Ring:Generating Release Guides logo

Ring:Generating Release Guides

Organization
LerianStudio
ring:generating-release-guides

Generating an internal Operations-facing update/migration guide from the git diff between two refs, documenting per-change client impact, deploy ordering, monitoring, and rollback notes in English, pt-br, or both. Use when preparing a version release or recording what changed for the Ops team. Runs read-only by default and previews before writing. Skip with no git repo or a trivial single-file change.

Overview

PublisherLerianStudio
Repositoryring
Skill namering:generating-release-guides
Stars
215
Forks
28
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by LerianStudio on GitHub. Read the source before you install it.

Installation

Install the Ring:Generating Release Guides AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LerianStudio/ring.git /tmp/ring
mkdir -p .claude/skills
cp -r /tmp/ring/default/skills/generating-release-guides .claude/skills/lerianstudio-ring-generating-release-guides
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ring:Generating Release Guides in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ring:Generating Release Guides on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ring:Generating Release Guides is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Release Guide — Ops Update Guide Generator

When to use

  • Preparing to release a new version
  • Need to document what changed between refs
  • Creating operational update guide
  • Communicating version updates to Ops team

Skip when

  • No git repository available
  • Single file change (too small for formal guide)
  • Customer-facing release notes only (use simpler template)

Inputs

  • BASE_REF (string, required): e.g. main, v1.0.0
  • TARGET_REF (string, required): e.g. HEAD, v1.1.0
  • VERSION (string, optional): auto-detected from tags if not provided
  • LANGUAGE (enum, optional, default en): en, pt-br, both
  • MODE (enum, optional, default STRICT_NO_TOUCH): STRICT_NO_TOUCH, TEMP_CLONE_FOR_FRESH_REFS

Produce an internal Operations-facing update/migration guide from git diff analysis.

Safety Modes

STRICT_NO_TOUCH (default): Read-only git commands only. Forbidden: fetch, pull, push, checkout, switch, reset, commit, merge, rebase. If ref doesn't exist locally → STOP and suggest TEMP_CLONE mode.

TEMP_CLONE_FOR_FRESH_REFS: Clone to temp dir, fetch refs there, run all analysis in clone, cleanup after. Never touches current repo.

Process

Step 0: Execution Location

Determine mode. In TEMP_CLONE mode, create isolated clone before proceeding.

Step 1: Resolve Refs

bash
git rev-parse --verify BASE_REF^{commit}   # verify both refs exist
git rev-parse --verify TARGET_REF^{commit}
BASE_SHA=$(git rev-parse --short BASE_REF)
TARGET_SHA=$(git rev-parse --short TARGET_REF)

Step 1.5: Version Detection

bash
# If TARGET_REF is a tag, extract version
# Note: avoid /i flag (GNU-specific); use explicit case alternation for portability (macOS + Linux)
if git tag -l "$TARGET_REF" | grep -q .; then
    AUTO_VERSION=$(echo "$TARGET_REF" | sed -E 's/^[Vv]//;s/^[Rr]elease[-_]?//;s/^[Vv]ersion[-_]?//')
fi
# Priority: explicit VERSION > auto-detected > none (omit from title)

Step 1.6: Commit Log Analysis

bash
git log --oneline --no-merges BASE_REF...TARGET_REF
git log --pretty=format:"%h %s%n%b" --no-merges BASE_REF...TARGET_REF

Parse commit prefixes: feat: → Feature, fix: → Bug Fix, refactor: → Improvement, breaking: / BREAKING CHANGE: → Breaking.

Step 2: Produce Diff

bash
git diff --find-renames --find-copies --stat BASE_REF...TARGET_REF
git diff --find-renames --find-copies BASE_REF...TARGET_REF

Step 3: Build Change Inventory

From diff, identify: endpoints (new/changed/removed), DB schema/migrations, messaging (topics/payloads), config/env vars, auth changes, performance (timeouts/pools), dependency bumps with runtime impact, observability changes.

Step 4: Write Guide

Use language-appropriate template based on LANGUAGE parameter.

English title: # Ops Update Guide — <repo> — <VERSION> — <TARGET_SHA>
Portuguese title: # Guia de Atualização (Ops) — <repo> — <VERSION> — <TARGET_SHA>
(Without version: use BASE_REF → TARGET_REF instead of <VERSION>)

Header block: Mode, Comparison, Base SHA, Target SHA, Date, Source.

Per section format: ## N. Descriptive Title [Category Emoji]

CategoryEnglishPortugueseEmoji
FeatureFeatureFuncionalidade
Bug FixBug FixCorreção🐛
ImprovementImprovementMelhoria🆙
BreakingBreakingBreaking⚠️
InfrastructureInfrastructureInfra🔧
ObservabilityObservabilityObservabilidade📊
DataDataDados💾

Each section contains (in order):

  1. Contextual narrative (1-3 paragraphs) — business/operational context, why this changed
  2. What Changed / O que mudou — bullet list with file:line references
  3. Why It Changed / Por que mudou — infer from code; if uncertain mark as ASSUMPTION + HOW TO VALIDATE
  4. Client Impact / Impacto para clientes — who's affected, risk level (Low/Medium/High)
  5. Required Client Action / Ação necessária do cliente — "None" or exact steps
  6. Deploy/Upgrade Notes / Notas de deploy/upgrade — ordering, rolling deploy safety
  7. Post-Deploy Monitoring / O que monitorar pós-deploy — logs in table format (Level | Message | Meaning), tracing spans in table format
  8. Rollback — Safety: Safe/Conditional/Not recommended (or pt-br equivalents) + steps

Special sections when applicable:

  • ### ⚠️ Attention Point — confusing but expected behaviors
  • Backward compatibility table for data/schema changes

Step 5: Summary Section

English: Summary table (Features/Bug Fixes/Improvements/Data counts) + Rollback Compatibility matrix (| Item | Rollback | Justification |).

Portuguese: ## Resumo + ## Análise de Compatibilidade de Rollback with same structure.

Step 6: Preview Before Saving (MANDATORY)

Show before writing to disk:

  • Repository, comparison range, version detected, language(s), mode
  • Change summary table (categories + counts)
  • Top 5 key changes
  • Output file path(s)

Wait for user confirmation.

Step 7: Save File

Output directory: notes/releases/

Has Version?LANGUAGEFilename
Yesen{DATE}_{REPO}-{VERSION}.md
Yespt-br{DATE}_{REPO}-{VERSION}_pt-br.md
Noen{DATE}_{REPO}-{BASE}-to-{TARGET}.md
Nopt-br{DATE}_{REPO}-{BASE}-to-{TARGET}_pt-br.md
AnybothBoth files above

Confirm after saving: file path(s), refs/SHAs used, version, language(s).

Hard Rules

RuleRequirement
No invented changesMUST: All changes traceable to diff — nothing invented
Uncertain infoMUST: Mark uncertain claims as ASSUMPTION + HOW TO VALIDATE
Preview requiredMUST: Show preview before saving — never skip
User confirmationMUST: Wait for explicit user confirmation before writing files
Special change typesMUST: Explicitly document DB migrations, breaking API, feature flags, security/auth, log level changes

Blocker Conditions

ConditionAction
Ref cannot be resolved in STRICT modeSTOP — suggest TEMP_CLONE mode
Not in git repositorySTOP — skill requires git context
diff returns emptySTOP — verify refs have commits between them
User declines previewSTOP — ask for corrections or abort confirmation

Frequently asked questions

What does the Ring:Generating Release Guides AI skill do?

Generating an internal Operations-facing update/migration guide from the git diff between two refs, documenting per-change client impact, deploy ordering, monitoring, and rollback notes in English, pt-br, or both. Use when preparing a version release or recording what changed for the Ops team. Runs read-only by default and previews before writing. Skip with no git repo or a trivial single-file change.

Why use Ring:Generating Release Guides on TypingMind?

Because you install it once and use it with any model. Ring:Generating Release Guides is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ring:Generating Release Guides in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LerianStudio/ring/tree/main/default/skills/generating-release-guides. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ring:Generating Release Guides?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ring:Generating Release Guides?

As many as you like. As long as a model supports skills, you can use Ring:Generating Release Guides with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ring:Generating Release Guides AI skill free?

Yes. It is published on GitHub by LerianStudio under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇