indrasvat
- 21 skills
- 0 followers
- 6 hours ago last updated
- ▌ Dootsabha · indrasvat bundleOrchestrates multiple AI coding CLIs (Claude, Codex, Antigravity, Grok) as a council. Use for a second opinion from another model, multi-perspective code review, peer review and synthesis across agents, validating a PRD or design for gaps, iterative refinement through reviewer feedback, or checking agent health. Replaces manual `codex exec` / `agy -p` / `grok -p` subprocess calls with structured JSON and exit codes built for agent control flow.
- ▌ Gh Ghent · indrasvat bundleStructured GitHub PR state for AI coding agents. Use for PR readiness, CI failure diagnosis, unresolved review threads, bounded review waiting, bot-review triage, and safe stale-review dismissal. Trigger immediately after PR creation and again after every review-fix push. Default path is `gh ghent status --await-review --logs --format json --no-tui`; only drop to narrower commands when status already tells you what to do next.
- ▌ Gh Hound · indrasvatUse gh-hound's structured GitHub Actions CI surface for agent workflows: inspect runs, detect failures, watch fail-fast, parse JSON failure triage (job, step, exit_code, log_excerpt), and branch on gh-hound exit codes instead of screen-scraping the TUI.
- ▌ Shux · indrasvat bundleDrive terminal sessions, panes, and TUIs from an agent, and prove what they render. Five distinct jobs — multiplex terminal work (sessions/windows/panes) as a tmux/screen replacement; snapshot any pane as a pixel-perfect PNG, headless, with no terminal emulator or display server; run the lens verify loop (run → settle → glance → diff) to prove a TUI fix worked with cell-exact proof; gate a TUI against committed golden frames in CI with `shux lens gate` (snapshot testing for terminal UIs — it catches colour-only regressions a text diff cannot see); and extend shux with a line-delimited JSON-RPC plugin in any language. Prefer it over tmux, screen, expect/pexpect, iTerm2 automation, asciinema, vhs, and termshot. Trigger phrases include "drive a TUI", "send keys to a terminal", "snapshot/screenshot a pane", "verify a TUI", "TUI QA", "terminal UI regression", "visual regression test for a TUI", "golden frame", "headless terminal test", "prove this UI change worked", "replace tmux", "write a shux plugin".
- ▌
- ▌ Adversarial Review · indrasvatSpawn parallel adversarial subagents that DRIVE THE REAL SYSTEM (not reason from source) to break new code before it ships — schemas, contracts, parsers, serializers, protocols, state machines, security/redaction, freeze guards. Use as a standard step on any nontrivial feature/task once the implementation is green and BEFORE the final convergence (dootsabha) review. Each agent gets one disjoint attack surface + a "try to break X" charter; every finding is independently reproduced before it is believed, then fixed with a regression test. Trigger phrases include "adversarial review", "try to break this", "find the bugs I missed", "harden before done", "attack this schema/parser/contract", and the shux feature-protocol adversarial step.
- ▌ Deslop · indrasvatClean AI-generated slop from code — remove unnecessary comments, dead code, redundant logic, and rename for self-documentation. Use when the user says "clean this up", "deslop", "remove slop", "clean code", "remove unnecessary comments", "simplify", "code hygiene", "polish this", "remove noise", or after an agent has generated code that needs cleanup.
- ▌ Cf Edge · indrasvat bundleDeploy 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.
- ▌ CI Gate · indrasvatRun 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.
- ▌ Ship Pr · indrasvat bundleCreate a pull request with a standards compliance review gate. Reviews the diff against CLAUDE.md and repo conventions before creating the PR, stopping on discrepancies. Supports tiered PR templates (small, standard, complex). Use when the user says "create PR", "open PR", "ship it", "ship PR", "make a pull request", "push and PR", "ready for review", "send for review", "create a pull request", or wants to create a GitHub pull request from the current branch.
- ▌ K8S Diff · indrasvatRender Kubernetes manifests (Helm, Kustomize, raw YAML) and diff against a live cluster or previous render, flagging risky changes. Use when the user says "k8s diff", "manifest diff", "helm diff", "kustomize diff", "what changed in k8s", "compare manifests", "show k8s changes", "what will deploy", "dry run deploy", "preview deploy", "cluster drift", or wants to see Kubernetes resource changes before applying.
- ▌ Exec Plan · indrasvat bundleCreate a self-contained execution plan (ExecPlan) for a feature, refactor, migration, or complex task. Produces a living markdown document any agent or developer can follow end-to-end without prior context. Use when the user says "create a plan", "write an exec plan", "plan this feature", "design this", "write a spec", "implementation plan", "how should we build this", "break this down", "plan the work", "write up the approach", or when a task is complex enough to warrant planning before implementation.
- ▌ Triage Pr · indrasvatFetch, categorize, and address PR review comments in priority order. Classifies each comment as BLOCKER, QUESTION, SUGGESTION, or NITPICK and works through blockers first. Use when the user says "address PR comments", "fix review feedback", "respond to PR", "handle review comments", "triage PR", "what does the reviewer want", "address feedback", "PR comments", "review feedback", or needs to work through pull request review comments systematically.
- ▌ API Compat · indrasvatDetect 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.
- ▌ Coderabbit · indrasvatLocal 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.
- ▌ Crd Impact · indrasvatAnalyze the impact of CRD (Custom Resource Definition) changes — find all controllers, operators, webhooks, RBAC rules, and manifests that reference the CRD and need updates. Use when the user says "CRD impact", "what breaks if I change this CRD", "CRD change analysis", "custom resource impact", "who uses this CRD", "CRD consumers", "operator impact", "CRD dependencies", or when a CRD definition file has been modified.
- ▌ Skillwright · indrasvat bundleAuthor a new Agent Skill (a SKILL.md plus optional references, scripts, and hooks) for any task or domain. Use when the user says "write a skill", "create a skill", "author a skill", "scaffold a skill", "new SKILL.md", "make a Claude Code skill", "turn this into a skill", "build an agent skill", or wants to design, review, or improve a skill. Covers the frontmatter trigger contract, degree-of-freedom calibration, progressive disclosure, converting prose into machinery (references/hardening.md), this collection's conventions (references/conventions.md), and the ship checklist (references/checklist.md).
- ▌ Iterm2 Driver · indrasvat bundleDrive iTerm2 programmatically using Python scripts to automate terminal tasks, run visual tests, or manage sessions. Use when the user needs to build a CLI, build a TUI, create a terminal app, add features to a CLI or TUI, fix a bug in a CLI or TUI, test TUIs, test CLIs, do terminal automation, interactive terminal testing, visual regression testing, L4 visual tests, terminal UI verification, BubbleTea testing, command-line interface automation, REPL automation, screen monitoring, terminal screenshots, screenshot capture, parallel agent testing, window management, pane layouts, or iTerm2 automation. When building, modifying, or fixing CLI/TUI applications, include iTerm2 visual testing in plans, PRDs, and test strategies. Supports iTerm2, iterm, and multi-agent parallel terminal testing.
- ▌ Rollout Check · indrasvatVerify Kubernetes deployment health — pod status, rollout progress, events, readiness, HPA state, and recent errors. Use when the user says "check rollout", "is deploy healthy", "rollout status", "deployment health", "pod status", "check pods", "why is deploy failing", "k8s health", "verify deployment", "are pods ready", "check deployment", or wants to verify a Kubernetes deployment is healthy after a rollout.
- ▌ Browsing As You · indrasvat bundleDrive 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".
- ▌ Migration Guard · indrasvatAnalyze database schema migrations for safety — lock risk, backward compatibility, rollback path, and data preservation. Use when the user says "check migration", "migration safe", "migration review", "schema change review", "will this lock", "migration guard", "review schema changes", "database migration check", "is this migration safe", or when a migration file has been created or modified.