Execute PRD-driven engineering sprints in isolated git worktrees: auto-generate specs, delegate implementation/testing to agents, run CI/CD to staging/prod with audits and fixes, enforce safety hooks, capture learnings into docs, and audit workflows for self-improvement.
Read-only code review agent. Use after sprint execution to verify quality, catch issues the executor might have missed, and check adherence to project patterns. Cannot modify files.
Task orchestration and sprint lifecycle management. Use when the user has a PRD with multiple sprints, when sprint coordination is needed, or when the user says "orchestrate", "run the sprints", "execute the PRD". Manages sprint delegation, coherence checks, and completion verification.
Executes a single sprint from a sprint spec file. Use when a sprint needs to be implemented in isolation. Receives sprint spec content from orchestrator or direct user invocation.
Adopt a PRD owned by another (typically dead) session — list adoptable plans in this repo, pick one, force-release any stuck sprint claims, and write a fresh active-plan pointer for THIS session. Auto-invoke when the user says "adopt plan", "take over plan", "resume someone else's plan", "my pointer is gone", or runs /adopt-plan. Do NOT auto-invoke on every fresh terminal — /plan-build-test Phase 0 already self-adopts when this session is the legitimate owner.
End-to-end hands-off run from PRD to staging. Chains /plan-build-test then /ship-test-ensure with CLAUDE_PIPELINE_MODE=staging-only,aggressive-fix-loop. Halts before production with exit 99 — the canonical success state for staging-only delivery. User verifies staging, then runs /ship-test-ensure manually for prod. Use for "ship the PRD to staging unattended", "fire and forget", or "autonomous staging".
Post-task learning capture and knowledge promotion. Auto-invoke when a task or sprint is completed, when the user says "done", "finished", "wrap up", or when all acceptance criteria are checked off. Do NOT invoke when user says "ship it" — that triggers /ship-test-ensure instead.
Creates a new project from scratch with a production-grade PRD. Use this skill whenever the user wants to start a new project, build a new product, create a new application, or says things like "new project", "start a project", "build me an app", "create a new API", "I have an idea for", "let's build something new". This is for greenfield projects — not for adding features to existing ones (use /plan for that). Runs a structured discovery interview, applies battle-tested architecture defaults, generates a full PRD with adversarial analysis, and outputs sprint-ready specs compatible with /plan-build-test.s
Local-only feature builder that plans, implements, and tests code using agent teams — all locally, no deploy. Use this skill when the user describes a problem, feature request, bug, or improvement to build. Triggers on phrases like "build this", "implement", "create feature", "fix this problem", "add functionality", or when user provides a feature description to execute. Also triggers when user wants to work through pending task files. After local testing completes, user manually verifies, then uses /ship-test-ensure to deploy.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
A Compound-Engineering workflow for Claude Code, packaged as a plugin that installs into your existing ~/.claude/ without overwriting anything.
/vini-workflow:<name>): /plan, /plan-build-test, /research, /ship-test-ensure, /compound, /workflow-audit, /skill-evolve, /create-project, /verify-staging, /autonomous-staging, /adopt-plan, /update-docs, /playwright-stealth.orchestrator (PRD lifecycle), sprint-executor (worktree-isolated sprints), code-reviewer (post-sprint review)./plugin available — claude --version)jq (apt-get install jq / brew install jq)Inside Claude Code:
/plugin marketplace add vinicius91carvalho/.claude
/plugin install vini-workflow@claude-engineering
/reload-plugins
This installs the plugin's skills, agents, commands, and hooks. Your ~/.claude/CLAUDE.md, settings.json, and any other personal customizations are untouched.
The Claude Code plugin system can ship skills/agents/hooks but cannot ship: a custom statusline, env vars (autocompact percent, etc.), or auto-loaded CLAUDE.md content. The bootstrap script adds those pieces additively, with a timestamped backup.
# Preview what will change (no writes):
bash ~/.claude/plugins/cache/claude-engineering/vini-workflow/*/scripts/bootstrap.sh --dry-run
# Apply (default mode):
bash ~/.claude/plugins/cache/claude-engineering/vini-workflow/*/scripts/bootstrap.sh
The bootstrap:
@import line to your ~/.claude/CLAUDE.md so the workflow's constitution loads (creates the file if absent — never edits prior content).settings.json (your existing keys win).<file>.backup-YYYYMMDD-HHMMSS.Skip individual steps with --no-statusline, --no-env, --no-claudemd. Install the 9 companion plugins from the official marketplace (commit-commands, skill-creator, etc.) with --with-companions.
/exit and reopen, or run /reload-plugins.
/help # confirm skills appear under /vini-workflow:*
/vini-workflow:plan # try the plan skill
Edit any file in a project — post-edit-quality.sh should run silently and write to ~/.claude/state/. Statusline should render the HUD.
/plugin uninstall vini-workflow@claude-engineering
bash ~/.claude/plugins/cache/claude-engineering/vini-workflow/*/scripts/bootstrap.sh --revert
--revert restores the last bootstrap backup of settings.json and CLAUDE.md, and removes any file that the bootstrap created from scratch.
If you previously installed by cloning this repo into ~/.claude/, run:
bash plugins/vini-workflow/scripts/migrate-from-monolith.sh --dry-run
bash plugins/vini-workflow/scripts/migrate-from-monolith.sh
Detailed steps and the manual fallback are in MIGRATION.md.
PLAN → WORK → REVIEW → COMPOUND → (next task is now easier)
Plan + Review = 80% of effort. Work + Compound = 20%. The bottleneck is knowing what to build and verifying it was built — not typing speed.
The autonomous pipeline:
flowchart LR
A["/vini-workflow:plan"] --> B[User approves PRD]
B --> C["/vini-workflow:plan-build-test"]
C --> D[User tests]
D --> E["/vini-workflow:ship-test-ensure"]
E --> F[🔒 Confirm prod]
F --> G[Production + Lighthouse]
Safety gates that autonomous mode never skips: production deploy, rollback, escalation on ambiguity / scope > 2x, anti-premature-completion verification.
npx claudepluginhub vinicius91carvalho/.claude --plugin vini-workflowCorca Workflow Framework — consolidated hooks and skill orchestration for structured development sessions
Implementation planning, execution, and PR creation workflows with multi-agent collaboration
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Software engineering workflows with skills for planning, implementation, quality review, and structured thinking, plus a suite of specialist agents
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
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