Ar9av

Ingest Claude Code conversation/session history into Obsidian as distilled knowledge. Use for importing or mining past Claude sessions, .claude data, project/session history, or audit logs.

Map the load-bearing files, symbols, callers, and dependencies of an unfamiliar codebase before making changes. Use for architecture orientation, impact analysis, what-would-break questions, or finding callers. Uses CodeGraph when available and a…

Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge. Use for importing or mining ~/.codex sessions, rollout files, indexes, or transcript logs; use wiki-agent for targeted topic-only recall.

Ingest GitHub Copilot CLI/session history into Obsidian as distilled knowledge. Use for importing or mining Copilot history; not for general Copilot help, simple session search, or backup.

Find and add missing cross-references between wiki pages. Use when pages are disconnected or after large ingestion. This modifies pages to add links; use wiki-lint for report-oriented structural auditing.

Run or configure the daily wiki maintenance cycle: check source freshness, refresh the index and hot.md, and manage its scheduled 9 AM launchd/systemd/cron reminder. Use for daily or morning wiki refresh or scheduler setup and verification.

Configure Obsidian graph colors by tag, folder, category, or visibility by updating .obsidian/graph.json. Use for graph colorization; preserve other graph settings and back up before changes.

Ingest Hermes agent history into Obsidian as distilled knowledge. Use for importing or mining ~/.hermes sessions, memories, or logs; use wiki-agent for targeted topic-only cross-agent recall.

Generates Zelda/Hyper-Light-style top-down action adventures with zero image assets — every sprite, prop, tile edge and effect is rasterized in code as 3-colors-plus-outline pixel art. Multi-level campaigns across distinct biomes (coast, jungle, snow,…

Generates playable isometric city-builder "games" — zone residential/commercial/industrial land, draw roads, watch buildings grow (or abandon) as demand and land value change, with cars routing over whatever road network the player actually built. Use when…

Generates living isometric pixel-art world "games" — ambient explorable cities/villages with a movable player, wandering NPCs with speech bubbles, ambient traffic, and district-based world layout. No win condition; the world itself is the product. Use when…

Generates genre-appropriate sound effects and looping background music for a generated game. When ELEVENLABS_API_KEY is set, calls the ElevenLabs text-to-sound-effects API for real MP3 audio; otherwise falls back to Web Audio oscillator synthesis. Produces…

Writes the gameplay code for a Phaser 3 game (src/scenes/Game.js plus optional helpers). Reads the GDD, levels, and sprite/tile manifest; produces ES module code that consumes assets by name (never magic numbers). Use after sprite-artist and tile-artist have…

Orchestrator skill that turns a one-line description into a runnable Phaser 3 game. Coordinates eight sub-skills (game-designer, world-architect, sprite-artist, tile-artist, bg-artist, codesmith, playtester, refiner) into a deterministic-where-possible,…

Static analysis of Game.js that cross-references every animation key and texture key against manifest.json. Catches "Animation not found" and "Texture not found" bugs before the browser is opened. Run after codesmith, before playtester.

Checks 5 mobile-compatibility properties in the generated game (roundPixels, image-rendering CSS, devicePixelRatio, touch input, AudioContext unlock) and patches any missing items. Run after codesmith, before playtester.

Render a music-only, hand-drawn cartoon launch film (about 45 s, square 1080, 30 fps) for an X, LinkedIn or Threads post. It has boiling ink linework, a mascot with on-model poses, squash and stretch, a paper-and-grass world and a synthesised 120 BPM score…

Start here for any framesmith request. framesmith is a library of motion-graphics, video and visual-design skills for AI agents; each template is driven by a brief and renders deterministically with Python and ffmpeg. Use this skill to pick the right template…

Render a music-only abstract title film (about 80 s, 16:9, 24 fps) in which a small glowing orb travels through a chain of worlds and lands on the logo. The worlds are a dark glitch data field, a UI card in a lit chamber, wireframes that fill into a web page,…

Render a narrated explainer video (about 45–90 s, 16:9) animated from layers. It uses a consistent cast of characters generated with gpt-image-2 on transparent backgrounds, with every pose kept on-model by reference-guided edits, plus transparent props, empty…

Render a narrated archive-to-product launch film (about 60–90 s, 16:9). A dark documentary cold open plays single words synced to the voice over a falling dotted chart, archival engravings made with gpt-image-2, cutaway line drawings whose interiors flood…

Render a music-driven SaaS story film (about 60–90 s, 16:9) in the blue-light style. It opens with typewriter captions, a caret and a selection highlight over ghosted UI, then a huge 'Meet' word that collapses into the brand line. The body shows product UI in…

Find, fetch, preview and credit real brand/logo SVG icons from thesvg.org (7,400+ marks, e.g. Claude, OpenAI, Cursor, GitHub Copilot, Stripe, Vercel, AWS, Figma, Docker). It picks the right variant for a light or dark background and renders crisp transparent…

Render a 22-second brutalist / industrial product promo video (spec-sheet motion graphics) for any hardware, device, robot, drone, vehicle or tech product. The video is 9:16 with a signal-colour accent on black and white, and includes ASCII glitch fields,…

Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by…

Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables,…

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that…

Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware…

Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript…

Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level…

Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md…

Run the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 partition + Precision/Recall/F1), Literature Review Quality (6-axis 0-100 with anti-inflation rules), SxS Overall Paper Quality (side-by-side), and SxS…