작업 완료 후 상세 리포트 문서를 작성. 변경 이력, 영향도 분석, 검증 결과를 문서화할 때 사용. 파일명 규칙 YYYY-MM-DD-<제목>-report.md
Score 70/100
Checks biomedical manuscripts against reporting guidelines such as CONSORT, STROBE, PRISMA, and TRIPOD to identify missing or weak reporting elements before submission or revision.
Score 70/100
Use when building, auditing, or troubleshooting Salesforce Reports and Dashboards. Triggers: 'report', 'dashboard', 'missing data in report', 'pipeline report', 'cross-filter',…
Score 70/100
Evaluate a repository's readiness for AI-assisted development across 4 axes: code understanding, dependency restore, build success, and test execution.
Score 70/100
Check whether a paper’s Methods section contains all information needed for replication; use when preparing a manuscript for submission or reviewing methodological completeness.
Score 70/100
Run a workflow multiple times and compare outputs to produce a similarity score and pass/fail verdict
Score 70/100
Invoke when the user asks about review management, crisis communication, brand reputation, brand safety, online reputation, negative press, sentiment monitoring, or reputation…
Score 70/100
Standardize requirement/feature changes in an existing codebase (especially Chrome extensions) by turning "改需求/需求变更/调整交互/改功能/重构流程" into a repeatable loop: clarify acceptance…
Score 70/100
Request Body Validator - Auto-activating skill for API Development. Triggers on: request body validator, request body validator Part of the API Development skill category.
Score 70/100
Request orchestration agent. Transform natural language infrastructure or application needs into structured, reviewable service request drafts.
Score 70/100
Request Interceptor Creator - Auto-activating skill for API Integration. Triggers on: request interceptor creator, request interceptor creator Part of the API Integration skill…
Score 70/100
Intelligent request analysis and routing system. Analyzes incoming requests, calculates complexity, and routes to appropriate resources (27 agents, 27 skills, 14 MCPs).
Score 70/100
Turn a noisy inbound request into a bounded triage artifact and an explicit next runx lane.
Score 70/100
Use when the PM asks for staff input on a plan or review, when the EM needs multi-perspective planning or critique, or when deciding between /staff-session and /review-dispatch.
Score 70/100
Rédaction de requêtes devant le Conseil de prud'hommes pour contester un licenciement pour faute grave.
Score 70/100
Rédaction de requêtes devant le Conseil de prud'hommes pour contester un licenciement pour faute grave.
Score 70/100
Walk command tokens while inspecting attached/inline arguments so validators never skip missing or dangerous flag values.
Score 70/100
Recueillir les besoins d'une feature. Utiliser quand on démarre une nouvelle feature et collecte les exigences.
Score 70/100
Clarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear, features are complex (>2 days), or involve cross-team…
Score 70/100
Interactive PM interview with expertise-adaptive questioning for requirements elicitation
Score 70/100
How to use reseed to manage agent skills in a project. Use when the user mentions reseed, agent skills, SKILL.md, .agents/skills/, or .claude/skills/, or wants to install, add,…
Score 70/100
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media…
Score 70/100
Automate Resend tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Reserve part of the context window for summary output so proactive compaction does not kill the response budget.
Score 70/100
Removes files installed by /optimus:init and /optimus:permissions from the project. Compares each file against plugin templates and classifies as unmodified, likely generated, or…
Score 70/100
Reset an epic's test data — close PRs, delete branches, reopen issues, revert code
Score 70/100
Restore a project's .claude/ directory to the dotforge template from scratch, with backup and rollback option.
Score 70/100
Assess error handling, isolation boundaries, and recovery mechanisms in agent frameworks. Use when (1) tracing error propagation paths, (2) evaluating sandboxing for code…
Score 70/100
Türkçe resmi yazı, dilekçe, itiraz mektubu ve kurumsal yazışma üretimi. Devlet kurumlarına dilekçe, SGK/vergi idaresi yazışması, Noter belgesi, şikâyet mektubu, iş başvurusu için…
Score 70/100
Resolve code review comments by verifying their validity and proposing multiple solutions for confirmed issues.
Score 70/100
Resolves stuck review findings via a put-up-or-concede exchange. Invoked by the facilitator when a finding survives arbitration without new evidence.
Score 70/100
Find all FIXME comments across the codebase and fully implement the work they describe. Use when the user asks to fix, resolve, or address FIXME comments, or when running the…
Score 70/100
Use Mergiraf to let an agent attempt tree-aware conflict resolution during merge, rebase, revert, or cherry-pick before falling back to manual edits.
Score 70/100
SmartCMP resource browsing, detail inspection, and power operations skill. Use when the user asks to 查看云资源列表、查看云主机列表、查看云主机详情、分析云主机属性、启动云主机、停止云主机、开机、关机.
Score 70/100
Resource compliance skill. Analyze one or more SmartCMP resources with componentType-driven cloud/software/OS analyzers.
Score 70/100
Monitor system resources (CPU, memory, disk, network) during development and production.
Score 70/100
Automate Respond IO tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Address review feedback on your own merge request — resolve threads fixed by a commit, reply to threads you are not addressing
Score 70/100
Compress verbose responses by removing filler, hype, and unnecessary framing. Directness and termination guidelines.
Score 70/100
Helps organize reviewer comments and generate a standardized Word (.docx) response letter that maps each change to its exact location (page/paragraph/line).
Score 70/100
Patterns for human/LLM readable MCP responses with automation flags, token/ID cross-tool references, and confidence-based progressive detail.
Score 70/100
Response Transformer - Auto-activating skill for API Integration. Triggers on: response transformer, response transformer Part of the API Integration skill category.
Score 70/100
Assess an AI feature or product for ethical risks, bias, safety issues, fairness gaps, and regulatory compliance.
Score 70/100
Responsive Breakpoint Analyzer - Auto-activating skill for Frontend Development. Triggers on: responsive breakpoint analyzer, responsive breakpoint analyzer Part of the Frontend…
Score 70/100
Create responsive web designs that work across all devices and screen sizes. Use when building mobile-first layouts, implementing breakpoints, or optimizing for different…
Score 70/100
Conception responsive et mobile-first pour tout type de site ou app web. Se déclenche avec "responsive", "mobile first", "media queries", "breakpoints", "adaptatif", "mobile",…
Score 70/100
Build responsive layouts with CSS Grid, Flexbox, and container queries. Use when creating responsive designs, fixing layout issues, or building mobile-first layouts.
Score 70/100
Use when handling multiple resolutions — stretch modes, aspect ratios, DPI scaling, and mobile/desktop adaptation
Score 70/100
Test website responsiveness across viewport widths using browser automation. Resizes a single session through breakpoints, screenshots each width, and detects layout transitions…
Score 70/100
No-acción intencional de IA — detenerse deliberadamente sin limpiar, evaluar ni reequilibrar. Reconocimiento de que a veces la respuesta más productiva es ninguna respuesta.
Score 70/100
Restart the channelhub hub-daemon tmux session cleanly and verify it came back up. Use when the user asks to restart the daemon, when code changes need to take effect, or when…
Score 70/100
Production-grade REST API automation framework with REST Assured, POJO serialization using GSON, PayloadManager pattern, E2E integration workflows with TestNG ITestContext, and…
Score 70/100
Run GitHub Agentic Workflow jobs behind a domain allowlist and optional API-key sidecar instead of giving repository agents broad outbound access.
Score 70/100
Collect and synthesize results from multiple agents into cohesive outputs. Use for combining work from parallel executions or brainstorming sessions.
Score 70/100
Agrégation et synthèse des résultats de multiples sous-agents en un résultat cohérent. Se déclenche avec "agréger résultats", "fusionner résultats", "combiner outputs", "agent…
Score 70/100
Checks consistency between paper result descriptions and figure legends (text-only) when the input is a PDF-to-Markdown full text containing page breaks (e.g., `## Page XX`) and…
Score 70/100
Type-safe error handling via Result. Trigger: When handling expected business errors (validation, not found) without throwing exceptions.
Score 70/100
Explains result schema classes for Synapse plugin actions. Use when the user mentions "TrainResult", "InferenceResult", "ExportResult", "UploadResult", "WeightsResult",…
Score 70/100
Optimize resumes for Applicant Tracking Systems, check ATS compatibility, and analyze keyword match
Score 70/100
Auto-invoke after task completion to generate powerful resume bullet points from completed work.
Score 70/100