TRIP 3 Release logo

TRIP 3 Release

Community
PiLastDigit
TRIP-3-release

Release a completed implementation - version, code review promotion, changelogs, docs, commit, tag, ff-merge, push

Overview

PublisherPiLastDigit
RepositoryTRIP-workflow
Skill nameTRIP-3-release
Stars
636
Forks
91
Bundled files
Instructions only
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 PiLastDigit on GitHub. Read the source before you install it.

Installation

Install the TRIP 3 Release 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.
    https://github.com/PiLastDigit/TRIP-workflow/tree/master/skills/TRIP-3-release
  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/PiLastDigit/TRIP-workflow.git /tmp/TRIP-workflow
mkdir -p .claude/skills
cp -r /tmp/TRIP-workflow/skills/TRIP-3-release .claude/skills/TRIP-3-release
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable TRIP 3 Release 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 TRIP 3 Release 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 TRIP 3 Release 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 Mode

You are now in release mode for [PROJECT_NAME].

Release: $ARGUMENTS

This skill runs after TRIP-2-implement has converged (implementation done, testing gate green, Codex code review APPROVED or explicitly skipped). It is normally chained from TRIP-2 in the same session, but can be invoked standalone in a fresh session.


Prerequisites

  • Implementation complete and user-confirmed.
  • Testing gate green: affected unit tests pass.
  • Codex code review converged (APPROVED), or explicitly skipped by the user.
  • Lint and type-check/build green.

Standalone verification (fresh session, not chained from TRIP-2)

If this skill was NOT chained from a TRIP-2 session in the current conversation, verify before any release step:

bash
# [ADAPT_TO_PROJECT: Replace with actual lint/type-check/test commands during Init]
[LINT_COMMAND]
[TYPECHECK_COMMAND]
[TEST_COMMAND] <pattern-from-the-plan's-Test-Impact-section>

All must be green. Also verify the Codex state file exists for the given plan path/label (see Step 3 below); if absent, treat as the skipped-Codex fallback (manual CR) and say so explicitly in the CR.

Any failure blocks the release — fix or return to TRIP-2-implement first.


Step 1: Get Current Date/Week

Run this command to get date and project week:

bash
date '+%d-%m-%Y %H:%M' && python3 -c "from datetime import date; print('Project week:', (date.today() - date.fromisoformat('[WEEK_ANCHOR_DATE]')).days // 7 + 1)"

(Week anchor: the Monday of the week TRIP Init was run. Python is used instead of date -d because macOS BSD date doesn't support it. If python3 is not on PATH — e.g. Git Bash on Windows — use python instead.)

Use the project week in all subsequent steps.

Step 2: Version Update

  • If not already done in the plan phase, propose new SemVer version (x.y.z)
  • Update version in [VERSION_FILE]
  • Do not modify anything else in this file

Step 3: Promote Code Review

Now that week (a) and version (x.y.z) are known:

  1. Compute state file path (derive the key via key.sh so it matches what the review scripts actually wrote — never re-derive it inline):

    bash
    STATE_KEY="$(bash .claude/skills/codex-plan-review/scripts/key.sh <plan-path>)"
    STATE_FILE=".claude/skills/codex-code-review/state/${STATE_KEY}.review.txt"
  2. Content source:

    • Multi-round loop: state file has synthesized review + PROMOTION_READY. Strip sentinel.
    • Turn 1 convergence: state file has full review already.
    • Skipped Codex: write CR from .claude/skills/TRIP-review/cr-template.md with body "Code review skipped — trivial change." Verdict: APPROVED with observations.
  3. Replace <x.y.z> with actual version. Fill any remaining <...> placeholders.

  4. Save to docs/3-code-review/CR_wa_vx.y.z.md.

  5. Verify: no <...> placeholders, no PROMOTION_READY, version matches version file.

Step 4: Commit Message

Propose a one-line commit message.

Step 5: Changelog File

Create docs/2-changelog/wa_vx.y.z.md (a=project week, x.y.z=version):

markdown
# Changelog - Week a, DD-MM-YYYY, V. x.y.z

**Release Date**: Week a, DD-MM-YYYY at HH:MM
**Version**: x.y.z (previously x0.y0.z0)
**Object**: the commit message
**Code review**: `docs/3-code-review/CR_wa_vx.y.z.md` (Codex loop, N rounds -> verdict)

## Changes

[Describe what changed]

Step 6: Changelog Table

Add entry on top of docs/2-changelog/changelog_table.md:

markdown
| `x.y.z` | a | the commit message |

Also add a summary entry in the Changelog Summary section.

Step 7: Architecture Update

  1. Read fully @docs/ARCHI-rules.md
  2. Update @docs/ARCHI.md following the rules
  3. Run bash .claude/skills/TRIP-compact/count-tokens.sh docs/ARCHI.md to check token count

Warning: If ARCHI.md exceeds ~20,000 tokens, warn the user:

"ARCHI.md is at ~X tokens. Consider running TRIP-compact to reduce it before committing."

Step 8: README Update

Update README.md with the new version number. (Content corrections belong to Documentation Sync, next step — do not sync sections here.)

Step 9: Documentation Sync

Keep the pre-existing (non-TRIP) documentation aligned with the code:

  1. Read the plan's Documentation Impact section.
  2. Contrast it with the actual diff of the release (git diff [MAIN_BRANCH]...HEAD or equivalent) — the plan may have fallen short; a doc affected by the real changes must be synced even if the plan didn't list it.
  3. Update every affected document. Factual corrections only: commands, paths, build targets, script/table entries, cadences, config/env vars, structure trees. It is forbidden to touch the voice, tone, or strategic/editorial content of these documents.
  4. The updated files are included in the release commit (Step 10) — never a separate commit.

If the plan says "None" and the diff confirms it, skip with a one-line note.


After completing all documentation steps, use the AskUserQuestion tool to ask:

  • Question: "All documentation steps are complete. Ready to commit?"
  • Options: "Yes, commit now" (proceed with git commit and tag), "Not yet" (review changes first)

ONLY after user selects "Yes", proceed:

Step 10: Commit

bash
git add -A && git commit -m "<commit message from Step 4>"

Important: Only use the commit message. Do NOT add Co-Authored-By or any other trailer.

Step 11: Tag

bash
git tag vx.y.z

Step 12: Merge (fast-forward)

Merge the feature branch back into the main branch, keeping a single clean linear history:

bash
git checkout [MAIN_BRANCH]
git merge --ff-only <feature-branch>
git branch -d <feature-branch>

If --ff-only fails, the main branch moved during implementation — rebase the feature branch onto it, then retry. Never create a merge commit.

Step 13: Push

Use the AskUserQuestion tool to ask:

  • Question: "Release vx.y.z is committed, tagged, and merged. Push to remote?"
  • Options: "Yes, push now" (push branch and tags), "Not yet" (push manually later)

If "Yes":

bash
git push && git push --tags

Frequently asked questions

What does the TRIP 3 Release AI skill do?

Release a completed implementation - version, code review promotion, changelogs, docs, commit, tag, ff-merge, push

Why use TRIP 3 Release on TypingMind?

Because you install it once and use it with any model. TRIP 3 Release 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 TRIP 3 Release in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PiLastDigit/TRIP-workflow/tree/master/skills/TRIP-3-release. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use TRIP 3 Release?

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 TRIP 3 Release?

As many as you like. As long as a model supports skills, you can use TRIP 3 Release with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the TRIP 3 Release AI skill free?

It is published on GitHub by PiLastDigit. Check the repository for licensing terms. 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 👇