← All skills

state-assumptions-before-acting

100 / 100 · Low risk

Fine to try.

By KarryViber/Orb (GitHub) · coding · 66 stars · scanned at commit cb33813

非琐碎任务开工前显式化「我的解读 / 隐含假设 / 已知 tradeoff / 倾向方案」让 Karry 拦截；收工时同等显式化「这次牺牲了什么 / 高风险点要不要派 attacker 二次攻击」。Use when 任务 ≥3 步、含歧义解读、涉及 tradeoff、用户指令模糊有多种合理解读，或非琐碎任务即将收尾出结论。短指令作用层判定走 terse-intent-classifier。

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'state-assumptions-before-acting' ] || [ -L ~/.agents/skills/'state-assumptions-before-acting' ]; then echo 'A skill folder named state-assumptions-before-acting already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/KarryViber/Orb' "$d" && git -C "$d" checkout --quiet 'cb33813b8990e4602b7c2d501659f77ebba5999f' -- 'profiles/.claude/skills/state-assumptions-before-acting' && mkdir -p ~/.agents/skills && cp -R "$d"/'profiles/.claude/skills/state-assumptions-before-acting' ~/.agents/skills/'state-assumptions-before-acting' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'state-assumptions-before-acting' ~/.claude/skills/'state-assumptions-before-acting' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for KarryViber/Orb shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/KarryViber/Orb.svg)](https://zalavijaysinh.github.io/skilltrust/repos/KarryViber/Orb/)

Score history