By kesteva
Orchestrate a solo product-development pipeline directly within Claude Code: capture raw ideas, clarify them through structured probing, break them into execution-ready tasks, run automated sprints with code review and visual verification, then compound learnings back into the backlog.
Quickly capture multiple ideas and tasks from a braindump session
Identify, resolve, and verify a bug. Spawns bug-investigator → executor → shadow-verifier in sequence.
Propose learnings from completed sprint(s) in three buckets (clean-ups, backlog tasks, CLAUDE.md improvements) plus optional SoloFlow self-improvement feedback (tester mode), then apply what the user approves. Batches multiple pending sprints into one merged proposal when --all or multi-select subset is used.
Walk through SoloFlow configuration and adjust settings interactively
Clean up .soloflow/ state cruft (orphan plans, ghost sprint entries, stale stuck files, mid-commit settle crashes, empty epics, malformed queue entries)
Investigates a bug report — performs read-only root-cause analysis and produces a structured fix plan. Does NOT modify code.
Reviews CLAUDE.md improvement proposals against the existing codebase and CLAUDE.md files, producing tightly scoped diffs at the lowest appropriate directory level
Reviews all CLAUDE.md files for focus, trims redundancy, and identifies content that should be moved to specialized reference files
Reviews completed code for quality, reuse, and security
Reviews a codebase for redundancy, inefficiency, orphaned code, and dead exports, then produces a structured pruning proposal
This skill should be used when a raw user idea is ambiguous and needs conversational disambiguation before structured extraction or planning. Provides a clarification loop with ambiguity checklist, scope-decomposition gate, one-question-at-a-time probing, and a readiness gate.
Deep conversational questioning to build a project roadmap brief before research and epic generation. Provides an 8-point checklist, scope-decomposition gate, one-question-at-a-time probing, and a readiness gate.
This skill should be used when verifying UI changes visually. Mobile prefers Maestro MCP with Maestro CLI fallback. Web uses Playwright MCP. macOS prefers Peekaboo MCP with the peekaboo CLI fallback. Provides patterns for availability probes, path selection, ephemeral/inline flows, screenshot capture, and view hierarchy inspection.
Matches all tools
Hooks run on every tool call, not just specific ones
Modifies files
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Hook triggers on file write and edit operations
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Soloflow is a hooks-based workflow orchestration for solo product development with Claude Code.
It's built specifically to address some of the limitations of using Claude Code as a solo developer work on side projects and aims to solve two core problems:
To address this, Soloflow automates the product development lifecycle through five stages: idea extraction → refinement → execution → verification → learning. Each stage is designed so you provide input at the beginning and then the agent runs autonomously while you walk away. Check in occasionally in your terminal or from your phone to tee up the next stage.
With that said, even with the rough edges, it works.
The fastest way to get started is to install the plugin inside Claude Code (two steps — add the marketplace, then install):
/plugin marketplace add kesteva/soloflow
/plugin install soloflow@soloflow
By default this installs at user scope — available in every project on your machine. To scope it to a single project, use the CLI form with --scope project:
claude plugin install soloflow@soloflow --scope project
Alternatively, you install the plugin by opening /plugins within Claude Code, adding the marketplace, and then installing the plugin through there.
Once you've installed the plugin, run /soloflow:init to initialize the project. This will create a .soloflow/ directory which holds all workflow files.
From there, you can tackle a simple task using /soloflow:quick, for example:
/soloflow:quick "fix the loading indicator on the character generation screen which currently shows a question mark"
This will take a single task through the execution -> verification -> review loop.
To test on the full workflow, go through four commands in sequence:
/soloflow:idea-extractor: use this to capture an idea that Claude will then refine. It will ask you questions to understand your intent./soloflow:planner this turns the idea into execution ready tasks for Claude./soloflow:sprint takes tasks through the execution -> verification -> review loop/soloflow:compound optional final stage, but extracts learnings from your sprint including clean-up items, tasks to add to the backlog, and improvements to your project documentation.If you are working in an established project, an optional first step is to run /soloflow:map-codebase which will create Architecture and Code Patterns documentation for your project as well as nested claude.md's where applicable. If you don't want it editing or creating your Claude.md then call it with flag --skip-claudemd.
SoloFlow ships as a self-hosted plugin marketplace. From inside Claude Code:
/plugin marketplace add kesteva/soloflow
/plugin install soloflow@soloflow
The first command registers this repo as a marketplace (reading .claude-plugin/marketplace.json). The second installs the soloflow plugin from that marketplace.
npx claudepluginhub kesteva/soloflow --plugin soloflow-devResearch-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and adversarial review. 51 commands, 15 agents across 7 departments.
Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams
HarnessFlow — From idea to shipped product: high-quality engineering workflows for AI agents. Spec-anchored SDD, gated TDD, evidence-based routing, independent reviews, and formal closeout.
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Compound Engineering workflow: PRD-driven sprints, isolated worktrees, hook-enforced safety, automated learning. Skills become /vini-workflow:plan, /vini-workflow:compound, etc.
Autonomous Development Orchestrator - Transform ideas into production-ready applications through multi-agent pipeline. Spec → Plan → Tasks → 100% Working App.