Help us improve
Share bugs, ideas, or general feedback.
From flow
Create branches with naming conventions, load issue context, perform impact analysis, and decompose acceptance criteria into parallel tasks. Use when starting work on a GitHub issue.
npx claudepluginhub synaptiai/synapti-marketplace --plugin flowHow this skill is triggered — by the user, by Claude, or both
Slash command
/flow:branch-and-task-managementThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Domain skill for starting work: branch setup, context loading, and task decomposition.
Creates synced feature branches for new tasks: pulls latest main, fetches context from Jira tickets/GitHub issues/local specs, pushes {type}/{task-number}/{slug} branches.
Syncs Claude Code sessions with GitHub Issues as a shared plan — reads issue context on branch detection, updates progress via comments, checks off tasks, and creates issues from plans.
Processes GitHub issues via TDD workflow on main branch: interactive selection, auto-prioritization, label filtering, conflict detection, and parallel task execution.
Share bugs, ideas, or general feedback.
Domain skill for starting work: branch setup, context loading, and task decomposition.
NO CODE BEFORE CONTEXT. Read the issue, load the history, understand the scope — then create the branch.
Starting a branch without loading issue context leads to misaligned implementations and wasted effort.
Before creating a branch, confirm:
Follow project conventions from settings or CLAUDE.md:
DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name' 2>/dev/null || echo "main")
git fetch origin "$DEFAULT_BRANCH"
git checkout -b "feature/issue-{N}-{desc}" "origin/$DEFAULT_BRANCH"
Branch naming patterns (from settings.json → conventions.branchPatterns):
feature/issue-{N}-{desc} — New featuresfix/issue-{N}-{desc} — Bug fixesdocs/issue-{N}-{desc} — DocumentationKeep {desc} to 3-5 words, kebab-case, meaningful.
Fetch issue details in parallel:
# Parallel: issue details + comments + linked issues
gh issue view $N --json title,body,labels,assignees,milestone
gh issue view $N --comments
Extract from issue body:
- [ ] item becomes a taskBefore implementation, identify affected areas:
# Search for related code
grep -r "keyword_from_issue" --include="*.{rb,js,ts,py}" -l
# Check recent changes in related areas
git log --oneline -10 -- "path/to/related/"
Map acceptance criteria to likely file changes. Flag if the issue touches:
Convert acceptance criteria to tasks using TaskCreate:
For each acceptance criterion:
TaskCreate(
subject: "Implement: {criterion summary}",
description: "Acceptance criterion: {full text}\nLikely files: {paths}\nVerification: {how to check}"
)
Rules:
Identify tasks that can run concurrently:
If agent teams are enabled and >5 acceptance criteria with independent file sets → suggest team dispatch.
Create {JOURNAL_DIR}/issue-{N}.md (journal dir defaults to .decisions/):
# Decision Journal: Issue #{N} — {title}
**Issue**: #{N} | **Branch**: {branch-name} | **Started**: {YYYY-MM-DD}
---
The autonomous-workflow skill governs ongoing journal entry format (Init/Log/Summarize).
Branch setup is valid when: