05-output-boundary
legal ai contextual chat
Install / Use
npx skills add semaj90/deeds_web_appInstalls into whichever agent you are using.
.clinerules
Cline rules
Quality Score
Category
Content & MediaSupported Platforms
Tags
Skill content
View source on GitHubOutput Boundary
- Do not write internal reasoning, scratch notes, or chain-of-thought into files.
- When producing reports or task updates, write only concise evidence: commands, results, file paths, counts, blockers, and next actions.
- If a task needs explanation, summarize the decision and evidence in plain prose; do not dump the full intermediate analysis.
- Keep generated markdown and JSON artifacts compact and machine-readable.
- If a prompt asks for "thinking", "reasoning", or "analysis", keep that in the conversation response only, not in workspace files.
Related Skills
siyuan
46.4kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间，让人与智能体在此协作
humanizer
50.9kAgent skill that removes signs of AI-generated writing from text
oh-story-claudecode
7.0kClaude Code / Codex / OpenCode agent skills for writing Chinese web novels (网文): 扫榜、拆文、写作、去AI味、封面全流程，长篇短篇都支持 | 13 skills for novel writing and long-form fiction with file-based continuity tracking. MIT.
iPolloWork
6.5kEnterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.
Security Score
Audited on Invalid Date