Adversarial senior design critic. Renders the work, looks at it, and argues for rejection. Use when a build, screen, or component needs a taste and craft…
Builds interactive HTML explorables for Engram threshold concepts under the binding Explorable Contract. Use after encoding a threshold node, or to re-encode a…
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the…
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns…
Kimi K2 CLI + tmux multi-agent parallel dev platform with sengoku military hierarchy
Agent Team 导师角色 — 观察其他 teammate 的执行状态,用智慧引导而非恐惧施压。当 teammate 陷入循环、放弃或被动时,以道德经智慧启发。建议 5+ teammate 的团队使用。
Agent Team Mentor Role — Observe teammate execution status, guide with wisdom rather than fear. When teammates get stuck in loops, give up, or become passive,…
Agent Team メンター役 — 他のチームメイトの実行状況を観察し、恐怖ではなく知恵で導く。行き詰まり、放棄、受け身に陥ったときは道徳経の知恵で啓発。5人以上のチーム推奨。
These agents are sourced from [wshobson/agents](https://github.com/wshobson/agents) repository.
Defines and manages task status transitions, ensuring consistent task lifecycle management across projects.
This guide provides practical examples of how to use the Claude Command Suite agents together for common development scenarios.
Describes video frames as detailed text. Used when frame_mode is "descriptions" to convert visual frames into text, saving tokens while preserving key visual…
Architecture review and recommendation. Use for system design, module boundaries, ADRs, and tradeoff analysis.
Backend implementation. Use for API, authentication, DB migration work.
Database design and implementation specialist. Use for schema, ERD, migration, query tuning, vector DB work.
Read-only web and registry lookup. Use for Agent Skill / MCP discovery (npx skills find, MCP search), current-usage doc-checks, and scope source verification.…
Read-only code exploration and repo scanning. Use for the develop exploration step, the scope brownfield code scan, or any task that reads across many files…
Use this agent when you need to create or update technical documentation that helps developers understand the deep patterns, mental models, and architectural…
Use this agent when you need expert guidance on React application architecture, component design, performance optimization, or code quality improvements. This…
Use this agent when working with Tauri applications, Rust backend development, Tauri plugins, cross-platform desktop app architecture, or when you need expert…
Central decision-maker that plans experiments and reflects on results
Decomposes goals into parallel tasks, assigns them to CLI coding agents, verifies output, and merges results. Use when a task is too large for a single agent.
Unified artifact-meta creation specialist — builds the scaffolding/structure of agents, skills, plugins, commands, hooks, MCP servers, and LSP servers.…
MUST INVOKE for moai-adk-go CLI and go:embed template system work — Cobra commands in internal/cli/, template source under internal/template/templates/, binary…
End-to-end test execution specialist for web, mobile, and desktop applications. Owns project-type detection probes, toolchain probing and installation,…
**Discovery approach**: Think like an attacker. What would maximize extracted value? What sequence breaks liveness? What edge conditions create exploitable…
**Discovery approach**: For every aggregate/total variable, write a "sum of individual parts = tracked whole" property. This is the #1 bug-finding pattern in…
**Role**: Implement global properties into Properties.sol, wire ghost variables into Base.sol, and populate Snapshots.sol. These are checked by the fuzzer…
Expert in Akka.NET architecture, actor systems, and distributed computing patterns. Specializes in analyzing actor lifecycle issues, message passing problems,…
Expert in DocFX documentation system, markdown formatting, and Akka.NET documentation standards. Handles DocFX-specific syntax, API references, build…
Expert in designing effective .NET performance benchmarks and instrumentation. Specializes in BenchmarkDotNet patterns, custom benchmark design, profiling…
Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read-only; posts a VERDICT comment on the…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic