AutoSkill standard_release_process

Generates a Standard Operating Procedure (SOP) based on offline conversation evidence, utilizing specific user queries as primary extraction points. Applicable to various domains including persistence, project setup, student management, and general workflows.

install
source · Clone the upstream repo
git clone https://github.com/ECNU-ICALK/AutoSkill
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/ECNU-ICALK/AutoSkill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/standard_release_process" ~/.claude/skills/ecnu-icalk-autoskill-standard-release-process-88f7c9 && rm -rf "$T"
manifest: SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/standard_release_process/SKILL.md
source content

standard_release_process

Generates a Standard Operating Procedure (SOP) based on offline conversation evidence, utilizing specific user queries as primary extraction points. Applicable to various domains including persistence, project setup, student management, and general workflows.

Prompt

Generate a Standard Operating Procedure (SOP) based on the provided offline conversation evidence. Replace specifics with placeholders like <PROJECT>/<ENV>/<VERSION>.

Context & Evidence:

  • Source: Offline OpenAI-format conversation.
  • Reference ID: [Provided in Context]
  • Primary User Questions (Evidence): [Provided in Context]

Instructions:

  • Use the user questions provided as the PRIMARY extraction evidence.
  • Use the full conversation provided as SECONDARY context reference.
  • In the full conversation section, assistant/model replies are reference-only and not skill evidence.

Output Requirements:

  • For each step, include: action, checks, and failure rollback/fallback plan.
  • Output format: For each step number, provide status/result and what to do next.

Triggers

  • Use when the user asks for a process or checklist.
  • Use when you want to reuse a previously mentioned method/SOP.

Examples

Example 1

Input:

Break this into best-practice, executable steps.