Analyze a specific directory (e.g. frontend/, backend/, e2e/) and generate .claude/rules/ markdown files for it.
Skill 기반의 규칙을 레포지토리에 추가하고 관리합니다. 기존 구조 분석 → 적절한 위치 판단 → 사용자 확인 후 추가. 규칙 추가, 룰 추가, rule 추가, 새 규칙, 컨벤션 추가, 스타일 가이드 추가, 가이드라인 추가 요청 시 활성화.
Use this agent when you need to review UniProt annotation rules (ARBA, UniRule) for quality, biological accuracy, and GO annotation appropriateness.
New Stack alerting/retrieval webinar process steal: prevention rules vs eval budget, retrieval latency budget, review volume is not the control.
Apply ordered rules for string transformations like pig latin, atbash, or rot. Use when translating words with specific prefix/suffix rules and ordered predicate matching.
Fixes failing test data so rules pass kantra tests, with built-in verify loop. Use when kantra tests fail and test data needs diagnosis and repair.
Use when creating or editing a rule in .agent-src.uncompressed/rules/ — trigger wording, always vs auto classification, size budget — even when the user just says 'add a rule for…
毎セッション実行する GitHub Actions ワークフロー健全チェック (CLAUDE.md Rule 9/17)。 最近の run (20件) を集計し、失敗・cancelled パターンを自動抽出。timeout / concurrency 設定の鮮度も確認する。PS版専任ルーチン。 Triggers on:…
MCP server integration for programmatic task and skill management. Use when managing tasks via MCP protocol, enabling/disabling skills programmatically, or integrating Rulebook…
Use when editing .claude-rules/ruler.yml or .claude-rules/rules/*.md files, or when the user asks to add/modify a project rule, write a ruler entry, or debug why a rule did not…
Design a RULER emotional literacy sequence for recognising, understanding, labelling, expressing, and regulating emotions.
Drafts enforceable Rules and Regulations Exhibits for attachment to commercial leases and transactional agreements.
Audit Claude Code rules and CLAUDE.md/AGENTS.md files for staleness, quality, and drift. Use when asked to audit rules, check stale CLAUDE.md, check stale AGENTS.md, review rules…
Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files
Evaluate and validate Claude Code rules in .claude/rules/ directories. Use for frontmatter, glob patterns, and quality audits.
Settle a board game rules dispute like a fair judge — reconstruct the situation, rule from the rulebook text (pasted or known), separate rules-as-written from house rules, and…
Convert implicit or scattered project conventions into governed GAAI rule files, and create or modify rule files with integrity.
Reference catalogue of the ten design patterns used in Jardis (Facade, Strategy, Adapter, Value Object, Factory, Repository, Decorator, Priority-Based Layers, Chain of…
Authoring guide for Pega GenerativeAI connector rules (Rule-Connect-GenerativeAI), including model configuration, prompt FieldValue references, response mappings, and examples
Authoring guide for Pega REST connector rules (Rule-Connect-REST) -- URL configuration, HTTP method stubs, request/response mapping, parameters, and authentication
Authoring guide for Pega activity rules (Rule-Obj-Activity), including step methods, parameters, pages, and examples
The primary authoring guide for Flow rules (Rule-Obj-Flow). Load this first before any examples.
Authoring guide for Pega Theme rules (Rule-UI-Theme), including the pyDefinition design-token content field, instance discovery, and branch-safe updates
Audit ~/.claude/rules (always-loaded behavioral rules) for residency cost, staleness, redundancy, broken See-skill pointers, and substrate absorption, assigning…
Synchronizacja lokalnych wytycznych współpracy i jakości z baseline `skills/_shared`: usuwa duplikaty z `AGENTS.md`/docs, zostawia lokalne nadpisania i raportuje je jawnie.
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source.
Use when mining past Claude Code conversations for patterns, corrections, and knowledge that reflect missed and that were never written into the brain; triggers include…
Für Rumor Control Center: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Translate an English user manual into Traditional Chinese, especially when the input is a full manual and the output should preserve first-use original terms for proper nouns.
Use before committing to build anything non-trivial — name the one assumption that, if wrong, kills the idea, and design the cheapest test that could falsify it, run BEFORE the…
Use when running or executing a multi-step EPS flow end to end — fetches the runbook via the eps MCP and executes each step's endpoint in order, branching on response_status_id.
Deploy Hermes Agent as a persistent personal agent that learns skills from experience, searches past sessions, schedules automations, and coordinates work across CLI and chat…
Help users run agents with different adapters — Claude, OpenAI, Lyzr, GitHub Models, and more
Use if driving agent-browser for Chrome/CDP automation, @ref snapshots, tabs, or verification.
Constrain Claude Code, Codex, OpenClaw, and similar agent CLIs inside a kernel-enforced local sandbox with explicit filesystem, network, credential, and snapshot controls.
Use Microsandbox to create local microVM-backed sandboxes for isolated execution of untrusted agent-generated code and tool calls.
Give an agent a mailbox it can send from, read from, search, sync locally, and mine for login codes or attachments without hand-driving a normal email client.
コード変更を伴う Issue（新機能・既存機能の変更・バグ修正）を Agent Teams で進めるとき。「チームで進めて」「Agent Teams でやって」等で使う。architect→reviewer→developer→tester→documenter を編成し、タスク依存で順に進め、解散前チェックまで回す。TeamCreate…
Put pctx between agents and tools so MCP servers and custom tools can run through a code-oriented execution layer instead of one-off tool calls.
Use PyOD's agent skill or MCP server to turn natural-language anomaly detection requests into repeatable detector selection, fitting, scoring, and investigation workflows.
Build, run, and drive the AgentREPL.jl MCP server. Use when asked to start AgentREPL, launch the Julia REPL MCP server, run its tests, eval Julia code through it, render a plot,…
Launch risky agent work inside disposable microVMs when you need stronger isolation, sealed egress, and host-side secret injection instead of direct host access.
Build, run, smoke-test and screenshot the الأَلْواح (AL-ALWAH) 3D browser game. Use when asked to run, start, launch, serve, build, typecheck, smoke-test, screenshot, or visually…
Validate, smoke-test, and run the alfred Claude Code marketplace. Use when asked to validate the marketplace manifest, run or test the marketplace, smoke-test plugin install/load,…
Use Microsoft's Magentic-UI to run supervised browser and local file tasks with an agentic UI, model endpoint, and approval-aware configuration.
Design a small team of AI agents to tackle a complex task in parallel — who does what, how they hand off, and how to keep them coordinated — instead of one overloaded agent doing…
Execute QaaS CLI verbs (run/act/assert/execute/template) and collect allure-results artifacts.
Deploy an internal coding agent that accepts tasks from GitHub, Slack, or Linear, runs them in isolated sandboxes, and opens pull requests automatically.
Run local Appium test scripts against Kobiton devices. Guides you through app upload, device selection, script capability parsing, and local execution.
Use Zeroshot when a coding issue or spec needs an executor agent and an independent verifier loop before the change is accepted.
Turn Claude Code, OpenCode, or Codex into a metric-driven loop that makes one change at a time, verifies it mechanically, and keeps or reverts automatically.
Use Autoprompt when an operator wants a coding agent to turn one goal into a planned, delegated, reviewed, and verified execution loop across supported agent runtimes.
Use Automa when an operator needs repeatable browser workflows for form filling, scraping, screenshots, or scheduled web tasks through a browser-extension block builder.
Use Camofox Browser to route agent browser work through an anti-detection browser server with stable element refs, snapshots, cookies, proxies, and session isolation.
Run, launch, screenshot, or drive the Bloom desktop app (Bloom.exe with embedded WebView2). Use when you need to start Bloom from this worktree, attach to a running Bloom, switch…
Expose Playwright browser and API automation commands to MCP-capable agents for supervised test workflows.
Run a test checklist — execute items manually via browser and API, report results
Use when a fast end-to-end smoke run is needed for the Eve loop development, will run on circle packing task.
Use Career-Ops to run a repeatable Claude Code powered job-search workflow: evaluate listings, tailor resumes, generate applications, and review outputs before sending anything.
Wrap Claude Code sessions in a spec, approval, and verification workflow before risky implementation work lands.