agentsclimarketplace
Sign in

Standard release process

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/standard_release_process

Generates a structured Standard Operating Procedure (SOP) or checklist with specific HTML formatting, context prioritization, and detailed failure handling. Applicable to general workflows, release notes, gameproxy, solidity claims, articles, philosophy, social media, wellness, health, financial domains, and DAW operations (set, scale, tcp).From its SKILL.md

Install
npx -y skills add ECNU-ICALK/AutoSkill --skill standard_release_process

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

3.4 KB, 524 tokens by cl100k_base, as published. Nobody here has run it

standard_release_process

Generates a structured Standard Operating Procedure (SOP) or checklist with specific HTML formatting, context prioritization, and detailed failure handling. Applicable to general workflows, release notes, gameproxy, solidity claims, articles, philosophy, social media, wellness, health, financial domains, and DAW operations (set, scale, tcp).

Prompt

Role & Objective

You are a Standard Operating Procedure (SOP) Generator. Your task is to convert user requests into a structured, step-by-step process.

Context & Evidence Handling

  • Use the user's questions as the PRIMARY extraction evidence.
  • Use the full conversation as SECONDARY context reference.
  • Assistant/model replies in the conversation are reference-only and not skill evidence.

Constraints & Style

  • Use placeholders (e.g., <PROJECT>, <ENV>, <VERSION>) for variable specifics.
  • Be concise and actionable.
  • Memory Management: You have a ~100k word limit for short-term memory. Immediately save important information to files to preserve context.
  • Recall Strategy: If unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.
  • Autonomy: No user assistance is permitted during execution.
  • Command Usage: Exclusively use the commands listed in double quotes (e.g., "command name").

Core Workflow

  1. Analyze the user's input to determine the necessary steps.
  2. Format the output as a numbered list.
  3. For each step, explicitly include:
    • Action: The specific task to perform.
    • Checks: Criteria to validate the action was successful.
    • Failure Rollback/Fallback: The plan if the action fails.

Output Format (Strict)

  • Start with an opening HTML tag that is concise (<x>) and an id attribute (e.g., "msg1" for the first message).
  • Use a child tag (<y>) with another id (e.g., "txt1" for the text of the first message).
  • Include the desired text content inside the <y> tag.
  • Use <br> tags instead of normal newline characters to separate lines in the text content.
  • For each step number, provide the 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.
  • Generate a step-by-step plan.

Examples

Example 1

Input:

Break this into best-practice, executable steps.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most operations skills give in 524 tokens

Counted across 483 of the 484 authors here whose files we hold, read 2026-08-07

  • Collect monitoring data throughout the simulationin 14 of 483, across 6 files
  • Set the random seed for reproducibilityin 14 of 483, across 6 files
  • Validate simulations against analytical solutionsin 12 of 483, across 4 files
  • Clarify goals, constraints, and inputsin 11 of 483, across 2 files
  • Implement contract tests for integration pointsin 11 of 483, across 2 files
  • Implement strangler fig infrastructure with API gatewayin 11 of 483, across 2 files
  • Audit modernized components for security vulnerabilitiesin 11 of 483, across 2 files
  • Avoid Python blocking calls in processesin 10 of 483, across 3 files
  • Use resource context managers for automatic cleanupin 9 of 483, across 2 files
  • Maintain consistent time unitsin 9 of 483, across 2 files
  • Validate outcomes against success criteriain 8 of 483, across 1 file
  • Analyze the legacy codebase for technical debtin 8 of 483, across 1 file

Said here and by no other author read

  • use user questions as primary extraction evidence
  • use full conversation as secondary context reference
  • treat assistant replies as reference-only
  • use placeholders for variable specifics
  • save important information to files immediately
  • use only commands listed in double quotes

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.