싱글 에이전트 하네스 루프. 간단한 작업이나 단일 Stage 작업 시 사용. 멀티에이전트 조율이 필요한 경우 /orchestrate를 대신 사용할 것. Use for simple single-stage work. For multi-stage or parallel work, use /orchestrate instead.
Scaffold a custom AI agent harness via `metaharness new --template --host `. Defaults to DRY-RUN (no writes) unless --confirm is passed.
Iterates a fresh ralph-worker subagent per attempt in a persistent worktree until
tag and verify command both confirm success.
Manages version bumps, CHANGELOG, git tags, and GitHub Releases. Use when cutting a release or updating version metadata.
Manages SSOT memory — decisions.md, patterns.md, and cross-session learnings. Use when recording decisions, searching memory, or promoting learnings.
Runs Plans.md tasks in a long-running autonomous loop with ScheduleWakeup, sprint contracts, and plateau detection. Use when running tasks overnight or on a scheduled cadence.
5-dimension harness readiness scorecard from `metaharness score
`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd +…
HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror.
Harnessダッシュボードを表示。現状を一目で把握できる司令塔。Use when user mentions '/harness-ui', dashboard, monitoring, or UI display.
Executes Plans.md tasks — solo, parallel, or breezing team mode. Use when implementing tasks or running the work loop.
Hash-anchored line edits — refuse the edit if the target line content changed since the read
Generate a comprehensive health analysis combining labs, DNA, activity data, supplement regimen, and sickness log into actionable interpretation.
Unified health conversation entry point - automatically loads all health data for each conversation, supports natural language queries, and intelligently routes to appropriate…
Fetch the consolidated health snapshot from a DocVault instance (Apple Health + clinical labs + DNA).
Pair Claude and Codex as collaborating peer agents inside herdr. Use whenever the user invokes /herdr-pair, asks to "pair", "team up", "collaborate with codex", "collaborate with…
Heritage hardware — build a spec from a flight-proven reference. Use when you can point at code (a vendored crate, a file, a repo, a URL) that already behaves the way you want: it…
Rédiger et poster un message BBCode sur le topic Redface 2 de forum.hardware.fr (cat=23, post=35395) en respectant les règles BBCode HFR et l'attribution IA.
Run the Hibernate ORM test suite against CUBRID and measure a dialect change's impact: total failures, +N recovered / −N regressed vs a baseline, and failures grouped by…
One-shot CUBRID dialect verification + report. Runs the hibernate-core test suite against one or ALL CUBRID versions, diffs pass/fail vs a baseline (a prior run's JSON, results…
Interview you in depth to surface overlooked or suppressed talents and write your Personal Talent Manual.
Build and iterate playable browser games, or create game-specific sprites, textures, animated 3D assets, music, SFX, and voice with Higgsfield CLI.
Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation.
Prüfung von Arbeitsvertrag und Befristung bei Neueinstellungen – TzBfG (Sachgrund, Vorbeschäftigungsverbot), AGG (diskriminierungsfreie Ausschreibung und Einstellung), AÜ — from…
Build and run Hive integration tests. Use when you need to test Ethereum clients using Hive's simulation framework.
Optimize a Hacker News post for maximum engagement. Analyzes headlines, content type, timing, and submission strategy based on data from 5 years of top-performing HN posts.
Score any content, headline, or post idea for Hacker News potential. Get a detailed breakdown of what works, what doesn't, and how to improve.
Take any content idea and reframe it with an HN-friendly angle, then produce a detailed content outline optimized for the Hacker News audience.
The distributed-correctness lens: design or audit anything that spans machines. Use when the user designs or reviews RPC, queues, replication, consensus, sharding, fault…
VernHole / K-Hole Vern - Be careful what you wish for. Random Vern personas do discovery on your idea. The more the merrier.
Annual home-maintenance calendar by home type (apartment / freestanding / period / coastal), AU-state-specific compliance tasks (smoke alarms, gutters, pool).
Make a set of things (code, prose, config, docs) consistent along a dimension the user names, by picking a canonical form and conforming every member to it.
Audit and improve an existing Quickstop plugin's quality against Claude Code plugin spec
Audit Claude Code hooks for fire frequency, latency, exit codes, and output value. Surfaces hooks that never fire, hooks that fire too often (spam), hooks that exit non-zero…
Runtime enable/disable of KeiSeiKit hooks via env vars (v0.15.1). Click-only wizard that emits shell `export` / `unset` commands for the user to paste.
Manage Claude Code Hooks Daemon - install, upgrade, check health, restart, and develop project-level handlers
**DEFAULT for plugin hook design — dispatches reviewer/architect with plugin hooks focus.**
Use when the user asks for Instagram Reel hooks, TikTok or Shorts hooks, stronger openings, first-frame text, spoken intros, identity hooks, open loops, rehooks, retention paths,…
Check Hive test progress, update documentation, and commit with standardized message.
How might we, reframe this problem, turn this into an opportunity, HMW questions. Reframe problems as actionable opportunity questions using the Basadur/P&G HMW technique.
Cria planos de entrevista estruturados com perguntas baseadas em competências e scorecards. Use quando preparando entrevistas de candidatos para a Evolution.
Estrutura uma avaliação de desempenho com auto-avaliação, template de gestor e prep para calibração. Use quando a temporada de reviews começa, ao escrever a avaliação de um…
Acompanha e gerencia as etapas do pipeline de recrutamento da Evolution. Use quando precisar de atualização do pipeline, status de candidatos, métricas de hiring, ou ao discutir…
현재 세션에서 한 작업(또는 주어진 텍스트·파일)을 비전문가·미래의 자신도 이해하도록 쉽게 풀어 설명하는 인터랙티브 HTML 페이지 생성. 목차·단계별 펼침접힘·핵심요약·용어풀이 포함. ~/Desktop 저장 후 자동 오픈.
Claude의 응답(브레인스토밍·분석·계획·결정사항 등)을 인터랙티브 HTML 리뷰 페이지로 변환. 각 항목에 👍채택/🤔의문/🔁수정/❌거절 버튼, 코멘트, LocalStorage 자동저장, Markdown·프롬프트 export 기능 포함. ~/Desktop에 저장 후 브라우저로 자동 열림.
Render substantial replies (plans, specs, code reviews, explainers, comparisons) as polished, self-contained HTML in a live browser tab instead of walls of terminal Markdown.
Creates a text-only engineering implementation plan as a single self-contained HTML page saved to specs/.html — the plan authored directly in styled HTML plus a freeform…
Creates a visual engineering implementation plan as a single self-contained HTML page saved to specs/.html — the plan authored directly in styled HTML, with one AI-generated…
htmx 4 (alpha) を使った機能の実装・リファクタリングを支援する。HTML フラグメントの返却パターンによるサーバードリブン UI の実装、templ テンプレートでの htmx 属性の使用、OOB スワップによる複数要素の同時更新を正確に行える。
Summarise what the user can now see or do that they couldn't before this unit of work
Map every worktree in this repo in plain language and shepherd safe create/remove actions
Get every live session on this repo talking to each other, agree one path forward, then start the unblocked ones working.
Transform AI-generated text into natural, human-like content that bypasses AI detectors like GPTZero, Turnitin, and Originality.ai. Uses credits based on word count.
Transform AI-generated documentation into human-readable prose with personality. USE WHEN: Converting rigid AI docs (checklist spam, CAPS LOCK emphasis, perfect symmetric…
Strip AI tells, inject brand voice, and compress existing text so it reads human-written — 15%+ word reduction with zero idea loss + optional detector-resistance pass.
Surface the agent''s in-progress guesses about where the operator is heading — what they care about, what they are circling, what the implicit destination might be — and — from…
Proactively hunt for cdkrd bugs by deploying real CDK stacks that exercise common-but-untested AWS resources, configs, and CloudFormation notations against real AWS, then catch…
Publish a hunt as a case report, escalation, detection promotion, or leadership summary
Execute a hunt phase with parallel telemetry work, query logging, receipt generation, and optional wave targeting
Validate hunt conclusions against receipts, contradictory evidence, and success criteria
Hypertension management - blood pressure monitoring, target organ damage assessment, cardiovascular risk evaluation, and medication tracking