Loading...
Loading...
Found 72 Skills
Kanban methodology including boards, WIP limits, flow metrics, and continuous delivery. Activate for Kanban boards, workflow visualization, and lean project management.
Use to design provider sequences, throttling logic, and credit policies for enrichment waterfalls.
Use when users say "create a skill", "make a new skill", "build a skill", "skill for X", "package this as a skill", or when refactoring/updating/auditing existing skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.
Guides teams through designing, implementing, and optimizing CI/CD pipelines, GitHub Actions workflows, deployment automation, and agentic workflow patterns. Provides production-ready templates, cost optimization strategies, quality gates, and multi-environment deployment planning for modern DevOps practices.
Design prompts, schemas, validation, and recovery logic for reliable machine-readable model outputs. Use when generating JSON, typed objects, extraction results, tool arguments, or any output another system must parse safely.
暗终端 honest-review deck —
Use when the user reaches for a Code node, mentions writing JavaScript or Python in n8n, or any custom logic comes up in workflow design. Triggers on "Code node", "Code", "JavaScript", "Python", "custom logic", "transform data", "$input", "$json transformation", "loop in code", "write a function", or any time the obvious answer seems to be "just put it in code."
Document the pitfalls encountered or good practices discovered during this work into searchable learning documents, which can be accessed by both AI and humans when similar tasks arise in the future. Two tracks: The pitfall track records experiences where "things should have worked but didn't" — including bugs, configuration traps, environment issues, and integration failures; The knowledge track records findings that "should be the default approach going forward" — including best practices, workflow improvements, and reusable patterns. Trigger scenarios: Proactively prompt at the end of feature-acceptance or issue-fix workflows, or when the user mentions phrases like "document knowledge", "learning", "document learnings", or "record this experience". Spec documents record what was done, while learning documents record what pitfalls were encountered / what was learned — they complement each other and are not interchangeable.
Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.
Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.
Use when running the CTO flow-optimization loop — WIP scan, epic focus, triage unlabeled issues, and dispatch.