dev-flow

Plugin dev-flow from marketplace fzymgc-house-skills in fzymgc-house/fzymgc-house-skills. Commands read from the repo's manifest — 4 days ago.

Skills (26)

• address-findings

  Processes findings from review-pr by working through beads in the review epic. Use when the user asks to "address review findings", "fix review issues", "work through review beads", or "process review findings". - Task - Read - Edit - Write - Grep - Glob - "Bash(test *)" - "Bash(git *)" - "Bash(jj s

• bead-create-smart

  Create a tracked bd issue using structured flags (per Rule 3) rather than an 8-section description heredoc. Use for ad-hoc beads outside the plan-to-beads materialization flow — reviewer findings, bug reports, follow-up beads at session close, or single tasks the user wants tracked. Accepts an optio

• brainstorming

  You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

• capture-adrs

  Use when the user has finalized a spec or plan and wants to extract ADR-worthy decisions into both `docs/adr/<bd-id>-<slug>.md` files AND `bd create -t decision` records. Triggered by `/capture-adrs <path>` or by the nudge-adr-capture hook's reminder. NOT for general ADR audit — use the adr-extracto

• dispatching-parallel-agents

  Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

• drain-with-worker

  Launch an autonomous /drain worker in a detached cmux or tmux surface and arm a surface-aware watchdog (epic-mode drains). Use when the user runs `/drain-with-worker [cmux|tmux] DRAIN_ID` or accepts the `/drain` worker handoff. Takes an optional worker-type (auto-detected when omitted).

• draining-beads

  Use when you have an epic / set / cascade of beads to drain autonomously via Claude Code's /goal. Pairs with the /drain slash command. Requires Claude Code 2.1.148+ with hooks enabled.

• evolve-adr

  Use when you need to update, supersede, deprecate, or migrate an Architecture

• executing-plans

  Use when you have a written implementation plan to execute in a separate session with review checkpoints

• finishing-a-development-branch

  Use when implementation is complete, all tests pass, and you need to decide how to integrate the work (git or jj) - guides completion of development work by presenting structured options for merge, PR, or cleanup. Supports an autonomous (non-interactive) mode for callers like the drain worker that m

• handoff-prompt

  Generate a self-contained briefing prompt that a fresh Claude (or other agent) session uses to pick up a bead's work without inheriting the current session's context. Pulls model hint from the bead's `model:*` label (default sonnet), routes via the bead's `agent:*` label, and defers workspace setup

• plan-to-beads

  Materialize an implementation plan's task table into bd issues, dependency edges, and parent linkages per the design-bead lifecycle (Rule 6). Use after writing-plans + plan-reviewer return READY, after capture-adrs has fired, and before subagent-driven-development or executing-plans. Reads the plan'

• receiving-code-review

  Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

• requesting-code-review

  Use when completing tasks, implementing major features, or before merging to verify work meets requirements (supports git and jj) author: fzymgc-house

• respond-to-comments

  Manages GitHub PR review comments. Use when the user asks to "list PR comments", "check PR feedback", "respond to PR comments", "address reviewer feedback", "fix PR review issues", "work through PR review", or "acknowledge comments". Handles both quick lookups and full review-response workflows. - "

• review-pr

  Comprehensive PR review using specialized agents. Use when the user asks to "review this PR", "check my PR", "review code quality", "run PR review", "analyze this pull request", or invokes /review-pr. Launches targeted review agents for code quality, error handling, test coverage, type design, comme

• solving-a-bead

  Use when asked to solve, fix, address, or work a specific bead/issue by ID — validates the bead is open and unblocked, creates an isolated workspace off latest main, separates the problem from any suggested fix (treating suggested fixes as non-authoritative hypotheses), then drives a root-caused, TD

• subagent-driven-development

  Use when executing implementation plans with independent tasks in the current session

• systematic-debugging

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• test-driven-development

  Use when implementing any feature or bugfix, before writing implementation code

• using-git-worktrees

  Alias for using-worktrees. Use when starting feature work that needs isolation from current workspace.

• using-superpowers

  Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

• using-worktrees

  Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git/jj fallback

• verification-before-completion

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

• writing-plans

  Use when you have a spec or requirements for a multi-step task, before touching code

• writing-skills

  Use when creating new skills, editing existing skills, or verifying skills work before deployment

Slash commands (4)

• /dev-flow:adr

  ADR lifecycle operations. Modes: init, new, propose, update, supersede, addendum, accept, deprecate, render, migrate.

• /dev-flow:drain

  Autonomous bead iteration via /goal. Modes: init, epic, set, cascade, worker, resume.

• /dev-flow:review-design

  Read-only adversarial review of a spec. Emits VERDICT: READY|NOT READY + findings.

• /dev-flow:review-plan

  Read-only adversarial review of a plan. Emits VERDICT: READY|NOT READY + findings.

Subagents (16)

• adr-extractor

  Read-only agent that scans a finalized spec/plan and (optionally) its brainstorming session transcript to identify ADR-worthy decisions. Returns strict JSON. Used by /capture-adrs but reusable for batch retrospective extraction and audit workflows. - Read - Grep - Glob - Bash - mcp__probe__search_co

• api-contract-checker

  Detects breaking changes, backward compatibility issues, and contract violations in PRs, and suggests idiomatic contract-hardening. Used by the review-pr orchestrator for the `api` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__cont

• code-reviewer

  Reviews code for project guideline compliance, bugs, quality issues, and per-language documentation conventions. Used by the review-pr orchestrator for the `code` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-libr

• code-simplifier

  Improves code clarity, consistency, and maintainability while preserving functionality. Used by the review-pr orchestrator for the `simplify` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-library-id - mcp__context

• comment-analyzer

  Analyzes code comments for accuracy, completeness, and long-term maintainability. Used by the review-pr orchestrator for the `comments` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-library-id - mcp__context7__que

• design-reviewer

  Read-only adversarial review of a spec document. Emits READY/NOT READY verdict + grounded findings. Authorized to flag ungrounded specs per Rule 7.

• fix-worker

  Implements code fixes for PR review findings. Used by the address-findings orchestrator. Receives a finding bead ID, reads the finding details, and applies the fix in its isolated worktree.

• plan-reviewer

  Read-only adversarial review of a plan document. Emits READY/NOT READY verdict + grounded findings. Authorized to flag ungrounded plans per Rule 7.

• pr-test-analyzer

  Analyzes test coverage quality and identifies critical testing gaps in PRs across languages, verifying tests actually exercise the code. Used by the review-pr orchestrator for the `tests` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mc

• review-gate

  Validates that code fixes correctly address their review findings. Used by the address-findings orchestrator after fix commits are integrated. Receives finding IDs and a VCS diff, returns PASS/FAIL per finding.

• security-auditor

  Audits PR changes for security vulnerabilities using OWASP methodology. Used by the review-pr orchestrator for the `security` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-library-id - mcp__context7__query-docs -

• silent-failure-hunter

  Audits error handling for silent failures, inadequate handlers, and inappropriate fallbacks. Used by the review-pr orchestrator for the `errors` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-library-id - mcp__cont

• slop-hunter

  Detects AI-authorship tells in code and prose changes. Used by the review-pr orchestrator for the `slop` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-library-id - mcp__context7__query-docs - mcp__deepwiki__read_w

• spec-compliance

  Verifies implementation alignment with design documents, ADRs, and architectural decisions. Used by the review-pr orchestrator for the `spec` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-library-id - mcp__context

• type-design-analyzer

  Analyzes type designs for invariant strength, encapsulation quality, and practical usefulness. Used by the review-pr orchestrator for the `types` aspect. - Read - Grep - Glob - Bash - mcp__probe__search_code - mcp__probe__extract_code - mcp__probe__grep - mcp__context7__resolve-library-id - mcp__con

• verification-runner

  Validates fixes and runs project quality gates after fixes are applied. Used by the address-findings orchestrator. Receives a fix manifest with problem/fix/change context and verifies alignment plus lint/build/tests.

Hooks (4)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" session-start

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" nudge-adr-capture

• WorktreeCreate

  "${CLAUDE_PLUGIN_ROOT}/hooks/worktree-create"

• WorktreeRemove

  "${CLAUDE_PLUGIN_ROOT}/hooks/worktree-remove"

Similar plugins