ai-image-realism

Turn final manuscript or course text into ordered chapter audio with one narrator, a representative sample, clear pricing, and focused refinements.

1 skill

Turn a casual selfie into a studio-quality professional headshot with new backgrounds, professional attire, and studio lighting for LinkedIn, resume, company website, and social media.

1 skill

Generate, compose, and edit product images, brand visuals, posters, social graphics, illustrations, and photo variations.

1 skill

Turn a brand name, industry, or reference image into a professional AI logo, brand mark, or app icon with multi-concept exploration, precise brand colors, and scalable composition.

1 skill

Create reviewable multilingual voice-over audio from scripts for each language, with deliberate casting, pronunciation and timing pilots, and delivery organized by market and segment.

1 skill

Turn a photo into anime, manga, comic, cartoon, watercolor, clay, or 3D character art while the subject stays recognisable, and repeat the same look across a whole set.

1 skill

Cortex — persistent memory and cognitive profiling for Claude Code (renamed from the 'cortex' plugin in v4.15.0 to match the PyPI/MCP-registry identity hypermnesia-mcp) — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. These mechanisms are implemented and inspectable; committed ablations do not establish a retrieval gain from all 36 mechanisms. 57 MCP tools (60 with the optional ai-architect-mcp-codebase + ai-architect-mcp-spec integrations) with enriched schemas (visualization extracted to the standalone Hypermnesia MCP Viz server). PostgreSQL + pgvector in CLI mode; automatic SQLite fallback in Cowork/sandboxed mode. v3.17.0 — autonomous per-project wiki: SessionStart auto-spawns a 6-hour consolidate cycle; a headless `claude -p` worker drains the curation-gap queue, calls codebase-intelligence MCP tools to ground each section in the real call graph, and authors missing anchor pages (architecture / services / api / data-flow / operations / decisions / PRD) per project from the source tree. 15 canonical scopes × 13 file sections; per-project dashboards under `wiki/_dashboards/`. Mermaid diagrams have a 🔍 lens with zoom + pan. Workflow graph with caller-qualified CALLS chains rendering full method-to-method dependencies (native tree-sitter, no AP required). Side panel humanized for non-technical users. Ingests codebase analysis (ai-architect-mcp-codebase) and PRDs (ai-architect-mcp-spec) into wiki + memory + knowledge graph. Docker image available.

13 skills · 3 commands · 1 MCP server · hooks

Divi 5 development assistant: validates CSS compatibility, generates Divi-ready code, scaffolds page sections, audits project CSS health, checks accessibility, diagnoses symptoms, audits performance for Core Web Vitals, and learns from errors. Includes /setup (auto-detecting config bootstrap) and /selector (instant selector lookup). Updated for Divi 5.13 with the 5.12 AI Agents + Filters, 5.13 LayoutStyle/preset/Free-Form CSS fixes, the 5.6-5.11 new modules (Timeline, Breadcrumbs, SVG, Table of Contents, Instagram Feed, Tooltip, Post Filter, Charts, Gravity Forms, Imagely Gallery, Payment Button), 5.9 Variable Fonts + CSS Grid Editor, 5.7 Gradient Variables + text effects, 5.10 Loop Filters, 5.5 Aspect Ratio + Framing, 5.4 Variable Generators, 5.3 pseudo-class editing + Contact Form 7 Styler + Nested Option Presets, plus Composable Settings, Canvas system, Loop Builder.

3 skills · 10 commands · 5 agents · hooks

Local Slop or Not tools for Claude, Codex, Hermes Agent, OpenClaw, and other AI agents.

2 skills

Publication-quality figures plugin. Seven skills + one QA agent: scientific-figure (svgutils composer with font validation; Inkscape/cairosvg export); transparent-icons (flat scientific icons via Codex CLI, OpenAI Images API, or explicit Atlas Cloud); svg-figure (schematic authoring with consistency guidelines plus an editor-handoff reference and editor_prep.py pass for Illustrator/Affinity-editable masters); svg-primitives (mm-precise SVG builder in Python: auto-fit boxes, tangent-correct arrows on straight/cubic/orthogonal routes, multi-waypoint paths, brackets/annotations/groups, layered z-order); ai-full-figure (AI substrate + programmatic label/arrow/scale-bar overlay); plot-styling (library decision tree + SciencePlots recipes for Nature/IEEE/Science/Cell/PNAS/APS); figure-qa agent (type-dispatching QA across SVG/raster/plot-script with strict programmatic-vs-VLM separation).

8 skills · 1 agent

Add badges (the small status labels shown at the top of a README) to a repository, README, or document. Includes authorship badges that disclose how content was created (fully human-written, written with AI assistance, or AI-generated), a badge for crediting projects that follow SLIM best practices, and more. Badges are generated as shields.io images.

18 skills

Evaluate AI models for a real job, starting from start-eval: define the objective and workload, draw candidates from the live OpenRouter catalogue, and run wide and shallow (many models, about two outputs each). Covers in-repo and agent-run eval spaces, framework CLIs, image, RAG, agent, speech and regression evals, private annotation and human feedback Spaces, and findings through to articles.