adhishthite

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Apply before sending any longer user-facing prose: blog posts, LinkedIn posts, emails, documentation, social media drafts. Strips AI writing patterns and rewrites in Adhish's voice. Trigger on output > ~150 words that the user will read directly.

Web reading and searching via Jina AI APIs. Fetch clean markdown from URLs (r.jina.ai), web search (s.jina.ai), or deep multi-step research (DeepSearch).

Distance, routing, and geocoding using free APIs (OSRM + Nominatim/OSM). Use when the user asks about distance between places, travel time, directions, how far something is, or needs to convert a place name to coordinates. No API key required. Requires python3 (3.6+).

Use this skill when the user asks to look up library documentation, check API references, query MCP servers, or needs up-to-date docs for any programming library or framework. Triggers on: "check the docs for X", "how does X API work", "what's the latest X syntax", "look up X documentation", "find me examples for X", "how do I use X in version Y", or any request for current library/framework reference material. Uses Context7 MCP server for live, version-accurate documentation.

Indian language AI via Sarvam AI APIs. Text-to-Speech (TTS) with 38 voices in 22+ Indian languages using Bulbul v3, Speech-to-Text (STT) with Saaras v3. Use when the user asks to generate speech in Indian languages, transcribe Indian language audio, or needs Indic TTS/STT.

Use when adding, editing, or removing anything on the portfolio résumé/profile — a new job, a promotion, a title or location change, end-dating a role you left, a certification, an award, or an ambassador/community role. It all lives in src/data/resume.tsx. Trigger whenever the user says "I started a new job", "add my new role at X", "update my experience", "I got promoted", "I left Company Y", "add this certification", "add X to my resume/CV/website", or similar — even if they don't name the file.

Use when reviewing, editing, de-slopping, or "making more human" any blog post or prose copy (content/*.mdx and other Markdown/MDX). Removes AI-writing tells — the "X. Not Y." antithesis cadence, section-ending aphorisms, clichés, forced motifs, marketing fluff — while preserving all code, frontmatter, links, and facts byte-for-byte. Trigger whenever the user says copy "reads like AI", "sounds like slop", is "too polished", wants it "to sound human", mentions a Codex/AI-written draft, or asks to review, rewrite, tighten, or clean up writing — even if they never say the word "slop".

Use when creating, scaffolding, drafting, or starting a new blog post or article for this portfolio (content/*.mdx). Sets up correct frontmatter, the public/blog/<slug>/ image directory, OG image sizing, the content-pipeline conventions (GFM, Shiki highlighting, Mermaid), and applies the human writing voice from the first draft. Trigger whenever the user says "new post", "write a blog about", "add an article", "draft a post", "start a writeup", or similar — even if they don't mention frontmatter or files.

Cut MenuStat releases from the repository root, including docs, signed/notarized app packaging, DMG and zip assets, GitHub release upload, and verification.

Build, refine, and verify the MenuStat website under website/, including product-grounded copy, responsive checks, theme persistence, external links, and Apple Silicon download messaging.

Web reading and searching via Jina AI APIs. Fetch clean markdown from URLs (r.jina.ai), web search (s.jina.ai), or deep multi-step research (DeepSearch).

Convert DVD-Video rips and VIDEO_TS folders into validated MP4 or MKV exports. Use when Codex needs to scan backup folders for DVD exports, inspect VOB/IFO/BUP structures, create a single watchable H.265 or H.264 export, preserve originals read-only, handle split VOB/DVD timestamp quirks, convert interview/speech audio to centered dual-mono, boost audio to an acceptable level, report progress/ETA, and validate duration, codec, size, and audio balance.