Kickoff Branch logo

Kickoff Branch

Community
danielvm-git
kickoff-branch

Create an isolated Git worktree/branch or Jujutsu workspace, then verify a clean test baseline before code. Use when starting a feature or task.

Overview

Publisherdanielvm-git
Repositorybigpowers
Skill namekickoff-branch
Stars
206
Forks
18
Bundled files
Instructions only
LicenseMIT
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 danielvm-git on GitHub. Read the source before you install it.

Installation

Install the Kickoff Branch 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/danielvm-git/bigpowers.git /tmp/bigpowers
mkdir -p .claude/skills
cp -r /tmp/bigpowers/skills/kickoff-branch .claude/skills/kickoff-branch
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kickoff Branch 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 Kickoff Branch 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 Kickoff Branch 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.

story: e51s03

story: e20s03

story: e82s02

Kickoff Branch

HARD GATE — Direct Git work on main/master or reuse of an unrelated Jujutsu change is prohibited. Create a feature branch/worktree or Jujutsu workspace/change.

HARD GATE — Do NOT proceed with development until Preflight passes on the default branch. Red Preflight blocks branch creation and all forward work — invoke quick-fix or fix-bug per CONVENTIONS § Discovered Defects.

Create an isolated Git worktree or Jujutsu workspace before code. Preflight must be green first — solo-default owns the whole tree.

Process

1. Confirm task name

Ask if not already known: "What's the name of this feature or task?" Use it as the branch name slug (kebab-case, max 40 chars).

2. Select the VCS procedure

Read state.yaml vcs.kind. For jj, do not run the Git blocks below: verify with jj status and jj log -r '::@' -n 5, create isolation with jj workspace add ../<task-slug> -r @, then run jj -R ../<task-slug> describe -m "feat: <task>". Record the new stable change ID. For git, continue below.

2a. Anchor Git on the default branch (main or master)

HARD GATE — Git kickoff MUST start from an updated, clean default branch in the primary repository root (not a linked worktree).

bash
# Detect default branch
DEFAULT=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@' || echo main)

git checkout "$DEFAULT"
git pull --ff-only origin "$DEFAULT"   # skip if no remote
git status                             # working tree MUST be clean
git log --oneline -5

Spec-only pre-kickoff — before enforcing the clean-tree gate, check whether dirty files are spec artifacts:

bash
DIRTY=$(git status --porcelain | awk '{print $2}')
NON_SPEC=$(echo "$DIRTY" | grep -v '^specs/' || true)

if [ -z "$DIRTY" ]; then
  : # clean — proceed
elif [ -z "$NON_SPEC" ]; then
  # spec-only dirty tree — offer auto-commit
  echo "Dirty spec artifacts: $(echo $DIRTY | tr '\n' ' ')"
  read -p "Commit spec artifacts before kickoff? [Y/n]: " CONFIRM
  CONFIRM=${CONFIRM:-Y}
  if [[ "$CONFIRM" =~ ^[Yy] ]]; then
    git add specs/
    git commit -m "chore(state): checkpoint before kickoff"
  fi
else
  echo "Dirty tree: $NON_SPEC (not a spec artifact). Stash or commit before proceeding."
  exit 1
fi
  • Spec artifacts match specs/ — state.yaml, epics YAMLs, execution-status.yaml, etc.
  • Non-spec dirty files (src/, scripts/, SKILL.md, …) still enforce the full clean-tree gate.
  • If not on $DEFAULT after checkout, stop and fix before continuing.

3. Git pre-flight & conflict resolution

Before creating the worktree, verify the target environment is clean:

bash
# 1. Check for existing directory
ls -d ../<task-slug> 2>/dev/null

# 2. Check for existing branch
git branch --list <task-slug>

# 3. Check for "ghost" worktrees (metadata exists but directory is gone)
git worktree list | grep "<task-slug>"

Handling Conflicts:

  • Directory exists: If ../<task-slug> already exists, ask the user if they want to use it or delete it.
  • Branch exists: If the branch exists but no worktree is attached, ask to use the existing branch (git worktree add ../<task-slug> <task-slug>) or delete it.
  • Ghost worktree: If git worktree list shows the path but the directory is missing, run git worktree prune to clear the stale metadata. bash scripts/cleanup-worktrees.sh does this plus reports any worktree whose branch is already merged or deleted — advisory only, it prints the git worktree remove/git branch -d commands rather than running them, so review before acting.

4. Create Git worktree + branch

bash
# From the main repo root (not another worktree)
git worktree add ../<task-slug> -b <task-slug>
cd ../<task-slug>

If the user prefers a branch without a worktree:

bash
git checkout -b <task-slug>

4. Verify clean baseline

HARD GATE (e39s02): Acquire story lock in specs/agent-locks.yaml before running tests.

bash
LOCK="specs/agent-locks.yaml"; STORY="<story-id>"
if [ -f "$LOCK" ]; then
  python3 -c "
import yaml,sys,datetime
d=yaml.safe_load(open('$LOCK'))or{'locks':[]}
for l in d['locks']:
  if l['story_id']=='$STORY':print(f'LOCKED by {l[\"locked_by\"]} at {l[\"locked_at\"]}');sys.exit(1)
d['locks'].append({'story_id':'$STORY','locked_by':'agent: build-epic','locked_at':datetime.datetime.utcnow().strftime('%Y-%m-%dT%H:%M:%SZ'),'files_touched':[]})
yaml.dump(d,open('$LOCK','w'),default_flow_style=False)
print(f'LOCK ACQUIRED: $STORY')
"
fi

If locked: abort. If unlocked: entry added, proceed.

Run Preflight (from CLAUDE.md Commands table, or BP_PREFLIGHT from bash scripts/bp-read-agents.sh) and confirm green before writing any code:

bash
# Preflight — project's full local verification stack
# bigpowers example:
npm run compliance && bash scripts/run-verification-gates.sh

# Or project-specific from CLAUDE.md / AGENTS.md
  • Preflight passes (all chained gates green)
  • No type errors (npm run typecheck or equivalent, if not in Preflight)
  • No lint errors (npm run lint or equivalent, if not in Preflight)

If Preflight is red, stop — route to quick-fix or fix-bug. Fix before kickoff continues.

5. Confirm readiness

Report: ✓ Preflight green + branch + worktree. Suggest next: develop-tdd or execute-plan.

Handoff

Gate: READY -> next: develop-tdd Writes: state.yaml handoff.next_skill = develop-tdd

Frequently asked questions

What does the Kickoff Branch AI skill do?

Create an isolated Git worktree/branch or Jujutsu workspace, then verify a clean test baseline before code. Use when starting a feature or task.

Why use Kickoff Branch on TypingMind?

Because you install it once and use it with any model. Kickoff Branch 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 Kickoff Branch in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/danielvm-git/bigpowers/tree/main/skills/kickoff-branch. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kickoff Branch?

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 Kickoff Branch?

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

Is the Kickoff Branch AI skill free?

Yes. It is published on GitHub by danielvm-git under the MIT 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 👇