Archive completed milestone and prepare for next version
SAM-style feature initiation workflow: discovery -> codebase analysis -> architecture spec -> task decomposition -> validation -> context manifest.
Explain how and when to use Chain of Verification (CoVe) in prompt design. Use when designing prompts that require factual accuracy, self checking, or reduction of hallucinations.
Optimize CLAUDE.md — remove noise (directory trees, type defs, tool tables), keep only commands, constraints, and architecture rules that agents can't discover from code
Generate a single worker task prompt using the existing CLEAR + selective CoVe task design standard and the task structure requirements used by swarm-task-planner.
\"Holistic completion workflow after a feature's tasks are marked COMPLETE: code review, feature verification, integration check, documentation drift audit/update, and context…
Surface prior investigations from past Claude Code sessions on the current topic. Greps ~/.claude/projects/*/memory/ and recent transcripts for keyword matches.
Perform holistic review of completed refactoring, validate improvements, and create follow-up tasks if needed
Generate descriptive commit messages by analyzing git diffs, very fast and context pollution safe. Use on any request to commit staged changes.
Combine CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) and CoVe (Chain of Verification) to write and lint agent task files that will be executed by worker agents.
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, distributing workload, or orchestrating multi-agent workflows.
This skill should be used when the user asks to "review test coverage", "audit test quality", "check tests for completeness", or mentions reviewing pytest test suites.
This skill should be used when the user asks to "create a feature task", "set up development tracking", "plan a feature implementation", or needs to structure a new feature…
Terminal UX with Rich -- console setup, tables, panels, progress, logging, tracebacks, live updates. Load when building polished CLI output.
Reference guide for Claude Code skills system (January 2026). Use when creating, modifying, or understanding skills, SKILL.md format, frontmatter fields, hooks, context fork, or…
Coordinate multi-agent swarms for parallel and pipeline workflows. Use when coordinating multiple agents, running parallel reviews, building pipeline workflows, or implementing…
The model must apply when tasks involve .gitlab-ci.yml configuration, GitLab Flavored Markdown (GLFM) syntax, gitlab-ci-local testing, CI/CD pipeline optimization, GitLab CI Steps…
Assess a plugin and create refactoring task files for parallel agent execution
Implement approved plans into production-ready code. Use when user wants to build, implement, code, or execute an approved plan.
Learn Claude Code in 5 hands-on lessons. From basics to building applications. Use when: user wants to learn Claude Code, asks "how do I...", or is new.
Execute refactoring tasks from a task file with parallel agent orchestration
Query and manage feature implementation task status. Provides CLI tools to list features, check task status, find ready tasks, and validate task files.
Build Model Context Protocol (MCP) servers - comprehensive coverage of generic MCP protocol AND FastMCP framework specialization.
创建和配置 Claude Code 钩子以自定义代理行为。当用户需要以下操作时使用：(1) 创建新钩子，(2) 配置自动格式化、日志记录或通知，(3) 添加文件保护或自定义权限，(4) 设置工具执行前后的操作，(5) 询问钩子事件如 PreToolUse、PostToolUse、Notification 等。
Bilimsel metod, hipotez, kanıt değerlendirme, bias analizi. ⚠️ Araştırma/analiz için kullan. Mimari karar için → ultrathink-core.
Primary planning branch after /shape for major-tranche work that requires multiple independent PRDs. Use to create a GitHub milestone plus sequenced feature issues that will later…
Reflect on current session and suggest improvements to agents, commands, templates, workflows
Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.
Move an increment to backlog (planned but not ready to start)
Turn ideas into fully formed designs and specifications through structured collaborative dialogue. Use BEFORE any creative or implementation work — when exploring feature ideas,…
Autonomous feature research and gap analysis. Use when starting /add-new-feature or analyzing existing architecture documents.
Sammanfatta en TTRPG-session från ett mötesstranskript till en underhållande och korrekt sessionssammanfattning på svenska.
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into…
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns.
Uses the uv Python package and project manager correctly for dependencies, venvs, and scripts. Use when creating or modifying Python projects, adding dependencies, running scripts…