soloflow-dev

Plugin soloflow-dev from marketplace soloflow in kesteva/soloflow. Commands read from the repo's manifest — 1 month ago.

Skills (3)

• clarify-idea

  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.

• clarify-roadmap

  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.

• visual-verify

  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 captur

Slash commands (22)

• /soloflow-dev:braindump

  Quickly capture multiple ideas and tasks from a braindump session

• /soloflow-dev:bugfix

  Identify, resolve, and verify a bug. Spawns bug-investigator → executor → shadow-verifier in sequence.

• /soloflow-dev:compound

  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 subse

• /soloflow-dev:config

  Walk through SoloFlow configuration and adjust settings interactively

• /soloflow-dev:housekeeping

  Clean up .soloflow/ state cruft (orphan plans, ghost sprint entries, stale stuck files, mid-commit settle crashes, empty epics, malformed queue entries)

• /soloflow-dev:idea-extractor

  Extract a structured idea from raw input, with optional external research

• /soloflow-dev:init

  Scaffold or repair the .soloflow/ state directory and run the setup wizard

• /soloflow-dev:mad-max

  Unattended backlog-drain mode — runs executor → verifier → code-reviewer loops on all ready tasks, logs stuck/human-needed, never prompts. Visual verify off; parallel by default.

• /soloflow-dev:map-codebase

  Survey the project and create missing CLAUDE.md, ARCHITECTURE.md, and CODE-PATTERNS.md so future agents have shared context to load on entry

• /soloflow-dev:planner

  Plan a new idea, braindump multiple items, or refine an existing idea into execution-ready tasks

• /soloflow-dev:prune

  Deep-clean the codebase — remove dead code, trim CLAUDE.md files, and verify no regressions

• /soloflow-dev:quick

  Lightweight bugfix path — skip refinement, go straight to executor + verifier

• /soloflow-dev:review-queue

  Triage pending human-review items — resolve cruft, walk Decisions/Actions/Testing/Deferred Visual buckets, refine found issues into backlog tasks

• /soloflow-dev:roadmap

  Generate a phased roadmap from a project vision, with deep questioning, parallel research, and epic generation

• /soloflow-dev:sprint-and-compound

  Run /soloflow:sprint with /soloflow:compound interleaved before the merge choice — one end-to-end flow with a single final merge prompt

• /soloflow-dev:sprint

  Run an execution sprint over ready tasks in the backlog

• /soloflow-dev:status

  Show current SoloFlow sprint state and task progress

• /soloflow-dev:summarize-roadmap

  Summarize the backlog as a one-line-per-task roadmap, grouped by epic

• /soloflow-dev:sync-agents

  Re-sync MCP-dependent agent shadows in .claude/agents/ against the current plugin version

• /soloflow-dev:update

  Check for SoloFlow updates, run pending state migrations, and show the right install command

• /soloflow-dev:verify

  Run standalone visual verification using Maestro MCP (mobile, falls back to CLI) and/or Playwright MCP (web)

• /soloflow-dev:visual-smoke

  Smoke-test visual verification — verify Maestro (mobile) and Playwright (web) are working end-to-end

Subagents (17)

• bug-investigator

  Investigates a bug report — performs read-only root-cause analysis and produces a structured fix plan. Does NOT modify code.

• claude-md-reviewer

  Reviews CLAUDE.md improvement proposals against the existing codebase and CLAUDE.md files, producing tightly scoped diffs at the lowest appropriate directory level

• claudemd-pruner

  Reviews all CLAUDE.md files for focus, trims redundancy, and identifies content that should be moved to specialized reference files

• code-reviewer

  Reviews completed code for quality, reuse, and security

• codebase-pruner

  Reviews a codebase for redundancy, inefficiency, orphaned code, and dead exports, then produces a structured pruning proposal

• compound-skeptic

  Skeptical second-pass reviewer of a compound proposal; emits per-item IMPLEMENT / DONT_IMPLEMENT verdicts with concrete evidence. Read-only except for the proposal file where it inserts verdict blocks.

• compounder

  Analyzes completed sprints and out-of-scope findings, then produces a three-bucket proposal (clean-ups, backlog tasks, CLAUDE.md / CODE-PATTERNS.md improvements) for the user to approve

• executor

  Implements a single task from an execution-ready plan with scope boundaries, deviation rules, and atomic commits

• idea-extractor

  Extracts and structures raw ideas, feature requests, and bug reports into actionable task specs

• integration-tester

  Runs end-of-sprint integration and E2E tests, classifies failures as regressions or pre-existing

• roadmap-generator

  Synthesizes a roadmap brief and research into a phased set of epics with dependencies, milestones, and success signals

• sprint-closer

  Gathers sprint close context and executes sprint close (mark complete, archive, commit, merge run branch) for the executor orchestrator

• sprint-code-reviewer

  End-of-sprint aggregate code reviewer; surfaces cross-task quality and security findings as queued findings for the compounder

• sprint-initiator

  Gathers sprint context and executes sprint setup (branch, sprint.json, smoke tests) for the executor orchestrator

• task-decomposer

  Decomposes an approved idea into a coarse task skeleton (DAG, epic decisions, file-ownership hints) for downstream parallel detailers

• task-refiner

  Refines approved ideas into execution-ready plans with acceptance criteria, file ownership, and dependency mapping

• test-writer

  Writes or updates unit and component tests for a single completed task's changes

Hooks (6)

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.js"

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/post-tool-use.js"

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/context-monitor.js"

• TaskCompleted

  node "${CLAUDE_PLUGIN_ROOT}/hooks/task-completed.js"

• PreCompact

  node "${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact.js"

• SubagentStop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-stop.js"

Similar plugins