By indrasvat
15 Claude Code skills: CI gating, exec plans, PR shipping, code cleanup, PR triage, K8s diffing, migration safety, API compat, rollout health, CRD impact analysis, PRD generation, iTerm2 automation, Cloudflare deployment, CodeRabbit reviews, and browsing-as-you (shared authenticated Chrome over CDP)
Start True Ralph Loop to implement PRD with fresh Claude sessions
Recover context and resume PRD implementation after crash or new session
Show current PRD implementation status and progress
Generate a comprehensive PRD with interactive discovery questions
Detect breaking changes in APIs — protobuf, OpenAPI/Swagger, GraphQL schemas, or Go exported interfaces. Use when the user says "API compat", "breaking changes", "check API compatibility", "proto breaking", "schema breaking", "is this breaking", "backward compatible", "API diff", "contract check", or when API definition files have been modified.
Drive ONE persistent, already-authenticated Chrome — the user's real logged-in sessions — over the DevTools Protocol, instead of spawning a fresh unauthenticated browser per task. Use when a task needs the browser SIGNED IN AS THE USER: screenshotting a logged-in page, filling a form, posting a comment, uploading a file, attaching an image to a GitHub PR, or driving an app whose API can't — Gmail, Google Docs/Drive, Cloudflare, X, GitHub, Devin, or any site the user is signed into. Prefer over chrome-devtools-mcp, agent-browser, Playwright, or Puppeteer when they would open a new unauthenticated Chrome, hit a login wall, or cause repeated macOS Allow/keychain prompts. Bundles chrome-agent.sh (start/login/seed/autostart) and cdp.py (tabs, --front, navigate, eval, screenshot, seed logins). Triggers: "use my logged-in browser", "authenticated Chrome", "act as me on <site>", "share my cookies", "no API for this", "chrome-devtools-mcp", "browser-url", "stop the Allow popups".
Deploy web apps, APIs, static sites, and edge functions to Cloudflare's free tier using wrangler and cloudflared CLIs. Use when user wants to (1) host/deploy a website, blog, or web app, (2) create serverless APIs or edge functions, (3) set up databases (SQL or KV), (4) store files/objects, (5) expose localhost via tunnel, (6) deploy any personal project to the cloud for free. Covers Workers, Pages, D1, KV, R2, Durable Objects, Workers AI, Tunnels, Email Routing. All deployments stay within $0 free tier limits.
Run all CI checks locally before pushing — linters, type checks, tests, and vulnerability scans in parallel with a pass/fail summary table. Use when the user says "run CI", "check before push", "run all tests", "lint check", "pre-push checks", "validate before PR", "CI gate", "does it pass CI", "is it clean", "run checks", or wants to verify the project builds and passes before pushing.
Local AI code reviews via CodeRabbit CLI. ONLY use when (1) user explicitly requests "coderabbit"/"cr review", OR (2) code changes are high-risk (security, concurrency, complex logic). Rate-limited to 1 review/hour—be highly selective.
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.
A marketplace of personal Claude Code plugins: 15 skills for AI-assisted dev workflows, plus dootdashaa, a glanceable statusline.
This repository is a Claude Code marketplace exposing two independently-installable plugins:
| Plugin | Install command | What it adds |
|---|---|---|
| indrasvat-skills | /plugin install indrasvat-skills@indrasvat-skills | 15 skills (CI gating, exec plans, PR shipping, K8s diffing, PRD generation, iTerm2 automation, browsing-as-you, …) |
| dootdashaa | /plugin install dootdashaa@indrasvat-skills | Single-line, Nerd-Font-icon statusline. ~9ms p50 render budget. |
Both share one /plugin marketplace add step (see Installation). Each can be installed, updated, and uninstalled on its own.
Glanceable, single-line. One carrier per signal (icon, text, or colour — never two). Zero emoji. Pre-computed git cache keeps the hot path under the 300ms Claude Code debounce. See plugins/dootdashaa/README.md for env-var options and the install / uninstall command list; design report is at plugins/dootdashaa/docs/DESIGN.html.
| Skill | Command | Description |
|---|---|---|
| ci-gate | /ci-gate | Run all CI checks locally before pushing (Go, JS/TS, Rust, Python). --fix to auto-fix. |
| exec-plan | /exec-plan | Create self-contained execution plans any agent can follow end-to-end. |
| ship-pr | /ship-pr | Create PRs with a standards compliance review gate. Blocks on CLAUDE.md violations. |
| deslop | /deslop | Clean AI-generated slop — dead comments, unused code, redundant logic. |
| triage-pr | /triage-pr | Fetch, categorize, and address PR review comments by priority (BLOCKER > QUESTION > SUGGESTION > NITPICK). |
| Skill | Command | Description |
|---|---|---|
| k8s-diff | /k8s-diff | Diff Helm/Kustomize/raw YAML against live cluster, flag risky changes. |
| migration-guard | /migration-guard | Analyze DB migrations for lock risk, backward compat, rollback safety. |
| api-compat | /api-compat | Detect breaking changes in protobuf, OpenAPI, GraphQL, or Go exported APIs. |
| rollout-check | /rollout-check | Verify K8s deployment health — pods, events, HPA, logs. |
| crd-impact | /crd-impact | Find all controllers, webhooks, RBAC, and manifests affected by a CRD change. |
Generate comprehensive Product Requirements Documents with interactive discovery, progress tracking, and True Ralph Loop support for autonomous implementation.
Capabilities:
docs/PRD.md with checkboxes and phased tasksdocs/PROGRESS.md for context recovery across sessionsKey Insight: Unlike Anthropic's Ralph plugin (same-session Stop hook), True Ralph spawns fresh Claude sessions, preventing context pollution.
Slash Commands:
/prd - Generate a new PRD with interactive discovery/prd-status - Check implementation progress/prd-ralph - Start True Ralph Loop (autonomous implementation)/prd-resume - Recover context after crash/new sessionDrive iTerm2 programmatically using Python scripts to automate terminal tasks, run visual tests, or manage sessions. Includes parallel agent support for concurrent testing.
Capabilities:
Platform: macOS only (see cloud limitations)
Deploy web apps, APIs, static sites, and edge functions to Cloudflare's free tier using wrangler and cloudflared CLIs.
npx claudepluginhub indrasvat/claude-code-skills --plugin indrasvat-skillsSkills for the claude autonomous agent system - Generate PRDs and convert them to prd.json format for autonomous execution
GitHub PR dashboard for Claude Code. View PR status, CI/CD progress, bot comments, and merge PRs directly from your terminal.
Autonomous development methodology: PRD interviews → agent execution → automated review
Use this agent when setting up CI/CD pipelines, configuring Docker containers, deploying applications to cloud platforms, setting up Kubernetes clusters, implementing infrastructure as code, or automating deployment workflows. Examples: <example>Context: User is setting up a new project and needs deployment automation. user: "I've built a FastAPI application and need to deploy it to production with proper CI/CD" assistant: "I'll use the deployment-engineer agent to set up a complete deployment pipeline with Docker, GitHub Actions, and production-ready configurations."</example> <example>Context: User mentions containerization or deployment issues. user: "Our deployment process is manual and error-prone. We need to automate it." assistant: "Let me use the deployment-engineer agent to design an automated CI/CD pipeline that eliminates manual steps and ensures reliable deployments."</example>
DevOps automation scripts for CI/CD, health checks, and deployments
'MUST BE USED PROACTIVELY when user mentions: planning, PRD, product requirements document, project plan, roadmap, specification, requirements analysis, feature breakdown, technical spec, project estimation, milestone planning, or task decomposition. Use IMMEDIATELY when user says "create a PRD", "plan this feature", "document requirements", "break down this project", "estimate this work", "create a roadmap", "write specifications", or references planning/documentation needs. Expert Technical Project Manager that creates comprehensive PRDs with user stories, acceptance criteria, technical architecture, task breakdowns, and separate task assignment files for sub-agent delegation.'