YogirajA
- 50 skills
- 0 followers
- 4 hours ago last updated
- ▌ Wiki · yogirajaAlias for write-wiki. Kept for backward compatibility: /wiki triggers the same behavior as /write-wiki. Use write-wiki for adding, ingesting, or updating knowledge. Use read-wiki for querying and getting context before doing work.
- ▌ Accio · yogiraja bundleSummon the right skill. A router over this whole collection plus the enabled plugins: say what you are working on, get told what to type.
- ▌
- ▌ Watch · yogirajaWatch and analyze any YouTube video by fetching its transcript, then summarizing it, extracting key takeaways, pulling quotes, building timestamped chapter notes, listing action items, or answering a specific question about it. Use this whenever the user shares a YouTube link (youtube.com or youtu.be) and wants to know what's in it, says "watch this", "summarize this video", "give me the key points / notes / takeaways from this talk", "what does this video say about X", "tldr this YouTube video", or wants to skip watching something and get the content fast. Trigger even when the user just pastes a YouTube URL with a brief instruction, and even if they never say the word "watch".
- ▌ Smells · yogirajaReview code for the twelve Fowler code smells (Mysterious Name, Duplicated Code, Feature Envy, Data Clumps, Primitive Obsession, Repeated Switches, Shotgun Surgery, Divergent Change, Speculative Generality, Message Chains, Middle Man, Refused Bequest) and name each one Fowler-style with a concrete fix. Defaults to reviewing the current git diff; accepts an optional file or path argument to review specific files instead. Use whenever the user asks to "check for code smells", "smell check", "any smells here", "review for refactoring", "what should I refactor", "is this well structured", or runs /smells, and as a refactoring lens after /code-review. This is about design and structure quality (naming, duplication, coupling, over-abstraction), NOT correctness bugs; use /code-review for bugs.
- ▌ Archify · yogiraja bundleCreate polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid.
- ▌ Caveman · yogiraja bundleUltra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
- ▌ QA Deck · yogiraja bundleQA pass on a PowerPoint deck. Renders every slide and checks it for visual defects and fabricated facts. Use when the user asks to QA or check over a .pptx, and proactively before a deck is delivered or after its slides are edited.
- ▌ Primitive Classifier · yogiraja bundleAudit a folder for Claude Code primitives (skills, MCP servers, subagents, hooks, settings.json, CLAUDE.md) and classify each item into the primitive that actually fits, cross-checked against Anthropic docs. Produces a self-contained interactive HTML report with KPI hero, today vs target layout tabs, an explicit migration list, the 7-question decision framework, and provenance badges flagging documented vs inferred vs org-specific claims. Use when the user says "audit primitives", "classify skills and MCP", "primitive audit", "where does this content belong", "is this stuff in the right place", "review my Claude setup", or after generating any deck or doc that asserts which primitive a piece of context belongs in.
- ▌ Writing Great Skills · yogiraja bundleReference for writing and editing skills well, the vocabulary and principles that make a skill predictable.
- ▌ Anthropic Doc Validator · yogiraja bundleValidate claims, documentation, code examples, or generated content about Claude Code, the Anthropic API, or Anthropic SDKs against the latest official documentation. Use when the user asks to "validate against docs", "check against anthropic docs", "verify this is current", "is this still accurate", "audit content against documentation", or similar. Also use proactively after generating slides, READMEs, blog posts, training materials, or runbooks that make specific factual claims about Anthropic products, so that those claims do not drift from the source of truth.
- ▌ Sdd Workshop Walkthrough · yogiraja bundleGenerate a self-contained, animated, single-file HTML workshop walkthrough in the Athena SDD house style (the specworkshop.html / repo.html players): a step-by-step player with a workflow diagram, progress meter, narrated action band, expected-outcome boxes, a terminal/file/tree/scene artifact panel, toggleable trainer notes, autoplay, and keyboard nav. Use this WHENEVER the user wants an animated or interactive HTML walkthrough, workshop page, hands-on lab page, guided demo, or "click-through" explainer for a tool, script, repo, or CLI workflow, and ESPECIALLY when they reference an existing page like specworkshop.html or repo.html, say "like that other workshop", "same style", "animated HTML for this workshop", "make a repo.html / foo.html for X", or ask to turn a set of workshop steps into a playable page. Trigger even if they do not say the word "skill". Do NOT use for PowerPoint/Google Slides decks (use a pptx skill), for general web apps or dashboards, or for static prose docs.
- ▌ Setup Matt Pocock Skills · yogiraja bundleConfigure 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.
- ▌ Explain Yogi Like He Is 5 · yogirajaRun a deep Socratic learning session to make sure the user truly understands a piece of code, a PR, a system design, a concept, or a decision. Use this whenever the user says "explain this to me", "walk me through", "teach me", "help me understand", "I want to learn X", "break this down", "quiz me on", or shares a file or link and wants to be taught rather than just told. Also trigger when the user wants to understand a past decision, trace through logic, or prepare to explain something to someone else. Do not just summarize, run the full incremental mastery loop.
- ▌ Ponytail Audit · yogirajaWhole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.
- ▌ Spec Interview · yogirajaUse when the user wants to be interviewed into a written spec instead of prompting back and forth: when they already know roughly what they want built and need it pinned down fast, when they are iterating prompt-by-prompt and want to stop, or when they say "interview me", "spec me", "ask me questions first", or "help me write the spec". Ends in a spec they approve before any building. For a fuzzy idea that still needs 2-3 approaches explored first, use superpowers:brainstorming instead.
- ▌ Caveman Explore · yogiraja bundleRead-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
- ▌ Codebase Design · yogiraja bundleShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
- ▌ Ponytail Review · yogirajaCode review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.
- ▌ The LLM Council · yogirajaConvene a council of 5 advisors to attack a real decision from different angles, peer-review each other anonymously, and deliver a Chairman's verdict with a concrete next step. Use this whenever the user is wrestling with a decision and asks for the LLM Council, "convene the council," "run this by the council," "what would smart people say about X," "should I X or Y," "what's the right call on...," wants multiple sharp perspectives, or wants to stress-test a choice before acting. Trigger on decision questions even when the user does not say "council" by name, as long as a real choice with stakes is on the table.
- ▌ Caveman Compress · yogiraja bundleCompress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
- ▌ Prompt Optimizer · yogiraja bundleTransform a raw or messy ask into an XML-structured Claude prompt (role / context / task / examples / output format / constraints), tuned to the target Claude model's documented behaviour, validate it with the user, then execute it to produce the actual deliverable. The XML output is built to be used as-is and run for you, not hand-edited. Use when the user explicitly invokes /prompt-optimizer, says "optimize this prompt", "wrap this in XML tags", "rewrite this as a Claude prompt", or "structure this and run it", or pastes a long, ambiguous, multi-requirement, multi-step ask that clearly benefits from structured framing before execution. Do NOT use when the user just wants a cleaned-up, plain-English prompt handed back to read, paste, and tweak themselves, that is the prompt-fixer skill (English hygiene, no XML, no execution). Also skip simple one-liners, greetings, trivial code edits, direct file reads, or clear conversational follow-ups.
- ▌ Loop Design Check · yogirajaDesign a goal-oriented agent loop, or review one for the ways loops go wrong: spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion. WRITE mode gates whether to build the loop at all, then defines a machine-decidable goal, loop type, and skeleton. REVIEW mode runs an existing loop past five failure modes plus judge independence and the keep-judgment-with-the-human red lines. Use when designing an autonomous agent loop, or when you have one and worry it will spin, cheat, or finish a wrong answer.
- ▌ Scope Creep Check · yogirajaA self-awareness brake for Yogi. Invoke this PROACTIVELY (without being asked) the moment a request looks like a tangent from the current goal or an expansion of scope beyond what the task needs. Trigger signals include: "oh also let's...", "while we're at it", "should we also build/add/automate/ productionize/deploy/agentify...", "what if it could also...", "wouldn't it be cool if...", pivoting to a shiny new idea before the current work is finished, a small task about to balloon into a big build, gold-plating, premature optimization, or Yogi himself wondering aloud if he is getting carried away. Also self-apply it before YOU (Claude) propose expanding scope on Yogi's behalf. The job is not to refuse: it is to briefly name the drift, show the cost, and ask Yogi to proceed, park it, or drop it, then respect his answer completely. Do NOT use it for in-scope refinements, genuine bug fixes needed to finish the task, clarifications, or a decisive, deliberate change of priorities.
- ▌ Field Guide Builder · yogiraja bundleUse when building or extending a single-file, source-grounded, visually distinctive teaching guide on a technical topic, the kind with a concept hierarchy of worked examples and do/avoid practice, inline citations to primary sources, an editorial design system, an in-app router, and an optional interactive companion. Triggers on requests like "build a guide", "make a teaching guide / explainer / field guide / learning doc", or polishing and extending one.
- ▌ Conference Talk Deck · yogiraja bundleUse when the user wants to create a new conference talk / presentation deck (a slide deck), or asks to "make a deck", "start a talk deck", "scaffold slides", or mentions building a PlumDeck-style presentation. Interviews the user, then generates a self-contained, offline HTML slide deck with built-in author mode.
- ▌ Cavecrew · yogiraja bundleWhen to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
- ▌ Ponytail · yogirajaForces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
- ▌ Research · yogiraja bundleInvestigate 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.
- ▌ Config Gc · yogirajaGarbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.
- ▌ Gateguard · yogirajaDesign spec for a three-stage fact-forcing PreToolUse gate (deny the first edit, force named facts, allow on evidence). Not a runnable hook in this collection; use it to build one, or to review a gate someone built.
- ▌ Hindsight · yogiraja bundleReviews everything accomplished in the current session end-to-end, distills genuine process lessons (not one-off content specifics), and saves the durable ones as persistent memory, updating an existing related memory in place rather than duplicating it. Trigger on "get some hindsight," "run a hindsight pass," "what should we improve," "review today and notate lessons," "what did you learn today," "save what's worth remembering from this session." Does not redo or re-open any of the session's actual work, and never fabricates a lesson just to have something to report.
- ▌ Implement · yogiraja bundleImplement a piece of work based on a spec, a set of tickets, or an agent brief on a triaged issue.
- ▌ Prototype · yogiraja bundleBuild 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.
- ▌ Read Wiki · yogirajaQuery the knowledge base before doing work. Use when the user asks "what do we know about X", "get context before I update this", "have we seen this pattern", "what connects A and B", or any question that accumulated project or cross-project knowledge could answer. Also invoke proactively when starting a non-trivial code task in a project that has a wiki: read the relevant pages first before touching files. Strictly read-only: never writes to any wiki file. Triggers on /read-wiki or phrases like "check the wiki", "get context", "what's in the wiki about", "have we documented".
- ▌ Wayfinder · yogiraja bundlePlan 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.
- ▌ Excalidraw · yogiraja bundleGenerate architecture diagrams as .excalidraw files from codebase analysis, with optional PNG/SVG export. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, generate excalidraw files, export excalidraw diagrams to PNG or SVG, or convert .excalidraw files to image formats.
- ▌ No AI Slop · yogiraja bundleEdit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.
- ▌ Write Wiki · yogirajaAdd to, update, or health-check a knowledge base wiki. Use when the user wants to ingest a new source (article, PDF, URL, meeting notes, runbook, design doc), update existing pages, lint the wiki for stale or orphaned content, or save a synthesis back to the wiki. Also the entry point for creating a new wiki: if no wiki exists for the current project, write-wiki asks whether to create a General Knowledge wiki (path from the Wikis registry in ~/.claude/CLAUDE.md) or a project-specific one (inside the current folder). Triggers on /write-wiki, /wiki, "add this to the wiki", "ingest this", "save this to the wiki", "update the wiki", "lint the wiki", "file this", "remember this source".
- ▌ Geo Content · yogirajaWrite or rewrite content optimized BOTH for classic SEO (ranking in Google search) AND for GEO/AEO - Generative / Answer Engine Optimization, i.e. getting quoted and cited by AI answer engines like ChatGPT, Perplexity, Google AI Overviews, and Gemini. Produces answer-first, well-structured, citable content plus an "what I optimized and why" checklist. Use this whenever the user wants a blog post, article, landing page, FAQ, or web copy that needs to rank or get picked up by AI; mentions SEO, GEO, AEO, "answer engine optimization", "generative engine optimization", keywords, search intent, ranking, or being cited by ChatGPT/Perplexity/AI Overviews; or asks to audit or rewrite existing content to perform better in search and AI answers. Trigger even if they only say "write content optimized for AI search" or "help this article rank" without naming GEO or SEO directly.
- ▌ Skill Scout · yogirajaSearch existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
- ▌ Caveman Help · yogiraja bundleQuick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".
- ▌ Goal Creator · yogiraja bundleTurns a rough intent into a sharp session goal ready to paste into /goal, under the 4000-character limit. Use when the user wants to set, write, or refine a session goal, mentions /goal, or asks to sharpen what an autonomous session should accomplish. Produces one goal text with a verifiable outcome, scope guard, acceptance criteria with proofs, and explicit authorities (deploy, publish, spend, review policy).
- ▌ Onboard Repo · yogiraja bundleOnboard Claude onto a code repository so it holds durable, verified context. Explores the repo first, lets the user interrogate what it learned, asks only the questions the code cannot answer, verifies the test and build commands actually run, then writes a short CLAUDE.md, a project wiki that survives a cold-context check, and the repo's enforced .claude/ harness (settings, rules, hooks) built from those findings. Use when arriving at an unfamiliar codebase, when a repo has no CLAUDE.md and no knowledgebase/, or when the user says "onboard Claude on this repo", "get up to speed on this codebase", "learn this repo", "set this repo up for Claude", or "build a wiki for this repo". Runs once per repo to establish context. Do NOT use for querying an existing wiki (that is read-wiki), for ingesting a single source or linting a wiki (that is write-wiki), for interviewing the user about work they want built (that is spec-interview), or for teaching the user one file, PR, or concept (that is explain-yogi-like-he-is-5
- ▌ Prompt Fixer · yogiraja bundleCleans up a rough, vague, or underspecified prompt the user wrote into a clear, well-structured prompt in plain English (no XML, no tags), then hands it back to read, paste, and edit rather than executing it. Adds the four things most prompts miss, a persona, an unambiguous task, two or three examples where they help, and explicit constraints. Use whenever the user shares a prompt and wants it tightened, fixed, sharpened, polished, cleaned up, de-jargoned, made more precise, or made to produce less vague or inconsistent output, usually a short rough one (e.g. 'classify each lead as hot/warm/cold', 'review my script and tell me whats wrong', 'write a cold email to a VP'), or wants a solid reusable prompt as the takeaway from a brainstorm even if they do not say "fix this prompt." This is the default for plain-English prompt cleanup. Do NOT use when the user wants the prompt wrapped in XML or wants Claude to then run it (that is the prompt-optimizer skill), or for editing ordinary prose, emails, messages, or da
- ▌ Skill Comply · yogiraja bundleVisualize whether skills, rules, and agent definitions are actually followed, auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines. Use when checking whether agents actually follow the skills, rules, and definitions they were given, rather than assuming they do.
- ▌ Mental Models · yogirajaPressure-test a real decision by running it through a curated library of mental models (inversion, second-order thinking, opportunity cost, expected value, base rates / outside view, regret minimization, reversible vs irreversible decisions, margin of safety, incentives, and more), then synthesize a decisive recommendation and the one thing that would change it. Use this whenever the user is weighing a real choice and wants rigorous thinking: "help me decide", "should I do X or Y", "I'm trying to figure out whether to...", "think this through with me", "apply mental models / first principles to this", "what's the smart way to look at this decision", or is stuck between options with real stakes. Complements the-llm-council (which stages a multi-persona debate); this skill instead applies named thinking frameworks. Trigger on genuine decisions even when the user never says "mental models" by name.
- ▌ Modern Python · yogiraja bundleVersion-gated modern Python guidance backed by Ruff. Use before writing, editing, fixing or refactoring any Python file: list the rules the project's target version allows, apply them, verify. /modern-python setup runs the per-project interview.
- ▌ Onboard Light · yogirajaOnboard Claude onto a repo without touching .claude/: the full onboard-repo flow (recon, mutual interrogation, verified feedback loop, CLAUDE.md block, wiki, cold eval) with the harness phase (4b) skipped by standing instruction. Use when the user says "onboard light", "onboard without the harness", "onboard but no hooks/settings/rules", or wants knowledge-only onboarding on a repo where enforcement config is unwanted (a client repo, a restricted repo, or one that is not theirs to configure). For the full flow including the .claude/ harness use onboard-repo; to add only the harness to an already-onboarded repo, run onboard-repo and re-run phase 4b alone.
- ▌ Context Budget · yogirajaAudits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Use when the context window is filling up too fast and the agents, skills, MCP servers, or rules consuming it need to be identified.