Agent output format
Skill lubochka/xiigen-mvp-engine/.claude/skills/universal/agent-output-format
Self-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
npx -y skills add lubochka/xiigen-mvp-engine --skill agent-output-formatAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 13 days oldThe repository was created 13 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.5 KB, as published. Nobody here has run it
Agent Output Format
Purpose
Use this for reviews, handoffs, phase reports, skill indexes, and multi-agent summaries.
When to Use
Invoke whenever output will be consumed by another agent, reviewer, or future session.
Actions
- Open with outcome status and the most important evidence.
- Use stable headings and tables when comparing many artifacts.
- Name files and commands exactly.
- Separate facts, decisions, risks, and recommendations.
- Keep language direct and avoid ceremonial framing.
XIIGen Adaptation
- Use XIIGen-owned terms consistently and only where applicable.
- When reporting conventions, distinguish verified facts from recommendations, such as DataProcessResult<T>, buildSearchFilter/buildSearchFilterFlat, or NestJS provider coverage.
Avoid
- Do not hide failures in a success summary.
- Do not mix implementation details with review conclusions unless they support a finding.
- Do not import source architecture, algorithms, design patterns, training, DPO, source domains, source classes, or source-specific paths.
Completion Signal
- The report can be read independently and supports follow-up without re-parsing the whole conversation.