OpenParable
Skip to content
← Back to skills

Conversation Evidence Sop

Documents
conversation_evidence_sop

Conversation Evidence Sop is an Agent Skill for documents published in the ECNU-ICALK/AutoSkill repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

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.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/ECNU-ICALK/AutoSkill/blob/HEAD/SkillBank/Users/chinese_gpt3.5_8_GLM4.7/conversation_evidence_sop/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/conversation-evidence-sop, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

conversation_evidence_sop

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.

Prompt

Role & Objective

Extract evidence from offline OpenAI-format conversations. Distinguish between primary user questions (main evidence) and secondary context, adhering to specific user constraints such as brevity, ethical context, equality, translation, technical debugging, or image generation requests.

Constraints & Style

  • Use placeholders like // for specifics.
  • Assistant/model replies in the full conversation are reference-only and NOT skill evidence.
  • Do not provide superfluous explanations; be concise and direct.
  • Handle specific user constraints strictly as part of the evidence extraction process.

Core Workflow

  1. Identify the Offline OpenAI-format conversation source.
  2. Set Title format: <HASH_ID>.json#conv_.
  3. Use the user questions below as the PRIMARY extraction evidence.
  4. Use the full conversation below as SECONDARY context reference.
  5. Extract and list Primary User Questions (main evidence) explicitly from the provided list.

Output Format

For each step number, provide:

  • Status/Result
  • What to do next
  • Action
  • Checks
  • Failure rollback/fallback plan

Triggers

  • Use when the user asks for a process or checklist.
  • Use when you want to reuse a previously mentioned method/SOP.
  • Use when extracting evidence with specific constraints (e.g., brevity, ethical context, equality, translation, code errors, image generation).

Examples

Example 1

Input:

Break this into best-practice, executable steps.

Example 2

Input:

Extract evidence regarding Maslow's theories and Gini coefficient from the conversation.

Notes:

Derived from candidate specific examples.

Example 3

Input:

Extract evidence regarding 'Awakening Age' and 'Li Keqiang' from the conversation.

Notes:

Derived from candidate specific context.