praxstack
- 114 skills
- 0 followers
- 1 repo stars
- 6 days ago last updated
- ▌ Blueprint Creator · praxstack bundleCreate exhaustive BLUEPRINT.md files — the implementation bible that expands a SPEC.md into maximum granular detail so an AI coding agent can translate it line-by-line into code with zero interpretation. This skill REQUIRES a SPEC.md to already exist. Use this skill whenever the user wants to create a blueprint, implementation blueprint, detailed spec, "bible" document, or says "create the blueprint", "expand the spec", "make it more detailed", "generate BLUEPRINT.md", or "I need every detail spelled out." Also trigger when the user has a SPEC.md and wants to go deeper before implementation. The Blueprint is the final artifact before code — it takes the portable implementation contract (SPEC.md) and fills in every edge case, validation rule, error message, sequence, and example so nothing is left to judgment. Works for any software domain. If no SPEC.md exists, this skill MUST redirect the user to generate one first using the spec-creator skill.
- ▌ Orchestrion Universal Agent Router · praxstack bundleUniversal host-neutral agent orchestration skill. Use this at the start of any non-trivial task to discover the current agent host, load the right installed skills, route ambiguous human requests through planning/TDD/debugging/review/QA/council gates, create TODOs, and prevent false completion. Designed to coordinate Superpowers, gstack, Matt Pocock skills, and llm-council-plus without assuming Claude, Codex, OpenCode, Hermes, OpenClaw, Cline, KiloCode, Antigravity, or any other specific agent.
- ▌ Teach Pro Max · praxstack bundleTeach concepts and skills through adaptive, evidence-oriented tutoring and first-class immersive visualization for quick explanations, focused lessons, and consent-based multi-session courses. Use when the user asks to learn, understand, practice, be quizzed, build intuition, receive Socratic guidance, create an accessible visual lesson, or resume prior learning. Includes progressive hints, cautious mastery evidence, a packaged offline visual lab, 38-tool production routing, review scheduling, durable learner state, evaluation tools, and offline optional adapters.
- ▌ Techtutor · praxstack bundleIntuition-first technical mentor that makes complex concepts click through analogies, visuals, and a disciplined 6-layer explanation framework (WHY — HOW — VISUALIZE — CODE/MATH — SCALE — CONNECT). Use when the user asks to explain, tutor, teach, or mock-interview on DSA, System Design, Java internals, AI/ML (GenAI, LLMs, RAG, neural networks, transformers), distributed systems, cloud architecture, databases, or any technical topic. Produces layered explanations with Mermaid diagrams, ASCII state tables, working code (not pseudocode), real-world scale references, and targeted check-in questions. Handles comparisons, follow-ups, counterexamples, code review, direct tasks, and system-design mocks. Triggers: 'explain X', 'teach me', 'how does X work', 'tutor me on', 'mock interview', 'intuition for'.
- ▌ Spec Creator · praxstack bundleCreate production-grade SPEC.md files — portable implementation contracts that any AI coding agent can build from without follow-up questions. Use this skill whenever the user wants to write a spec, specification, technical spec, implementation contract, SPEC.md, or service specification for any software task. Also trigger when the user says "spec out", "write a spec for", "create a spec", "define the contract for", or describes a system they want built and needs a thorough specification before implementation. This skill works for backend services, full-stack apps, CLI tools, SDKs, developer tools, and any domain. It produces specs at the level of a principal-engineer-authored portable implementation contract — not a PRD, not an HLD, but the artifact that sits between architecture and code.
- ▌ Tech Tutor Ren Nakamura Persona · praxstack bundleIntuition-first tech mentor who makes complex concepts click through visuals, analogies, and the 6-layer explanation framework. Use this skill when the user asks to "explain", "tutor", "teach", "mock interview", or needs intuition regarding DSA, System Design, or AI/ML.
- ▌ Concept Cartographer 2 · praxstack bundleGenerate visual concept maps, flowcharts, architecture diagrams, and relationship diagrams from structured notes or technical content using Mermaid syntax. Use when the user has lecture notes, study materials, or technical documentation and wants visual diagrams to aid understanding. Produces multiple diagram types: concept hierarchy maps, process flowcharts, architecture diagrams, comparison matrices, timeline diagrams, and mind maps. Trigger phrases: "create diagrams from notes", "visualize concepts", "concept map", "make flowcharts", "diagram this", "visual notes".
- ▌ Concept Cartographer · praxstackGenerate visual concept maps, flowcharts, architecture diagrams, and relationship diagrams from structured notes or technical content using Mermaid syntax. Use when the user has lecture notes, study materials, or technical documentation and wants visual diagrams to aid understanding. Produces multiple diagram types: concept hierarchy maps, process flowcharts, architecture diagrams, comparison matrices, timeline diagrams, and mind maps. Trigger phrases: 'create diagrams from notes', 'visualize concepts', 'concept map', 'make flowcharts', 'diagram this', 'visual notes'.
- ▌ Lecture Alchemist 2 · praxstack bundleTransform raw lecture transcripts (Zoom, YouTube, classroom recordings) into structured, retention-optimized study notes with zero topic loss. Use when the user provides a lecture transcript, class recording text, or asks to process/convert lecture notes into study material. Handles WebDev, AI/ML, Web3, DSA, and other technical domains. Produces hierarchical topic breakdowns, cleaned code artifacts with enhanced comments, intuition builders for weak explanations, domain-specific technical analysis, knowledge-gap fills, Q&A extraction, flashcards, spaced repetition plans, three-level summaries, and actionable study materials. Triggers: 'process this transcript', 'convert lecture to notes', 'lecture notes', 'transcript to study material', 'Lecture Alchemist'.
- ▌ Lecture Alchemist · praxstack bundleTransform raw lecture transcripts (Zoom, YouTube, etc.) into structured, retention-optimized study notes. Use when the user provides a lecture transcript, class recording text, or asks to process/convert lecture notes. Handles WebDev, AI/ML, Web3, DSA, and general tech domains. Produces hierarchical topic breakdowns, cleaned code artifacts, intuition builders, flashcards, spaced repetition plans, and actionable study materials. Trigger phrases: 'process this transcript', 'convert lecture to notes', 'lecture notes', 'transcript to study material', 'Lecture Alchemist'.
- ▌ Eiirp · praxstack bundleEverything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands, (3) check schema-pack consistency against the brain's actual shape, (4) file enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify resolvability, (7) report. Named after the Radiohead song. Nothing produced during significant work lives only in chat — knowledge becomes permanent, patterns become reusable. Also carries the always-on auto-fire gate: when at least 500 words of structured analysis on a user-shared document is about to be delivered, file the brain page first, then deliver the analysis with the link in that same reply.
- ▌ Teacher · praxstack bundleA standalone teacher for any subject at any level, from first intuition to deep technical understanding. It picks the medium that makes the idea click (hand-drawn diagrams, interactive explorables, scrubbable animations, narrated videos), finds and checks the best tool the host can run, changes the explanation, example or medium when the learner is still confused, and keeps exploring until the learner says they're satisfied. Runs a single session or a series with a consented journal, and coordinates other agents when the host supports it. Works in Claude Code, Codex, Pi, OpenCode, Gemini CLI, Hermes, Cursor and any host that can read files and run commands. Use when someone says "teach me", "explain this visually", "help me understand", "make a lesson", "I still don't get it" or asks for an explainer, animation or interactive lesson.
- ▌ Handdrawn JS Video · praxstack bundleMake a finished, narrated explainer MP4 (natural voice, music, effects) in a hand-drawn style drawn every frame in plain JavaScript on a 2D canvas, with paper cut-outs and hand lettering by default, or chalkboard or blueprint. Wobbly boiling lines, stroke-on edges and letters, squash-and-stretch pops, a paper plane travelling a hand-drawn graph, comic callouts, a code card and a dry-run table filled in by hand. Use it for LeetCode/DSA walkthroughs and concept explainers when someone wants a hand-made, storybook, paper-cut, whiteboard or chalkboard look, a "JS-drawn every frame" short, or the fastest render of the tool family.
- ▌ Motion Canvas Video · praxstack bundleMake a finished, narrated explainer video (an MP4 with a natural voice, music and effects baked in) with Motion Canvas, built from TypeScript scenes timed to the voice, a persistent animated subject, camera moves, code panels with an active-line highlight, DP tables, complexity ladders and comic callouts. Use for LeetCode/DSA walkthroughs (five-part format), algorithm or system explainers, and any request for a video or animation made with Motion Canvas or code-driven 2D motion graphics. Covers voice (Kokoro, offline), a resumable headless render, mixing, QA and delivery through a state machine that survives interruptions.
- ▌ Draft In Voice · praxstack bundleGhostwrite content in a specific person's voice from a VALIDATED voice profile — tweets, replies, short posts, launch copy, recruiting blurbs, emails. Loads the subject's voice profile (people/{slug}-voice) plus first-party context from the brain, drafts 2-3 options in-register, then runs a hard voice-fidelity self-check before showing anything. Includes the profile BUILDER: if no validated profile exists, drafting hard-stops and this skill walks the corpus-to-fingerprint build instead. Never auto-posts.
- ▌ Skill Autobench · praxstack bundleAuthor an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session transcripts — a user correction after an invocation is the gold signal — then synthesize an eval_contract plus 4-8 replayable cases with honesty labels (SPEC-DERIVED vs HISTORY-IMPLIED) and stage the result at skills/{name}/eval/autobench-{date}.md as PENDING-HUMAN-APPROVAL. Never rewrites SKILL.md. Ships two guard companions: panel integrity (multi-model judging must prove each provider actually responded) and the fail-improve taxonomy (logged LLM-fallback cases convert to deterministic code over time).
- ▌ Skillpack Check · praxstackRun `gbrain skillpack-check` to produce an agent-readable JSON health report for the gbrain install. Wraps `gbrain doctor` + `gbrain apply-migrations --list` so a host agent (your OpenClaw's morning-briefing, any OpenClaw cron) can see at a glance whether the skillpack needs attention. Use when the user asks "is gbrain healthy?", when a cron fires a morning check, or proactively when something seems off (jobs not running, brain not updating, autopilot silent).
- ▌ Threejs Video · praxstack bundleMake a finished, narrated explainer MP4 (natural voice, music, effects) as a 3D Three.js "toy diorama" - rounded toy blocks on a game board on a wooden desk at night, a warm spotlight and a cool rim light, soft shadows, bloom on whatever is active, a city skyline and string lights behind - with the data structure as 3D pillars and glowing arcs, a little mascot token that flies routes, a camera that dollies and orbits on every line, and crisp DOM text on top (captions, chapter banners, question cards with a think countdown, a code panel with an active line, a dry-run table, a complexity ladder, comic bursts). Use it for LeetCode/DSA walkthroughs and concept explainers when someone asks for a Three.js, WebGL or 3D animated video, a "toy world" or diorama look, or a cinematic 3D explainer rendered frame by frame to MP4.
- ▌ Remotion Video · praxstack bundleMake a finished, narrated explainer video (an MP4 with a natural Kokoro voice, music and effects baked in) with Remotion, where React components are rendered frame by frame in headless Chromium. It gives a polished motion-graphics look with a persistent animated subject, camera push-ins, depth and glow, comic chapter stings and callouts, code panels with an active line, DP tables and a caption band, all keyed to the voice timing. Use it when someone asks for a Remotion video, a React or TypeScript animation, or a LeetCode or DSA walkthrough in a crisp motion-graphics style. It runs the resumable eight-phase pipeline (brief, script, voice, visuals, render, mix, QA, deliver) with segmented renders that survive the 2-hour job cap.
- ▌ Explain Diagram · praxstack bundleDraw a still figure that proves one claim, how parts connect, how a process flows, or how a subject is mapped out, and frame it with why it works, how it works and a look-for cue. Renders Mermaid, D2, Graphviz, PlantUML, Vega-Lite, BPMN and Excalidraw sources locally by default, with an explicit opt-in Kroki fallback, hand-drawn by default (Mermaid handDrawn, D2 sketch, Kalam labels), or uses hand-written SVG with lesson-notebook ink marks. Use when structure is the idea and nothing needs to move.
- ▌ Explainer Video · praxstack bundleMake a finished, narrated explainer video (an MP4 with a natural voice, music and animation timed to the voice), for example a LeetCode or DSA problem walkthrough, a concept explainer or an anim video. Use this whenever someone asks for a video, an animated explainer, a 3Blue1Brown-style animation, or a film made with Manim, Motion Canvas, Remotion, Revideo, HyperFrames, GSAP, Three.js, Theatre.js or hand-drawn canvas, or a short Claude Motion-style clip (a Short, Reel or data clip), even if they only say "make a video of this problem". It picks the right tool skill, enforces the rules that stop the usual failures (an interactive page instead of a video, a robotic or missing voice, slide-like visuals), and runs the resumable eight-phase pipeline.
- ▌ Lesson Notebook · praxstack bundleThe teacher's default look for every visual it makes, a hand-drawn whiteboard lesson. Quad-ruled paper, a red margin rule, three voices (printed book serif, machine printout, the coach's handwriting) and a pen that draws marks and writes notes live. Use it for explorables, diagrams, animations and video frames unless the learner or project asks for another style. Includes the CSS tokens, OFL fonts, seeded hand-drawn stroke geometry (ink.js), the pen animator (pen.js) and a bundler that makes single-file pages.
- ▌ Theatrejs Video · praxstack bundleMake a finished, narrated explainer MP4 (natural voice, music, effects) animated with Theatre.js, where every keyframe is generated from the voice timing so re-voicing re-times the whole film. The default look is a 2.5D motion-design diorama in the DOM and SVG, with parallax depth layers, a Theatre camera that pans, dollies and orbits, depth-of-field blur, and sky moods per chapter. It includes a persistent glowing graph with planes flying routes, comic callout bursts, chapter swipes, question cards with a think countdown, and a code panel with an active-line highlight. Use it for LeetCode/DSA walkthroughs and concept explainers when someone asks for a Theatre.js video, keyframed or 2.5D/parallax motion graphics, or a film they can later hand-tweak in Theatre Studio. A Three.js binding of the same sheet is included for a 3D variant.
- ▌ Concept Animation · praxstack bundleMake a short, scrubbable, captioned animation of one idea changing, driven by a model so every frame shows real numbers, then export it frame-exact to MP4, GIF and WebVTT captions with Playwright and ffmpeg. Use when the insight is in the change itself (a weight growing, a curve shifting, a process running) and the learner should watch rather than drive. Hand-drawn lesson-notebook look by default. For full narrated videos hand the clip to explainer-video; for learner-driven change use explorable.
- ▌ Hyperframes Video · praxstack bundleMake a finished, narrated explainer MP4 (natural Kokoro voice, music, effects baked in) with HyperFrames (one HTML + GSAP composition rendered frame-exact by the HyperFrames CLI) in a dark editorial look with per-chapter coloured light, a perspective floor, a tilted camera that pushes and pans over one persistent glowing graph with a hopping mascot, comic callout bursts, chapter stings, question cards with a think countdown, a code panel with an active-line highlight and a dry-run table. Use it for LeetCode/DSA walkthroughs and concept explainers when someone asks for a HyperFrames video, an HTML/GSAP motion-graphics explainer, or a polished animated explainer rendered to MP4 (never an interactive page).
- ▌ Algo Sensei · praxstack bundleYour personal DSA & LeetCode mentor. Use for problem explanations, progressive hints, code reviews, mock interviews, pattern recognition, complexity analysis, and custom problem generation. Automatically adapts to your learning style and request type.
- ▌ Manim Video · praxstack bundleMake a finished, narrated explainer MP4 (natural voice, music and effects baked in) with Manim Community Edition, the Python engine behind 3Blue1Brown / 3b1b style math animation. The starter film has a lit dark stage, a persistent weighted graph with glowing active paths, a travelling plane token, chapter cards, question cards with a think countdown, an input decoder, DP rows, a complexity ladder, a code panel without ligatures and comic callouts, all under a camera that pushes in. Use it when someone asks for a Manim video, a math animation, an "anim video", a 3b1b-style explainer, or a LeetCode/DSA or concept walkthrough as a video file. It runs the shared eight-phase pipeline (brief, script, voice, visuals, render, mix, QA, deliver) and renders chapters in parallel, synced to the voice to the frame.
- ▌ Motion Video · praxstack bundleMake a short narrated motion-graphics clip (an MP4 with a natural voice, music and burned-in karaoke captions) from one editable film.json of shots and ready-made blocks: titles, statements, steps, compare cards, counters that count up, bar, line and ring charts read from CSV or JSON data, a multiple-choice question with a think countdown and a reveal, a graph that flies routes, code with a focus bar and an array with pointers. Lays out for 16:9, 9:16 (Shorts, Reels, TikTok safe areas), 1:1 and 4:5, ships a browser editor where every word, number, colour and time can be changed, and fills the narration's numbers from the same data. Use it for daily-question Shorts, data or metrics clips, launch and product explainers, social cuts, or when someone asks for a Claude Motion style clip without Motion; for long five-part DSA films prefer the other kits.
- ▌ Revideo Video · praxstack bundleMake a finished, narrated explainer MP4 (natural Kokoro voice, music and effects baked in) with Revideo, the Motion Canvas fork with a headless render API, as one continuous TypeScript scene rendered in headless Chromium and encoded with FFmpeg in resumable segments. The look is a dark, warm, cinematic stage with a light pool, parallax dot grid, grain and vignette, a persistent glowing graph under a moving camera, decoded input that flies into the graph, question cards with a countdown ring, a code panel with an active-line highlight, dry-run tables, a complexity ladder, orange chapter wipes and comic callout bursts, all keyed to the voice timing. Use it when someone asks for a Revideo or Motion Canvas style video, a TypeScript/canvas animation rendered headless, or a LeetCode or DSA walkthrough in this style, even if they only say "make a video of this problem". It runs the eight-phase resumable pipeline and delivers the MP4.
- ▌ Eli · praxstackExplain any topic in a detailed, interactive, visual HTML explainer for a mature reader making a decision. Use when the user asks for an "eli" page, a decision-grade visual breakdown, or to regenerate an explainer with more depth. Extends /eli5 with evidence labels, tradeoffs, risks, costs, install commands, and interactive filtering and selection. Offline-safe, no CDN, no API keys, no telemetry.
- ▌ Course · praxstack bundleTurn a set of lessons into a course with a map of the whole subject (lessons placed by prerequisite, hand-drawn arrows), each lesson offering Quick explain, Teach me (interactive), Watch (film or narrated video), Read and run the code, Quiz me, and a Learning, Done or Skip status; plus an outline and a notes sheet kept apart from the lessons, and a catalog of courses. Use when a subject needs more than one sitting. Builds static pages in the lesson-notebook look and tests every lesson's code, interactions and looks in one command.
- ▌ Visual QA · praxstack bundleCheck every teaching page and video before a learner sees it. Pages run in real Chromium at desktop and phone sizes, light and dark, with and without reduced motion, failing on console errors, sideways scroll, low contrast, tiny text, figure text drawn under 11px, small tap targets and missing text alternatives, with screenshots to look at. Videos are checked with ffprobe and ffmpeg for size, frame rate, black or frozen stretches, captions, loudness and peaks, plus a contact sheet. Use after building any explorable, diagram, animation or video.
- ▌ Explorable · praxstack bundleBuild an interactive lesson where one executable model drives every view, a figure the learner manipulates, live readouts, optional practice questions, a narrated film, margin notes and a report back to the teacher. Complete explanation first, with immediate controls; attempt-first only for explicitly requested practice. One hint after a miss, taught directly after a second, and a "still confused?" button that swaps in a different explanation and records what was tried. Use for any "teach me X" where something can be varied, in any subject. Builds to one self-contained HTML file in the lesson-notebook style.
- ▌ Gsap Video · praxstack bundleMake a finished, narrated explainer MP4 (natural voice, music, effects) from one GSAP-animated web page, in a dark editorial look with coloured chapter lighting, a camera that pushes and pans over a persistent SVG graph (edges drawn on, a paper-plane token flying routes), comic callout bursts, chapter slabs, question cards with a think countdown, a code panel with an active-line highlight and a dry-run table. Use it for LeetCode/DSA walkthroughs and concept explainers when someone asks for a GSAP video, a motion-graphics or kinetic-typography explainer built with web tech (HTML, SVG, CSS), or a polished "Claude-made animation" style film rendered frame by frame to MP4.
- ▌ Skillify · praxstack bundleThe meta skill. Turn any raw feature into a properly-skilled, tested, resolvable unit of agent capability. Idempotent: running on an existing skill improves it (bug fix, new input, quality pass) instead of starting from scratch. Every skill declares an EVAL CONTRACT (its goal + skill-specific dimensions + hard-fails) so the cross-modal eval judges THIS skill's real purpose, not generic slop. Cross-modal eval runs BEFORE tests: 3 frontier models from different providers critique the output against the contract, you iterate to quality, THEN write/update tests that lock in the proven-good behavior. NO-REGRESSION LAW: any edit to a skill must score at least the previous iteration's eval score — forward only, never back. For skills that back a scheduled job, an edit MUST re-run a representative task and eval it before shipping.
- ▌ Soul Audit · praxstackRe-run or deepen the agent's identity interview. Drives the SHARED bootstrap answer bank (state/interview.json) via `gbrain bootstrap interview --set/--show/--confirm`, then re-renders the identity files with `gbrain bootstrap render --only FILE --force`. One answer store, two surfaces: first-boot bootstrap and this re-run skill write the same bank, so an updated answer flows into SOUL.md, USER.md, ACCESS_POLICY.md, and HEARTBEAT.md without hand-editing rendered files. Every answer is the user's own words — never invented.
- ▌ Book Mirror · praxstack bundleTake any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's life, NOT a therapist assigning homework. The reader decides what to do about it. Layout is a top-aligned HTML table or stacked sections, never a bare markdown pipe table (pipe tables center-misalign uneven columns). Output is a single brain page at media/books/{slug}-personalized.md plus an optional PDF via brain-pdf.
- ▌ Idea Lineage · praxstack bundleTrace one idea's evolution through the brain: first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version. Use for single-idea conceptual lineage, not broad concept-map synthesis or structured entity metrics.
- ▌ Prax Teach V2 3 · praxstack bundleTeach a concept or skill through adaptive, evidence-oriented tutoring that works for quick explanations, focused lessons, and persistent multi-session courses. Use when the user asks to learn, understand, practice, be quizzed, build intuition, receive Socratic guidance, create an accessible lesson, or resume and review prior learning. Do not use for ordinary task completion unless teaching is requested or clearly the goal.
- ▌ Prax Teach V2 4 · praxstack bundleTeach a concept or skill through adaptive, evidence-oriented tutoring that works for quick explanations, focused lessons, and persistent multi-session courses. Use when the user asks to learn, understand, practice, be quizzed, build intuition, receive Socratic guidance, create an accessible lesson, or resume and review prior learning. Do not use for ordinary task completion unless teaching is requested or clearly the goal.
- ▌ Chronicle 2 · praxstack bundlePersonal journal intelligence that transforms raw, unorganized thoughts into structured diary entries with clinically-informed psychological analysis. Use when the user provides journal entries, diary text, stream-of-consciousness writing, voice memo transcriptions, or asks to process daily thoughts into a structured format. Produces narrative entries, gratitude extraction, multi-level psychological analysis (surface/medium/clinical), health pattern flags, therapeutic micro-actions, bridge-to-tomorrow planning, and longitudinal pattern tracking. Triggers: 'journal entry', 'diary entry', 'process my thoughts', 'Chronicle', 'daily reflection', 'write up my day', 'voice memo journal'.
- ▌ Backend Pe 2 · praxstack bundlePrincipal-engineer-grade backend design and review orchestrator. Routes to the right language-specific backend skill (Python, TypeScript, Java, C++, Node.js, JavaScript, Python-ML) and applies cross-cutting backend methodology - correctness, reliability, performance, security, observability, data consistency, scalability, operability. Use when the user asks to design, build, review, harden, scale, or debug a production backend service, distributed system, or data pipeline and a language choice exists or is implied. Trigger keywords - backend design, system design, principal engineer, production backend, service architecture, distributed system, microservice, API design, backend review, harden service, backend-pe, supermode, antigravity. Not for single-file scripts, prototypes without reliability needs, or pure frontend work.
- ▌ Frontend Pe 2 · praxstack bundlePrincipal-frontend-engineer workflow for production-grade, design-led UI delivery. Use when the user demands a design-led UI, "ultra-frontend", Awwwards-style, or high-end UX, or when requests require a design-first workflow with motion strategy, luxury audit, and unconstrained implementation. Forces explicit aesthetic direction, spring-physics motion design, micro-interaction planning, and modern React/Next.js stack (App Router, React 19, Tailwind, Framer Motion, Zustand/Jotai) before any code is written. Triggers on "ultrafrontend", "high-end UX", "awwwards style", "world-class UI", "design first", "motion strategy". Not for: analysis/audit of existing UI (use ultrathink-frontend), cross-domain work (use super-mode-core), or depth-level selection (use kingmode). This is greenfield design-led implementation workflow, not analysis.
- ▌ Obsidian CLI 2 · praxstack bundleControl Obsidian from the terminal using the CLI v2 (Obsidian 1.12+). Create, read, append, prepend, move, rename, delete files; manage frontmatter properties; list and toggle tasks; search the vault; analyze links; query Bases; manage plugins, themes, snippets, workspaces. Use when performing vault operations, automating note workflows, appending content to notes, managing frontmatter properties, searching the vault, running Base queries, or scripting Obsidian from bash. Requires Obsidian app running. Trigger phrases: "obsidian cli", "append to note", "create obsidian note", "search vault", "obsidian property", "obsidian task", "daily note", "obsidian backlinks", "orphans", "base:query".
- ▌ Spec Creator 2 · praxstack bundleCreate production-grade SPEC.md files — portable implementation contracts that any AI coding agent can build from without follow-up questions. Use this skill whenever the user wants to write a spec, specification, technical spec, implementation contract, SPEC.md, or service specification for any software task. Also trigger when the user says "spec out", "write a spec for", "create a spec", "define the contract for", or describes a system they want built and needs a thorough specification before implementation. This skill works for backend services, full-stack apps, CLI tools, SDKs, developer tools, and any domain. It produces specs at the level of a principal-engineer-authored portable implementation contract — not a PRD, not an HLD, but the artifact that sits between architecture and code.
- ▌ Idea Capturer 2 · praxstack bundleStructured system for capturing fleeting thoughts, developing raw ideas into actionable concepts, and organizing creative thinking. Use when the user wants to capture an idea, brain-dump, develop or explore a half-formed concept, run a brainstorming session, organize scattered notes, synthesize ideas, or build a Zettelkasten/second-brain workflow. Trigger phrases: "capture idea", "save this idea", "idea dump", "brain dump", "develop idea", "brainstorm", "connect ideas", "review my ideas", "tag idea", "find ideas about".
- ▌ Blueprint Creator 2 · praxstack bundleCreate exhaustive BLUEPRINT.md files — the implementation bible that expands a SPEC.md into maximum granular detail so an AI coding agent can translate it line-by-line into code with zero interpretation. REQUIRES a SPEC.md to already exist. Use whenever the user wants to create a blueprint, implementation blueprint, detailed spec, "bible" document, or says "create the blueprint", "expand the spec", "make it more detailed", "generate BLUEPRINT.md", or "I need every detail spelled out." Also trigger when the user has a SPEC.md and wants to go deeper before implementation. The Blueprint is the final artifact before code — it takes the portable implementation contract (SPEC.md) and fills in every edge case, validation rule, error message, sequence, and example so nothing is left to judgment. Works for any software domain. If no SPEC.md exists, this skill MUST redirect the user to generate one first using spec-creator.
- ▌ Svg Logo Designer 2 · praxstack bundleElite SVG logo design intelligence. Creates professional hand-crafted SVG logos, brand marks, icons, wordmarks, lettermarks, emblems, abstract marks, and visual identities. Uses a rigorous multi-phase discovery interview (2-3 rounds) to extract brand DNA, emotional tone, and design intent before generating. Produces multiple concepts with layout variations, full color systems, design tokens (CSS custom properties, JSON, Figma-ready specs), and optimized SVG using advanced techniques (gradients, masks, filters, blend modes, animations). Self-evaluates every concept against a 7-criterion quality rubric. Structured iterative refinement loop. Use when creating logos, brand marks, icons, symbols, visual identities, wordmarks, lettermarks, emblems, mascot marks, scalable vector branding, brand guidelines, or design systems from logos.
- ▌ Constellation Team 2 · praxstack bundleCoordinate a cross-functional star-team workflow (Product Manager, Principal Engineer, Backend, Frontend, QA/Security, DevOps) with mandatory architecture and code-review checkpoints. Use when a request needs end-to-end product delivery, multi-role collaboration, or explicit role-based outputs, or when the user asks for "star team", "cross-functional", "full lifecycle", "multi-role" planning, or product delivery spanning PM + architecture + backend + frontend + QA + DevOps.
- ▌ Transcribe Refiner 2 · praxstackClean and reconstruct raw auto-generated captions (Zoom, YouTube, Teams, Google Meet, Otter.ai, etc.) into readable, coherent transcripts. Use when the user provides raw caption files (.txt, .vtt, .srt), meeting transcripts with timestamps and speaker tags, or asks to clean up/refine a transcript. Handles: timestamp removal, speaker tag normalization, filler word removal, broken sentence reconstruction, transcription error correction, paragraph formation. Preserves every piece of substantive content while removing noise. Trigger phrases: 'clean this transcript', 'refine captions', 'fix this transcript', 'process Zoom captions', 'clean up meeting notes'.
- ▌ Transcript Pipeline 2 · praxstack bundleDeterministic, auditable transcript-to-tutorial workflow for Zoom class captions with optional resource enrichment. Use when asked to 'process this transcript', 'convert lecture to notes', 'run transcript pipeline', 'generate class tutorial from Zoom captions', 'validate transcript coverage', or 'enrich class resources' (Notion/Canva/Drive links) for bootcamp notes. Combines deterministic scripts (ingest, validate, publish) with chat-stage prompts (refine, synthesize, enhance) and keeps traceability in .pipeline/* artifacts.
- ▌ Prax Teach V2 2 · praxstack bundleTeach a concept or skill through adaptive, evidence-oriented tutoring that works for quick explanations, focused lessons, and persistent multi-session courses. Use when the user asks to learn, understand, practice, be quizzed, build intuition, receive Socratic guidance, create an accessible lesson, or resume and review prior learning. Do not use for ordinary task completion unless teaching is requested or clearly the goal.
- ▌ Briefing · praxstack bundleCompile daily briefing with meeting context, active deals, and citation tracking
- ▌ Maintain · praxstackBrain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.
- ▌ Brain Ops · praxstackBrain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking. Read this before any brain interaction.
- ▌ Chronicle · praxstack bundlePersonal journal intelligence that transforms raw, unorganized thoughts into structured diary entries with psychological analysis. Use when the user provides journal entries, diary text, stream-of-consciousness writing, voice memo transcriptions, or asks to process daily thoughts into a structured format. Produces narrative entries, gratitude extraction, multi-level psychological analysis (surface/medium/clinical), health pattern flags, therapeutic micro-actions, and bridge-to-tomorrow planning. Trigger phrases: 'journal entry', 'diary entry', 'process my thoughts', 'Chronicle', 'daily reflection', 'write up my day'.
- ▌ Backend Pe · praxstackDistinguished Principal Engineer backend/system architecture skill. Use when the user demands "BackendPE", "Supermode", "Antigravity", or requests high-performance, unlimited-context, world-class backend and distributed systems design. This skill maximizes depth, rigor, and production readiness.
- ▌ Cold Start · praxstackDay-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses ClawVisor for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives. Use when a user has just finished gbrain setup and asks "now what?"
- ▌ Frontend Pe · praxstackACTIVATION TRIGGER. Use this skill when the user demands "Ultrafrontend", "High-End UX", "Awwwards Style", or world-class UI design. This skill enforces a design-first workflow with zero-compromise aesthetics.
- ▌ Kingmode · praxstackPrincipal-engineer routing guidance with three reasoning depths — Default, ULTRATHINK, and KINGMODE. Use when the user explicitly types "ULTRATHINK" or "KINGMODE", asks for "architecture-first" output, requests "deep reasoning", or the task is system design, scalability, reliability, security review, compliance planning, or any production decision where depth beats speed. Covers mode selection, the four-step clarify/decide/implement/validate workflow, non-hallucination discipline, and per-mode output formats. Not for: quick lookups, single-file refactors, or tasks where the user asked for brevity.
- ▌ Obsidian CLI · praxstackControl Obsidian from the terminal using CLI v2 (1.12+). Create, read, append, search files; manage properties, tags, tasks; query bases; use templates; analyze links. Use when performing vault operations, automating note workflows, appending content to notes, managing frontmatter properties, or searching the vault from the command line. Requires Obsidian app to be running.
- ▌ Superimprove · praxstack bundleRun a bounded, evidence-first audit-fix-review-verify loop on a codebase when the user asks to improve, harden, overhaul, or fix all confirmed defects. Use only with explicit edit authority in a git repository. Do not use for advisory-only reviews, a single narrow bug, or when the worktree is dirty and the owner has not chosen how to preserve it.
- ▌ Idea Capturer · praxstackProvides a structured system for capturing fleeting thoughts, developing raw ideas into actionable concepts, and organizing your creative thinking.
- ▌ Gbrain Advisor · praxstackProactive "make the most of gbrain" coaching. Runs `gbrain advisor` on a cadence and pings the user with the top high-leverage actions for their brain: version drift, pending migrations, stalled jobs, low embed coverage, setup smells, and uninstalled brain skills. Read-only; always asks before fixing.
- ▌ Daily Task Prep · praxstackMorning preparation. Calendar lookahead, meeting context loading, open threads from yesterday, active task review. Extends briefing with actionable prep.
- ▌ Signal Detector · praxstackAlways-on ambient signal capture. Applies on every substantive inbound message to detect original thinking and entity mentions. Spawn as a cheap sub-agent where the harness supports it; otherwise run detection inline. Aim to never block the main response.
- ▌ Company Brainify · praxstack bundleExtract a sanitized shared team/company brain from a personal brain. Strips internal ratings, compensation, performance assessments, retention and political dynamics from pages, takes, and facts across the full scan scope (people, companies, meetings, dailies, cross-references — not just people/), verifies with grep + retrieval passes, and purges sensitive git history behind the data-loss-gate confirmation card. Also runs as a report-only re-audit on an existing shared brain.
- ▌ Svg Logo Designer · praxstack bundleElite SVG logo design intelligence. Creates professional hand-crafted SVG logos, brand marks, icons, wordmarks, lettermarks, emblems, abstract marks, and visual identities. Uses a rigorous multi-phase discovery interview (2-3 rounds) to extract brand DNA, emotional tone, and design intent before generating. Produces multiple concepts with layout variations, full color systems, design tokens (CSS custom properties, JSON, Figma-ready specs), and optimized SVG using advanced techniques (gradients, masks, filters, blend modes, animations). Self-evaluates every concept against a 7-criterion quality rubric. Structured iterative refinement loop. Use when creating logos, brand marks, icons, symbols, visual identities, wordmarks, lettermarks, emblems, mascot marks, scalable vector branding, brand guidelines, or design systems from logos.
- ▌ Backend Pe Cpp · praxstackPrincipal-engineer-grade C++ backend design, implementation, and review for performance-critical services, networking, storage, and infrastructure. Covers C++20/23, RAII, ownership, modern concurrency (std::jthread, std::atomic, lock-free where proven), sanitizers, fuzzing, hardening, and C++-specific failure modes (UB, lifetime bugs, data races, false sharing, allocator pressure). Use when designing, building, reviewing, refactoring, profiling, hardening, or debugging C++ backend systems, low-latency services, network daemons, or storage engines. Trigger keywords - C++ backend, C++20, C++23, CMake, low-latency, RAII, smart pointers, sanitizers, ASan UBSan TSan, fuzzing, lock-free, zero-copy, performance review, memory safety review.
- ▌ Constellation Team · praxstack bundleCoordinate a cross-functional star-team workflow (Product Manager, Principal Engineer, Backend, Frontend, QA/Security, DevOps) with mandatory architecture and code-review checkpoints. Use when a request needs end-to-end product delivery, multi-role collaboration, or explicit role-based outputs (PM/PE/Backend/Frontend/QA/DevOps), or when the user asks for "star team", "cross-functional", "full lifecycle", or "multi-role" planning.
- ▌ Transcribe Refiner · praxstackClean and reconstruct raw auto-generated captions (Zoom, YouTube, Teams, Google Meet, Otter.ai, etc.) into readable, coherent transcripts. Use when the user provides raw caption files (.txt, .vtt, .srt), meeting transcripts with timestamps and speaker tags, or asks to clean up/refine a transcript. Handles: timestamp removal, speaker tag normalization, filler word removal, broken sentence reconstruction, transcription error correction, paragraph formation. Preserves every piece of substantive content while removing noise. Trigger phrases: 'clean this transcript', 'refine captions', 'fix this transcript', 'process Zoom captions', 'clean up meeting notes'.
- ▌ Backend Pe Java · praxstackPrincipal-engineer-grade Java backend design, implementation, and review. Covers JDK 21 LTS, virtual threads, Spring Boot 3 / Micronaut / Quarkus, reactive vs. imperative, JVM tuning, concurrency primitives, and Java-specific failure modes (connection pool starvation, GC pauses, blocking in reactive, boxing in hot paths). Use when designing, building, reviewing, refactoring, hardening, profiling, or debugging Java or Kotlin backend services. Trigger keywords - Java backend, JVM, Spring Boot, Micronaut, Quarkus, virtual threads, Project Loom, JPA, Hibernate, Kafka Java, JVM tuning, GC tuning, HikariCP, G1 ZGC, Resilience4j. Not for Android work.
- ▌ Product Manager · praxstack bundleProduct/program management for software products. Use when defining product strategy, writing PRDs, prioritizing roadmap, running discovery, setting success metrics, managing stakeholders, planning launches, or making build/buy/cut decisions. Covers vision, user research synthesis, RICE/ICE/Kano/MoSCoW prioritization, user stories, acceptance criteria, sprint planning, metrics (North Star, activation, retention, NPS), A/B testing, go-to-market, and business cases. Keywords: PM, product manager, PRD, roadmap, prioritization, RICE, user stories, acceptance criteria, North Star metric, activation, retention, A/B test, launch, stakeholder, JTBD, MVP.
- ▌ Super Mode Core · praxstackInternal loader for principal-engineer domain standards across backend, frontend, and security. Invoked by kingmode (or a calling skill) when a task spans multiple domains and needs the relevant standards loaded together. Does NOT make user-facing mode decisions — that is kingmode's job. Takes an already-selected mode + domain tags and loads the matching domain-standards skills (backend-architecture-standards, frontend-excellence-standards, security-compliance-standards). Triggers only as a downstream loader: kingmode classified a task as multi-domain, a caller asks for "super-mode", or a user typed "SUPER-MODE" to signal cross-domain scope. Not for: single-domain tasks (use the domain skill directly), mode selection or depth routing (use kingmode), frontend-only analysis (use ultrathink-frontend), greenfield frontend workflow (use frontend-pe), or any user-facing depth decision. Pure loader — no mode routing, no user-facing output.
- ▌ Cross Agent Handoff · praxstack bundlePrepare or consume a precise, privacy-safe handoff between agent sessions, harnesses, subagents, CLIs, or humans. Use when work crosses contexts, survives compaction, is delegated, or must be resumed without trusting narrative completion claims.
- ▌ Transcript Pipeline · praxstack bundleThis skill should be used when the user asks to "process this transcript", "convert lecture to notes", "run transcript pipeline", "generate class tutorial from Zoom captions", "validate transcript coverage", or "enrich class resources" (Notion/Canva/Drive links) for bootcamp notes.
- ▌ Baron Von Markup · praxstack bundleMarkdown architect that transforms raw text, unstructured notes, transcripts, or code output into well-formatted, semantically meaningful Markdown while preserving content integrity. Use when the user provides messy notes, meeting transcripts, API output, script logs, reference material, or inconsistent Markdown and asks to format, clean up, structure, normalize, or document it. Produces hierarchical documents with correct heading levels, code blocks with language tags, tables for key-value data, blockquotes for warnings, TOC when warranted, and reference sections — with zero fact invention or paraphrasing of technical literals. Triggers: 'format this', 'clean this up', 'make this markdown', 'structure this', 'document this', 'Baron von Markup', 'format as README', 'format as markdown'.
- ▌ Conversation Archive · praxstack bundleImport AI-assistant chat exports (ChatGPT, Claude, Perplexity) and agent session transcripts into the brain as one dated page per conversation under conversations/, validate each page against the native conversation parser, extract facts via the native conversation-facts flow, and keep the archive gap-free with a detect-and-backfill loop. Then answer archive questions: "when did I first discuss X", trace how an idea evolved across past conversations, pull a specific thread.
- ▌ Backend Pe Nodejs · praxstackPrincipal-engineer-grade guidance for the Node.js runtime itself - event loop, streams, worker threads, cluster, memory, GC, native addons, and runtime-level failure modes. Covers diagnosing event-loop lag, heap leaks, CPU profiling, AsyncLocalStorage, AbortController, and production-grade process lifecycle on Node 20+ LTS or Bun. Use when debugging or tuning Node runtime behavior, investigating latency spikes, memory leaks, throughput regressions, or designing at the runtime level. Trigger keywords - Node.js runtime, event loop, event loop lag, worker threads, cluster, streams backpressure, AsyncLocalStorage, heap snapshot, clinic.js, flamegraph, node --prof, memory leak Node, V8 tuning, AbortController, graceful shutdown Node. Not for language-level concerns (use backend-pe-javascript or backend-pe-typescript).
- ▌ Backend Pe Python · praxstackPrincipal-engineer-grade Python backend design, implementation, and review. Covers asyncio, FastAPI/Django, SQLAlchemy, Pydantic, type hints, packaging, and Python-specific failure modes (GIL, blocking-in-async, subprocess, multiprocessing). Use when designing, building, reviewing, refactoring, hardening, profiling, or debugging Python services, APIs, workers, and data pipelines in production. Trigger keywords - Python backend, FastAPI, Django, asyncio, SQLAlchemy, Pydantic, uvicorn, gunicorn, aiohttp, Celery, Python service review, Python API design, Python performance, blocking event loop, GIL contention. Not for Python ML/training code (use backend-pe-python-ml) or pure frontend work.
- ▌ Principal Engineer · praxstack bundleArchitecture governance, design review, and code-merge gatekeeping for senior/staff/principal-level technical oversight. Use when reviewing architecture proposals, approving or rejecting designs before implementation, gating pull requests before merge, arbitrating technology selection, enforcing cross-service API contracts, or setting quality/security standards for a team. Focuses on approval checkpoints, trade-off analysis, and non-obvious architectural anti-patterns. Not for hands-on implementation (use backend-system-design-expert or language-specific skills), product feature definition, or sprint management.
- ▌ Devops Sre Engineer · praxstack bundleInfrastructure-as-code, CI/CD, Kubernetes, observability, and reliability engineering for production systems. Use when designing or reviewing infrastructure (Terraform/Pulumi), CI/CD pipelines (GitHub Actions/GitLab CI), Kubernetes manifests and Helm charts, monitoring/alerting (Prometheus/Grafana), logging pipelines, SLO/error-budget policy, incident response/postmortems, disaster recovery, or cost optimization. Focuses on reliability patterns, deployment safety, and operational trade-offs. Not for application code (use backend/frontend skills), product requirements, or architectural approval (use principal-engineer).
- ▌ Ultrathink Frontend · praxstackTwo-mode frontend architecture skill — Default for concise production-ready UI and ULTRATHINK for exhaustive multi-dimensional analysis. Use when building React/Vue/Svelte components, pages, or interfaces where engineering rigor, intentional minimalism, and library discipline matter. Triggers on "ULTRATHINK", "deep frontend analysis", "architect this UI", "senior frontend review", "accessibility audit", "performance optimize this component", and any frontend task requiring reasoning beyond "make it work". Covers mode routing, the anti-generic design philosophy, UI library discipline (Shadcn/Radix/MUI/Headless UI must be used if present), and the full psychological/technical/accessibility/scalability lens. Not for: design-first greenfield UI (use frontend-pe), generic implementation asks (use the component library), or cross-domain orchestration (use super-mode-core). This is frontend analysis/review depth, not workflow.
- ▌ Apex Autonomous Mode · praxstack bundlePrincipal-engineer-grade autonomous execution mode for any AI coding agent. Calibrates rigor to task size: one primitive cycle for tiny work, 3-phase contract for small, 10-phase for medium/large. Loops until verified. Keep-or-revert on every change. Writes Actionable Side Information on failures. Escalates through a 6-tier Fallback Matrix. Respects 6 Ambiguity Blockers as the only valid pause reasons. Emits binary acceptance criteria per phase and a structured Final Summary at completion. Use on explicit opt-in via the APEX-ON token, /apex or /autonomous slash commands, auto-task wrapper, or the phrase apply APEX after echo-confirmation. Trigger keywords: APEX, autonomous mode, principal engineer mode, rigorous execution, godel primitives, keep-or-revert, loop-until-verified, ambiguity blocker, fallback matrix, ASI, auto-task, apex-on, /apex, /autonomous. Not for conversational exploration or trivial edits.
- ▌ Backend Pe Python Ml · praxstackPrincipal-engineer-grade Python ML backend design, implementation, and review - training pipelines, inference services, feature stores, and MLOps. Covers data quality and leakage, reproducibility, evaluation rigor (offline + online), model monitoring for drift, GPU efficiency, inference batching, and ML-specific failure modes (label leakage, distribution shift, train-serve skew, silent model regressions). Use when designing, building, reviewing, or debugging Python ML services, training pipelines, or MLOps systems. Trigger keywords - ML pipeline, model training, model serving, inference service, MLOps, PyTorch production, feature store, model registry, MLflow, data drift, model evaluation, train-serve skew, label leakage, GPU inference, batch scoring, model rollout. Not for generic Python backend work (use backend-pe-python).
- ▌ QA Security Engineer · praxstack bundleQuality assurance plus security engineering for software products. Use when designing test strategy, writing test plans, reviewing code for security, running SAST/DAST, doing penetration tests, managing vulnerabilities, validating compliance (GDPR/SOC2/PCI/HIPAA), responding to incidents, or hardening APIs. Covers test pyramid, unit/integration/E2E, performance/load testing, OWASP Top 10, authentication/authorization review, encryption, secrets hygiene, logging/monitoring, and post-incident forensics. Keywords: QA, testing, test automation, security, SAST, DAST, penetration test, pentest, OWASP, vulnerability, CVE, CVSS, GDPR, SOC2, PCI, HIPAA, compliance, incident response, Cypress, Playwright, k6, Burp, ZAP, Semgrep, Snyk.
- ▌ Ultra Reasoning Operator · praxstack bundleScope-calibrated ultra-rigor workflow for hard reasoning, high-risk code changes, architecture decisions, debugging with multiple plausible root causes, security-sensitive work, and user requests like "ultra reasoning", "think harder", "verify everything", "adversarial review", "war room", "deep check", "paranoid verifier", or "no hallucinations". Use to force evidence-first planning, assumption tracking, hypothesis falsification, adversarial self-review, verification gates, and clear uncertainty without overloading trivial tasks.
- ▌ Backend Pe Javascript · praxstackPrincipal-engineer-grade JavaScript (non-TypeScript) backend design, implementation, and review. Covers Node 20+ LTS / Bun, modern ESM, runtime validation (Zod/Ajv), JSDoc types, Fastify/Hono/Express, Prisma/Drizzle, and JavaScript-specific failure modes (untyped boundaries, prototype pollution, async leaks, event-loop blocking). Use when designing, building, reviewing, refactoring, hardening, or debugging plain JavaScript backend services where adopting TypeScript is not an option. Trigger keywords - JavaScript backend, Node.js service, Fastify, Hono, ESM, Bun JavaScript, JSDoc types, Zod validation, Ajv, plain JS. Not for TypeScript code (use backend-pe-typescript), Node runtime internals (use backend-pe-nodejs), or frontend work.
- ▌ Backend Pe Typescript · praxstackPrincipal-engineer-grade TypeScript backend design, implementation, and review. Covers strict tsconfig, Zod schemas, Fastify/NestJS/tRPC/Hono, Prisma/Drizzle, ESM, Bun/Node 20 LTS runtimes, and TypeScript-specific failure modes (any leakage, narrow-type erosion, module resolution). Use when designing, building, reviewing, refactoring, hardening, or debugging TypeScript services and APIs. Trigger keywords - TypeScript backend, tsconfig strict, Zod, Fastify, NestJS, tRPC, Hono, Prisma, Drizzle, Bun backend, Node TypeScript, TS review, TS performance, type safety review. Not for TS frontend work, pure Node runtime internals (use backend-pe-nodejs), or plain JavaScript (use backend-pe-javascript).
- ▌ Autonomous Orchestrion · praxstack bundleHost-neutral autonomous software work protocol. Use this when a human gives any non-trivial task and expects the agent to own discovery, planning, council review, execution, verification, documentation, and handoff without constant permission requests. Coordinates Superpowers, gstack, Matt Pocock skills, llm-council-plus, MCPs, local tools, and fallback reasoning across Claude Code, Codex, OpenCode, Hermes, OpenClaw, Cline, KiloCode, Antigravity-style IDE agents, Cursor, Windsurf, Aider, Augment, Gemini CLI, Copilot-like agents, or unknown hosts.
- ▌ Frontend Uiux Designer · praxstack bundleFrontend engineering plus UI/UX design for production interfaces. Use when building, designing, or reviewing web UIs, components, design systems, accessibility, responsive layouts, or visual hierarchy. Covers aesthetic direction, typography, color, motion, interaction states, WCAG compliance, and framework selection (React/Vue/Svelte, Tailwind/CSS-in-JS, Framer Motion/GSAP). Keywords: UI, UX, frontend, design, component, accessibility, a11y, WCAG, responsive, typography, color palette, motion, animation, design system, design tokens, Figma handoff, Core Web Vitals, visual design, interaction design. Not for: greenfield design-led implementation (use frontend-pe), pure aesthetic taste review (use frontend-design-excellence), or super-mode orchestration (use frontend-excellence-standards). This is the cross-functional UI/UX role in constellation-team workflows.
- ▌ Professor Alex Interview · praxstack bundleFAANG and HFT interview mentor with a Principal Engineer + quantitative analytics background. Use when preparing for coding, system design, behavioral, or quantitative finance interviews at Google, Meta, Amazon, Apple, Microsoft, Netflix, Uber, Citadel, Two Sigma, Jump Trading, Tower Research, DRW, Hudson River Trading, or Virtu Financial. Defaults to guided-discovery skill-building (5 levels: clarifying questions — solution direction — methodological hints — implementation guidance — complete solution) with anti-gaming safeguards, and switches to full Solution Mode only on explicit command or verified time pressure. Covers DSA, system design, low-latency C++, concurrency, probability, statistics, derivatives pricing, portfolio theory, market microstructure, and behavioral STAR-framework prep. Triggers: 'interview prep', 'mock interview', 'FAANG prep', 'HFT prep', 'Professor Alex', 'SOLUTION:', 'GUIDE:', 'TIMELINE:'.
- ▌ Frontend Design Excellence · praxstackCreate distinctive, production-grade frontend interfaces that reject generic AI aesthetics. Use when building a component, page, landing, marketing site, portfolio, or any UI where visual distinctiveness matters. Triggers on "design a UI", "build a landing page", "make this look better", "avoid AI slop", "distinctive design", "bespoke aesthetic", "visual identity". Covers aesthetic commitment, typography discipline, bold color palettes, purposeful motion, asymmetric layout, and atmospheric backgrounds. Not for: pure layout fixes, component library wrapper work, tasks that explicitly require template-matching, engineering workflow (use frontend-pe), cross-functional role work (use frontend-uiux-designer), or super-mode orchestration (use frontend-excellence-standards). This is aesthetic commitment discipline, not process.
- ▌ Backend System Design Expert · praxstack bundleSenior backend and system design expertise for API contracts, database architecture, microservice boundaries, distributed systems, scalability, caching, and messaging. Use when designing or reviewing backend systems, picking between REST/GraphQL/gRPC, modeling schemas, choosing consistency models, designing sharding or partitioning, selecting caching strategies, or architecting event-driven flows. Focuses on decision trees and trade-offs, not language-specific implementation. Not for frontend work, deployment/SRE (use devops-sre-engineer), or product discovery.
- ▌ Frontend Excellence Standards · praxstackPrincipal-engineer standards reference for frontend UI, aesthetics, accessibility, and performance. Use when super-mode-core loads this for frontend-heavy work, or when a skill needs the canonical frontend discipline without owning the rules. Triggers on "build a UI", "design a page", "accessibility audit", "improve frontend performance", "choose typography", "design tokens", "component library discipline", "motion design", "WCAG". Thin dispatch skill — the actual rules live in the canonical frontend-pe/references/design-rules.md; this skill wraps them with a quality-gate checklist for super-mode orchestration. Not for: standalone user invocation (use frontend-pe, frontend-uiux-designer, or ultrathink-frontend depending on scope). This is an internal domain reference loaded by super-mode-core.
- ▌ Security Compliance Standards · praxstackPrincipal-engineer standards for security, privacy, and compliance across the application stack. Use when designing or reviewing authentication, authorization, secret handling, input validation, data protection, audit logging, threat modeling, or compliance-bounded systems. Triggers on "threat model", "auth design", "OAuth", "OIDC", "secrets management", "input validation", "SAST", "DAST", "OWASP", "data retention", "privacy review", "PII handling", "audit log", "compliance". Covers threat modeling, least privilege, authn/authz patterns, secret management, encryption in transit and at rest, vulnerability management, privacy and data minimization, and audit logging. Loaded by super-mode-core for security-critical work.
- ▌ Backend Principle Eng Cpp Pro Max · praxstack bundlePrincipal backend engineering intelligence for C++ systems and performance-critical services. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale backend code and architectures. Focus: correctness, memory safety, latency, reliability, observability, scalability, operability.
- ▌ Backend Architecture Standards · praxstackPrincipal-engineer standards for backend services, APIs, data modeling, distributed systems, and reliability. Use when building or reviewing REST/GraphQL/gRPC APIs, database schemas, service boundaries, caching strategies, messaging, observability, or scaling patterns. Triggers on "design an API", "database schema", "service architecture", "distributed system", "caching strategy", "rate limit", "reliability pattern", "migration plan", "message queue", "SLI/SLO", and backend production reviews. Covers API disciplines, data modeling, scaling patterns, reliability patterns, DevOps and infra, data storage, observability, and performance. Loaded by super-mode-core for backend-heavy work.
- ▌ Backend Principle Eng Java Pro Max · praxstack bundlePrincipal backend engineering intelligence for Java services and distributed systems. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale backend code and architectures. Focus: correctness, reliability, performance, security, observability, scalability, operability, cost.
- ▌ Coding Agent Leadership Principles · praxstack bundleSet the operating floor for non-trivial coding, debugging, refactoring, and infrastructure work: own outcomes, investigate mechanisms, preserve user work, minimize blast radius, verify against reality, surface every defect, and distinguish reversible execution from irreversible actions that require approval.