rohitguta2432
UserAutonomous 6-stage dev pipeline for Claude Code — requirement in, reviewed & tested PR out, with a live mission-control dashboard
Categories
Indexed Skills (42)
autodev-specs
Produce a complete GitHub Spec Kit document set for a requirement under specs/NNN-slug/ — spec.md, plan.md, research.md, data-model.md, quickstart.md, contracts/, tasks.md and checklists/. Use when asked to write a spec, spec out a feature, create a Spec-Kit / spec-driven document set, and as autodev's stage-1 Spec skill.
autodev
Launch, monitor, resume, or stop a fully autonomous autodev pipeline run (spec → analyze → implement → push → review → test in an isolated git worktree, live on the Mission Control dashboard). Use when the user says "/autodev", "autodev run <requirement>", "start a pipeline for X", "autodev status", "resume run N", or "stop run N".
watch
Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
myfinancial-blog-post
Research a trending Indian personal-finance topic, draft an SEO-optimised blog in the MyFinancial house format with cover image, and publish via the admin API. Use on "write/publish a blog", "myfinancial blog", "find viral finance topic", /myfinancial-blog, a topic or competitor URL, or "beat <competitor>'s post" (ClearTax, Groww, ET Wealth, etc.).
scroll-world
Build an immersive scroll-scrubbed "fly through the world" landing page for any industry or brand using Higgsfield — one continuous camera flight through connected scenes, wired to a portable scroll-scrub engine. Use when the user wants a "3D world" hero, a scroll cinematic, a diorama landing, or to turn a business into a scrollable world.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
loop-me
Grill me about specs for the workflows I want to build, within this workspace.
setup-matt-pocock-skills
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
teach
Teach the user a new skill or concept, within this workspace.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
recall
Search agentmemory for past observations, sessions, and learnings about a topic. Use when the user says "recall", "remember", "what did we do", or needs context from past sessions.
recap
Summarize the last N agent sessions for the current project, grouped by date. Use when the user asks "recap", "what have we been doing", "this week", "today", or wants a rollup of recent work.
competitor-analysis
Analyze one competitor's organic footprint, ranking keywords, content themes, backlinks, and gaps.
grammar-corrector
Correct grammar, punctuation, spelling, and clarity in user text while preserving voice, tone, and meaning. Use on "fix grammar", "proofread this", "polish this text", "clean this up", "check spelling", or whenever the user pastes writing (post, email, essay, caption) and wants a language-level pass. Lean toward triggering.
humanizer
Rewrite text so it reads like a real person wrote it, stripping the telltale patterns of AI-generated writing (puffery, weasel wording, "not just X but Y", rule-of-three, em-dash overuse, AI vocabulary) based on Wikipedia's "Signs of AI writing" field guide. Use when the user says "humanize", "make this sound human", "de-AI this", "this sounds like AI", "make it natural", or runs /humanizer with or before a block of text.
keyword-research
Discover keyword opportunities, evaluate metrics and SERPs, and save/tag promising terms.
linkedin-post
Draft a LinkedIn post in Rohit's storytelling voice (bold-unicode hook, personal scene, em-dash bullets, mission close), especially for announcing his AI agents/products. Also accepts a YouTube/Shorts URL and turns it into an explorer-mode post without ever mentioning the video. Logs every post to Documents/wiki/linkedin/. Use on "linkedin post", "write a post for <product>", "turn this Short into a post", or /linkedin-post.
x-post-daily
Draft Rohit's daily X (Twitter) post — always AI + his own work, grounded in what's live on rohitraj.tech that day. Saves a copy-paste-ready post, logs every post to the wiki vault at Documents/wiki/x/, and runs a daily self-eval + learnings loop so posts improve over time. Use when the user says "x post", "tweet", "daily x", "post on x/twitter", runs /x-post-daily, or via the daily-x-post scheduled routine.
agentgrade
Audit any AI agent codebase for production readiness. Grades the repo against five pillars — evaluation, observability, data foundation, orchestration, governance — plus an incident playbook check, then reports the gaps ranked by risk with the exact artifact to build next. Use when the user says "audit my agent", "agentgrade", "is this agent production ready", "production readiness check", "agent gap analysis", or is about to deploy/launch an AI agent to real users.
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
fable-mode
Emulate Claude Fable 5's reasoning depth and tool-use efficiency on smaller models (Opus 4.8, Sonnet). Enforces hypothesis-first debugging, assumption verification, parallel tool calls, read-before-edit, minimal diffs, and evidence-based completion. Use when starting any non-trivial coding, debugging, refactoring, architecture, or multi-step task — especially when the session model is Opus or Sonnet and the user wants maximum reasoning quality per token.
git-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
migrate-to-shoehorn
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
specs-skills
Use when asked to spec out a feature, write a spec, create spec.md / plan.md / tasks.md, do spec-driven development, use GitHub Spec Kit or speckit, or set up .specify/ in a repo. Works in repos that have never been initialized with spec-kit. Triggers on "spec this out", "specify", "SDD", "write the spec and plan", "generate tasks from the spec".
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
claude-to-obsidian
Archive every Claude Code conversation into the Obsidian vault at ~/Documents/wiki as tagged, wikilinked markdown notes (chats/code/). Use when the user wants to track, export, sync, back up, or archive their Claude Code conversations/chats to Obsidian, set up automatic conversation tracking, or asks to "sync claude to obsidian", "save my chats", or catch up on un-exported sessions.
hermes-start
Boot full Hermes Agent local stack on macOS — Ollama service, hermes3:8b model warmup, Hermes Desktop GUI, optional gateway. Use when user says /hermes-start, "hermes-start", "harmes-start" (common typo), "start hermes", "spin up hermes", "launch hermes desktop", "run hermes agent locally", or "boot hermes stack".
usage-dashboard
Show token usage and estimated cost across local Claude Code instances. Use when the user asks to see their Claude Code usage, token usage, cost, spend, or a usage dashboard — especially across multiple accounts/config dirs (~/.claude and ~/.claude-myfinancial).
whatsapp-ai-chatbot-aws
Design a production architecture for an AI chatbot on WhatsApp running on AWS (End User Messaging Social or Meta Cloud API, SNS/SQS, Lambda, Bedrock, DynamoDB, Knowledge Bases). Produces an architecture doc with diagrams, component table, KB vs tool split, cost estimate, and a production checklist. Use when the user says "WhatsApp bot on AWS", "WhatsApp chatbot architecture", "Bedrock WhatsApp", "design my WhatsApp AI agent", "WhatsApp + Lambda", or asks how to connect an LLM to WhatsApp on AWS.
autodev
Launch, monitor, resume, or stop a fully autonomous autodev pipeline run (spec → analyze → implement → push → review → test in an isolated git worktree, live on the Mission Control dashboard). Use when the user says "/autodev", "autodev run <requirement>", "start a pipeline for X", "autodev status", "resume run N", or "stop run N".
implement
Implement a piece of work based on a spec or set of tickets.
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
obsidian-vault
Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.