check-pipeline
Check GitLab CI pipeline status and investigate failures. Use when user asks about CI status, pipeline failures, or wants to debug failed jobs.
Discover Databases skills, compare source repositories and read the instructions for each workflow.
Check GitLab CI pipeline status and investigate failures. Use when user asks about CI status, pipeline failures, or wants to debug failed jobs.
Generate an ML-centric PRD for ML-Ralph. Use when planning an ML project, experiment plan, or when asked to create an ML PRD. Triggers on: create a prd, write prd for, plan this ML feature, requirements for, sp...
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
Detailed procedures for finding, creating, and resuming collab sessions
Ruthlessly audit project features for justification. Challenge every feature to prove its value with evidence or face removal. Uses MCP tools for research.
Execute research experiments using TDD methodology. Pops plans from .claude/plans/research_tasks/, implements with smoke/unit/integration tests, and documents results to results.md. Use when: (1) executing the...
Explain technical projects, codebases, tools, or documentation to a non-engineer. Use when the user says "orient me", "explain this repo", "what does this do", "get me up to speed", "break this down for me", or...
Create an objective.json for goal-driven autonomous iteration. Use when you want to optimize toward a measurable target (performance, accuracy, coverage) rather than implement a specific PRD. Triggers on: creat...
Interacts with Linear for issue management. Use when the user asks about their issues, wants to create issues, or needs team/project IDs.
GitHub Issues を使ってバグ報告・機能要望・作業タスクを構造化する。テンプレ(再現手順/期待値/実績/環境)で書き、ラベル/優先度/受け入れ条件を揃える時に使う。キーワード: issue, bug, feature request, task, acceptan...
审核 ODIN 任务执行后的代码质量和规范。检查任务完成度、代码质量并生成审核报告。 由 odin-task-executor skill 调用,用户不应直接使用。
Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with c...
Remove a future phase from roadmap and renumber subsequent phases
Perform in-depth research on a feature using Jira, Confluence, and codebase analysis. Produces a comprehensive research document with feature overview, technology primers, gap analysis, and code impact assessme...
Create an interactive implementation plan and task breakdown from PRODUCT.md.
Execute ralph plan and implementation for a ticket
This skill should be used when the user asks to "design a system", "architect an application", "plan infrastructure", "create system architecture", "design for scale", "microservices architecture", "monolith vs...
Execute the implementation planning workflow using the plan template to generate design artifacts.
Review implemented work for correctness, test coverage, and code quality. May file blocking issues but NEVER closes the task under review. Used by coordinator as a subagent.
Comprehensive knowledge base for Photometrics AI, a street lighting optimization startup. Use when Ari needs help with any Photometrics AI business activity including sales materials, proposals, presentations,...
Analyze issues to identify the next work item and update focus.md. Enforces issue-first workflow and confidence-based batch limits.
TODO管理スキル 要件定義・設計段階でのTODO(不明点、仮定、リスク、技術的負債)を管理します。 既存ドキュメントからTODOを抽出し、対話的に確認・更新します。
Expense sharing calculations, split types (EQUAL/PERCENTAGE/FIXED), participant state management, and settlement tracking. Use when working with shared expenses, split calculations, payment status transitions,...
Daily morning briefing at 8:00 AM (or when user wakes up). Provides calendar summary, priorities from Responsibilities, urgent items, and suggested focus areas. Auto-invoke when it's 8 AM periodic pulse, user s...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.