Gravity and magnetic data processing and forward modelling using Fatiando a Terra. Use when Claude needs to: (1) Compute gravity forward models (point masses, prisms, tesseroids),…
Plant Normenrecherche zu industrieller Robotik, kollaborierenden Robotern, Sicherheitsfunktionen und Stand der Technik im Robotik-Recht.
Plant Normenrecherche zu industrieller Robotik, kollaborierenden Robotern, Sicherheitsfunktionen und Stand der Technik. — from Klotzkette/claude-fuer-deutsches-recht
Für Harmonisierung: Formular, Portal und Einreichungslogik: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Einreichungsplan mit Form- und Nachweischeck.
bAV-Systeme nach Unternehmensrestrukturierung rechtssicher harmonisieren und migrieren. Normen: §§ 4 17 BetrAVG, UmwG.
Creates Harmony patches for method interception and runtime modification in BepInEx plugins. Use when: intercepting EFT game methods, modifying bot behavior, hooking into game…
Harmonic analysis, voice leading, chord function, and modulation techniques for tonal music. Covers triads, seventh chords, Roman numeral analysis, figured bass, voice leading…
HarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities.
하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을…
Add or use full agent harness runtimes like Claude Code, Codex, Pi, Cursor, Mastra, or ACP agents inside Agent Native.
harness-ai-kit 资产操作手册（dsh 随包精简版）：list/search/info/install/doctor 团队 Skill/CLI/Plugin/Loop 资产，及 doctor dsh 环境检查。当用户在 dsh 会话中询问团队资产、安装技能、检查 dsh 环境时使用。
Use the Harness Alchemist CLI to create or validate universal coding-agent plugins for Claude Code, Codex/ChatGPT, OpenCode, Google Antigravity, and DeepSeek Harness/Cordis.
Comprehensive guide for Harness Platform API authentication, rate limiting, error handling, and endpoint operations — from general/general-misc
Comprehensive guide for Harness Platform API authentication, rate limiting, error handling, and endpoint operations — from majiayu000/claude-skill-registry
하네스(hooks, skills, agents, rules) 전체 건강도를 진단하고 점수 산출. Triggers on: harness audit, 하네스 진단, 설정 점검, 하네스 점검. NOT for: 코드 작성, 구현.
Install or sync the superpowers harness in a repo with code already present. Scaffolds CLAUDE.md, skeleton docs (overview, techstack, superpowers/), path-scoped rules, and curated…
agent 環境に mechanism（rule / skill / hook / agent / workflow / runtime 拡張 / prompt chain）を追加・変更・レビューするとき、それが 6 層（model capability / skill = 手続き記憶 / values・policy / eval /…
실행 모드(once/scheduled/realtime) 간 경계 위반과 LLM SDK 직접 호출을 감지한다. Use when writing or reviewing code that touches execution modules, LLM calls, or import statements across mode…
Auto-configure a production-grade Claude Code harness for any project. ALWAYS trigger when user mentions: harness setup, configure claude code, project setup, claude…
🥷 차크라 카카시 — 클로드코드 2.0 스킬의 토큰 사용량을 3인칭 관찰자 시점에서 감사하고 개선안을 제안하는 스킬. 토큰(차크라)·프롬프트(술법)·AI 성능(차크라 효율) 관점에서 작업 세션을 평가한다.
Run harness gate checks at every development transition point. Enforces that all gates pass before the agent proceeds to the next phase.
Use when working with other agents or the harness from inside a runner-spawned task — messaging peers on the agentboard, spawning / driving / killing worker agent sessions,…
Suggests strategic /compact checkpoints to preserve context across phase transitions. Use when deciding when to compact, checking session tool-call stats, or resetting the compact…
Use when user invokes /harness-compile or wants to compile a harness.yaml into native config files for Claude Code, Cursor, and GitHub Copilot.
Contrato que el harness Mefisto impone al repo consumidor: esquema completo de `.mefisto/harness.config.json`, las secciones obligatorias de `AGENTS.md` (Tokens del harness,…
プロジェクト側の改善をハーネスリポジトリに自動還元する。対象ファイルを指定すると、ハーネスリポジトリに feature branch を作成し、変更を適用して PR を作成する。
Teach and run Theorem's Harness cross-agent coordination protocol. Use when Codex, Claude Code, Claude.ai, or another head works the same repo/task and the user wants…
에이전트 하네스 12원칙 기반 자가 진단 및 개선 제안. Triggers on: 하네스 진단, audit, 환경 점검, setup, maintenance, drift 확인. NOT for: 코드 구현, 버그 수정, 테스트 작성.
Scans a project's harness structure (.claude/ directory, CLAUDE.md, rules, agents) to diagnose complexity, drift, missing files, and broken references, then suggests improvements.
Multi-agent task scheduling, resource allocation and parallel task management. Trigger on resource-intensive parallel workflows requiring intelligent scheduling and resource…
ハーネスエンジニアリングスキル。AIエージェントの品質と信頼性を高めるための手法論。Ralph Wiggum Loop（自己レビュー）、Golden Principles（機械的ルール）、Progressive Disclosure（段階的情報開示）、Mechanical Enforcement（不変条件強制）、Garbage…
針對單一 harness-eval 維度做深度稽核與具體修法。配合 /harness-eval 使用： 先跑全面評估，發現 WARN/FAIL 後用此 skill 精準挖掘。 用法：/harness-eval-focus D2（或 D1~D10）。 觸發關鍵字：harness-eval-focus、深度稽核、維度修法、D2 hook 問題、 D3…
Use when user invokes /harness-export or wants to save their current harness-kit plugin setup to a shareable harness.yaml file.
Agent that extracts taste invariants from GitHub PR reviews and generates a Claude skill file (SKILL.md).
Triggers on harness friction events (hook failures, ambiguous guidance, violated mandates, mismatched reality) encountered during any session.
Coach and critique Harness-First Project Design for substantial AI or software starts, ambiguous initiatives, team training, reusable skill or workflow design, and project…
刷新并复核 docs/generated 下的导航索引，包括 workspace-index、repo-doc-index、api-map、db-schema、frontend-routes、frontend-components；用于 planning/run 前让 Codex 看见当前仓库入口、检查 stale 和更新 review metadata。
Use when user invokes /harness-import or wants to install plugins from a shared harness.yaml config file.
Improve Kandev's AI harness from session learnings or explicit requests. Use when the user asks to record learnings, update or create skills, agents, subagents, commands,…
Agentic harness diagnostic + improvement loop. Probes the framework with real model runs, uses the rax-diagnose CLI to root-cause failures from structured trace data, ships ONE…
Bootstrap a Sisyphus-compatible engineering harness in any project. Generates HARNESS.md, FEATURE_INTAKE.md, story template, HARNESS_BACKLOG.md, optional OpenSpec config, GitHub…
Reference guide for building new Omnigent harness integrations — covers SDK/subprocess harnesses and native harnesses as separate tracks, each with their own feature matrix,…
Use when the user explicitly asks for "하네스 모드", "하네스로 하자", "harness mode", role-separated development, CEO/CTO/implementer/verifier/reviewer separation, or gated implementation.
Analyze the protocol layer between agent harness and LLM model. Use when (1) understanding message wire formats and API contracts, (2) examining tool call encoding/decoding…
Use whenever you change Compose UI code (composables, @Preview functions, themes) or render or review Compose previews, catalog components or UI Builder designs.
Analyze and improve the local agent harness configuration for reliability, cost, and throughput.
Explains polyglot-agent-harness layout: Claude Code plugin-dir vs .claude copy, Trae skills symlink install, Cursor rules bridge, Codex instructions_file; points to AGENTS.md and…
Generate a Plan Brief HTML for non-engineer vibecoders before implementation starts. Searches harness-mem (project-only) for relevant past decisions, patterns, and Plans archive…
Harness Platform administration including delegates, RBAC, connectors, secrets, templates, policy as code (OPA), user management, audit logs, and governance
반복되는 결함·리뷰 지적·경계 위반을 docs/design-docs/core-beliefs.md 의 R 룰로 승격하고, 대응하는 강제 장치(테스트·린터 규칙)를 스캐폴드한다. Use when the same defect/review comment/boundary violation appears 2+ times, when…
비자명한 작업에 계획 → 구현 → 검증 흐름을 적용하고, 큰 변경일 때만 깊은 리뷰로 승격한다. Use when starting a new feature, multi-file change, or any non-trivial implementation task.
Restart the Claude Code or OpenCode processes running in herdr panes so they pick up a newer binary, keeping each conversation by resuming its session id.
Regenerate the structural skeleton of a harness — agent role stubs, KB layout, and per-stack rule files — for a repository's stack, in seconds.
Audit and reduce a live multi-runtime agent harness after adoption. Use for installed skill/plugin parity, cold-start context, routing overlap, telemetry, or human-attention load.
Creates or updates pipeline step schemas in the harness-schema repository. Use when the user wants to add a new step, modify an existing step's fields, or make a step available in…
Harness Engineering 第一阶段：扫描现有项目，生成 AGENTS.md（目录文件）和完整的 docs/ 知识库结构。 当用户想要"为项目添加 agent 支持"、"让 AI 更好地理解我的项目"、"开始 harness engineering"、 "创建 AGENTS.md"、"搭建 agent 文档结构"、"让 Claude Code…
Harness Engineering 第二阶段：建立跨 session 状态管理，解决 agent 每次对话失忆的问题。 创建 tasks.json（任务清单）、progress.md（进度记录）、init.sh（环境初始化脚本）三个文件。
Use when user invokes /harness-sync or wants to sync AI tool configurations across Claude Code, Cursor, and GitHub Copilot.
Use after harness DDD design or maintenance scope analysis is complete and before implementation planning to decide detailed technical strategies such as polling vs push, retry…
Use after a completed or validated workflow run to separate product implementation from durable harness evolution.