By NapticStacks
Naptic-owned team skills — UNF wrappers around `gstack`, standalone team skills (e.g. `sprint-recap`), and vendored content-generation skills (`higgsfield-*`).
Produce a Unicode box-drawing ASCII-art visual of a topic — flow, system architecture, agent topology, decision tree, deploy pipeline, before/after comparison, anything explainable as a picture rendered in monospace. Triggers on "ascii visual", "ascii art", "ascii diagram", "draw X", "visualize X", "diagram of X", "show me a picture of X", "make a visual of X". Speech-to-text alias: "a s c i i" (with spaces). NOT for: numeric charts (use a chart), external Slack/PDF deliverables (those have their own skills — sprint-notify, nap-slack, gen-pdf), or requests that explicitly want SVG/Mermaid output.
Generate images/videos via Higgsfield AI. Default: GPT Image 2 for images/design/text, Seedance 2.0 for video, Nano Banana 2/Pro for character/reference image work, Marketing Studio for ads with avatars/products/hooks, settings, plus Soul V2/Cinema/Cast/Location and Kling 3.0. Use when: "generate an image", "make a video", "animate this photo", "image-to-video", "edit/stylize/remix this image", "produce a clip", "create an ad", "make a UGC video", "product demo", "unboxing", "brand video", "presenter video", "import product from URL", "create avatar for ad", or "analyze video virality". Supports image-to-image, image-to-video, references, job/upload IDs, and Marketing Studio. Chain with higgsfield-soul-id for face/identity consistency. Virality Predictor (`brain_activity`) analyzes video virality: hook strength, attention, retention, distraction risk, and creative score. NOT for: Soul Character training (use higgsfield-soul-id), product photoshoots, marketplace listing cards, text/chat/TTS tasks.
Generate marketplace product image cards through Higgsfield: compliant main image, secondary product images, and A+ style content modules. Use when the user asks for marketplace listing images, product detail cards, secondary product images, product infographics, lifestyle listing shots, A+ style content, marketplace image sets, or sales-ready product visuals. Backend owns marketplace compliance references and prompt templates; this skill only routes user intent to the CLI. NOT for generic brand product photography without marketplace/listing context (use higgsfield-product-photoshoot), video generation or UGC ads (use higgsfield-generate), or Soul Character training (use higgsfield-soul-id).
Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2 / gpt_image_2. Entry point for professional brand/product visuals. Use when: "product photo", "studio shot", "lifestyle image", "Pinterest pin", "hero/banner", "carousel", "ad creative", "Meta ads", "virtual try-on", "model wearing", "person holding product", "closeup with hands", "levitating/floating/splash product", "CGI/surreal product", "restyle", "seasonal/aesthetic variation", or any product, brand, or paid-social creative. Modes: product_shot, lifestyle_scene, closeup_product_with_person, moodboard_pin, hero_banner, social_carousel, ad_creative_pack, virtual_model_tryout, conceptual_product, restyle. Backend assembles the final prompt; never freehand it. NOT for: no-product text-to-image (use higgsfield-generate), branded avatar video (use higgsfield-generate Marketing Studio), marketplace listing cards (use higgsfield-marketplace-cards), Soul Character training (use higgsfield-soul-id).
Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation. Use when: "create my Soul", "train my face", "make my digital twin", "build me an avatar", "learn my appearance", "create a character of me", "set up identity for video", "I want my face in generated images". Chain: train Soul (one-time, returns reference_id) → use in higgsfield-generate via `--soul-id <id>` with models like `text2image_soul_v2` or `soul_cinema_studio`. NOT for: one-shot face swaps (use higgsfield-generate with --image), named-character / non-photo avatars (use higgsfield-generate with prompt).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Naptic-owned team skills distributed via the napticstack-plugins Claude Code marketplace. Three flavors live here:
garrytan/gstack skills that add Naptic framing.sprint-recap).higgsfield-* content-generation skills). See THIRD_PARTY_NOTICES.md.UNF (Unified Naptic Framework) wrappers add Naptic-specific framing (org conventions, security posture, phase context) and then defer to the underlying gstack skill they wrap:
naptic-pickup wraps gstack /picking-up-work with UNF phase context (which engagement phase the session belongs to, how to pick the next task in that phase).naptic-review wraps gstack /review with NapticStacks org conventions (review-requested-to maydaycyber, per-org git identity rules, label/project-board hygiene).naptic-cso wraps gstack /cso with Naptic security posture (Bedrock Guardrails, Mayday/Naptic tenant separation, secrets-manager-first credential handling).naptic-phase-04 is a UNF Phase 04 helper (planning / scoping bridge between client discovery and tenant-register).The overlay is thin — wrappers add framing and call the gstack skill underneath; they do not reimplement gstack behavior.
sprint-recap — generate a 3-paragraph plain-English recap (7th-grade reading level) of what shipped in a session. Designed to auto-fire via a Stop hook so non-technical teammates (Alex, Jenn, investors) can read the recap without parsing diffs. Promoted to the team plugin so every Naptic operator gets the same recap discipline.ascii-visual — produce a Unicode box-drawing ASCII-art visual of a topic (flow, system architecture, decision tree, before/after comparison, agent topology, deploy pipeline). Triggers on "ascii visual", "ascii art", "ascii diagram", "draw X", "visualize X", "diagram of X", "show me a picture of X", "a s c i i" (speech-to-text variant). Encodes the visual rules already in use across /sprint-notify + @nap Slack client comms so every Naptic operator produces a consistent aesthetic. NOT for: numeric charts, external Slack/PDF deliverables (those have their own skills — /nap-slack, /gen-pdf), or requests that explicitly want SVG/Mermaid output.naptic-agent-qa — pre-launch stress gate for any Naptic conversational AI agent (FAQ, conversion, winback, support). Drives a synthetic-persona probe matrix at a deployed agent webhook, audits replies against a per-engagement brand-protection contract, runs an adversarial round, triages P0–P3, and emits a branded PDF report with a GO/NO-GO verdict. Methodology is fixed; the brand-protection contract + connection details live in a per-engagement agent-qa.config.yaml. The synthetic-persona design sends no real messages and consumes no client messaging plan. UNF phase 09c (deployment-readiness-audit); also 02d / 11a. Reference implementation: AER Pilates FAQ-agent run 2026-05-22 (37 probes, 0 P0/P1). Triggers on "agent qa", "stress test the agent", "pre-launch gate", "naptic agent qa". NOT for web-UI QA (gstack /qa) or code review (/review).Prerequisite (UNF wrappers): the gstack plugin must be installed first. The overlay assumes gstack skills are already present at ~/.claude/skills/<name>/ and will not function correctly without them.
Skills wrapping an external CLI rather than a gstack skill. Vendored verbatim from upstream (MIT) so every Naptic operator gets the same content-generation toolkit as part of the UNF skill set. Attribution + license: THIRD_PARTY_NOTICES.md.
higgsfield-generate — generate images/videos via Higgsfield AI (GPT Image 2, Seedance, Nano Banana, Soul V2, Kling, Veo, Marketing Studio). Also runs the Virality Predictor (brain_activity) on finished videos. Triggers on "generate an image", "make a video", "animate this photo", "create an ad", "make a UGC video", "analyze video virality".higgsfield-product-photoshoot — brand-quality product images (product shots, lifestyle scenes, hero banners, ad creative packs, virtual try-on). Triggers on "product photo", "studio shot", "ad creative", "Pinterest pin", "hero/banner".higgsfield-marketplace-cards — marketplace listing image sets (compliant main image, secondary product images, A+ content modules). Triggers on "marketplace listing images", "product detail cards", "A+ content".higgsfield-soul-id — train a Soul Character (identity-faithful face model) for consistent image/video generation; chain into higgsfield-generate via --soul-id. Triggers on "create my Soul", "train my face", "make my digital twin".npx claudepluginhub napticstacks/napticstack-skillsCreate branded Typeforms via natural language. Three modes (wizard, spec, sketch) auto-detected from input. Brand-aware (Omertá, Sunkissed pre-seeded).
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Editorial "Web Designer" bundle for Claude Code from Antigravity Awesome Skills.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques