conversation_evidence_sop
100 / 100 · Low risk
Fine to try.
SOP for extracting evidence from offline OpenAI-format conversations, distinguishing primary user questions from secondary context, and handling specific constraints (e.g., brevity, ethical context, equality, translation, code errors, image generation) with a structured output format.
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/'conversation-evidence-sop' ] || [ -L ~/.agents/skills/'conversation-evidence-sop' ]; then echo 'A skill folder named conversation-evidence-sop already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ECNU-ICALK/AutoSkill' "$d" && git -C "$d" checkout --quiet '94c47ca488d4ba4117d20272e66d49b9877e68cf' -- 'SkillBank/Users/chinese_gpt3.5_8_GLM4.7/conversation_evidence_sop' && mkdir -p ~/.agents/skills && cp -R "$d"/'SkillBank/Users/chinese_gpt3.5_8_GLM4.7/conversation_evidence_sop' ~/.agents/skills/'conversation-evidence-sop' && 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/'conversation-evidence-sop' ~/.claude/skills/'conversation-evidence-sop' (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
[](https://zalavijaysinh.github.io/skilltrust/repos/ECNU-ICALK/AutoSkill/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | 94c47ca | 100 |
| 2026-11-07 | 94c47ca | 100 |