By vpaivag
Skills for planning, executing, tracking, and reviewing software work — plus a CLAUDE.md refactor utility.
Produce a thorough, self-contained implementation plan for a coding task. Explores the codebase read-only, considers alternatives, enumerates risks, and writes a plan suite (an index plus one or more chunk files) that can be executed in a fresh Claude Code session via /execute-plan. Detects under-decomposed tasks to offer splits. Use this when the user invokes /deep-plan or asks for a deep plan before implementation.
Execute a chunk file produced by /deep-plan. Reads the specified chunk, validates suite dependencies via the suite index, confirms files and order with the user, implements in sequence, verifies each acceptance criterion, and prompts for the final status update. Use when the user invokes /execute-plan <path>.
Front-door planning skill that gathers context before a coding task is planned. Requires the user to state their intent first; if /intake is invoked with no task, it asks for one and stops. Order is: restate → ask the 3 core questions (intent, scope, anchor) → explore the codebase bounded by those answers to resolve anything code can settle → continue asking only the follow-ups code couldn't answer (hard cap of 10 follow-ups in Phase 3 on top of the 3 core questions, asked one at a time via AskUserQuestion, recommended-answer option first). Recommends either /simple-plan or /deep-plan via an ADR-gate (hard-to-reverse / surprising-without-context / real-tradeoff / cross-concern — task spans multiple distinct kinds of change). File count is deliberately NOT a criterion: uniform bulk work (e.g. a 30-file rename) belongs in /simple-plan. Writes a single `context.md` artifact into a new suite directory under the configured plans directory (default `.claude/plans/`) and prints a handoff command for the user to run in a new session. Use when the user invokes /intake, asks to "gather context before planning", or wants a checkpoint before /deep-plan or /simple-plan.
Guided onboarding for newcomers to a codebase. Three phases — gate on CLAUDE.md quality, run a conversational tour driven by CLAUDE.md and the docs it points at, then write one contrived hands-on task to `.claude/onboarding-task.md` for the newcomer to implement themselves on a sandbox branch. Read-only on the codebase during the tour; writes exactly one artifact. Aborts with a pointer to `/claude-md-refactor` (bootstrap mode) if CLAUDE.md is missing, and warns + offers an override if it looks thin. Use when the user invokes /onboarding, says "I'm new to this codebase", "help me onboard", "give me a tour of this repo", "show me around", or otherwise asks to be ramped up on an unfamiliar project.
Read-only status view for plan suites in the current project. Detects the active suite (one with chunks not yet done) and shows status, dependencies, and what's runnable next. Use when the user invokes /plan-tracker or asks "what's the state of the plan" / "what's next in the plan" / "what's left".
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.
Personal collection of agent skills covering planning, repo setup, and onboarding workflows.
Each skill is a self-contained SKILL.md under skills/<name>/ that loads on demand when its trigger fires. The planning skills compose into one loop:
flowchart TD
intake[/intake/]
simple[/simple-plan/]
deep[/deep-plan/]
execute[/execute-plan/]
review[/review-plan/]
tracker(plan-tracker)
intake -->|straightforward| simple
intake -->|ADR-gate fires| deep
deep --> execute
execute --> review
deep -.reads-output.-> tracker
tracker -.tracks-changes.-> execute
classDef helper fill:#f5f5f5,stroke:#999,stroke-dasharray:4 3,color:#555
class tracker helper
Diagram shows the planning loop; see the clusters below for setup and onboarding skills.
/intake is the recommended front door — it gathers context and points you at the right planner. You can still invoke /deep-plan or /simple-plan directly if you already know which one fits.
Pick the path that matches your setup:
Manually add the skills to any agent using the skills CLI.
Install all skills:
npx skills@latest add vpaivag/skills
Install a specific skill:
npx skills@latest add vpaivag/skills --skill deep-plan
Target a specific agent (e.g. Claude Code):
npx skills@latest add vpaivag/skills -a claude-code
This repo is a Claude Code plugin marketplace. Run each command on its own line at the Claude Code prompt:
/plugin marketplace add vpaivag/skills
/plugin install skills@vpaivag
/reload-plugins
The first command registers the marketplace (named vpaivag) by fetching .claude-plugin/marketplace.json from this repo. The second installs the skills plugin from it. The third activates the plugin in your current session — without a restart.
Verify it's registered:
/plugin marketplace list
If /plugin install skills@vpaivag returns Marketplace "vpaivag" not found, the marketplace add step didn't complete — re-run it and check the output.
Update later:
/plugin marketplace update vpaivag
Or use a local clone instead of GitHub:
/plugin marketplace add /absolute/path/to/skills
Trigger: /intake or asking to "start a new task", "scope this out", or wanting help deciding whether a task needs a deep plan.
Short, focused Q&A front door for any new task. Asks up to a handful of clarifying questions, writes a context.md capturing the task and the resolved assumptions, then recommends either /simple-plan or /deep-plan based on an ADR-gate (hard-to-reverse, surprising-without-context, real-tradeoff, or cross-concern — task spans multiple distinct kinds of change). File count is deliberately not a criterion: a 30-file uniform rename stays in /simple-plan. The downstream planner adopts the same suite directory, so no context is lost between intake and planning.
Highlights:
/deep-plan only when it's actually warranted, otherwise routes to /simple-plan.context.md into a suite dir the planner picks up automatically.Trigger: /simple-plan or asking for a lightweight plan for a straightforward task.
Lightweight planner for mechanical or bounded tasks where /deep-plan's full Restate → Explore → Design → Specify → Risk → Verify treatment is overkill. Produces a single simple-plan.md in a suite directory and, if you approve, implements it in the same session — no /execute-plan handoff, no chunk decomposition, no index.md (so /plan-tracker and /execute-plan ignore it by design).
Use this when the work is mechanical (rename a field across a codebase), a small bug fix, a one-file addition, or otherwise lacks real design choices. If a task turns out to be deeper than expected, switch to /deep-plan.
npx claudepluginhub vpaivag/skills --plugin skillsMulti-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Editorial "Web Designer" bundle for Claude Code from Antigravity Awesome Skills.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions