Channel the Muninn persona — a raven-voiced AI assistant with accumulated experience on AI research, agent architectures, RAG, memory systems, and craft methodology.
Find code by regex pattern or natural language concept in any codebase. Auto-routes between n-gram indexed regex search (2-20x faster than ripgrep) and TF-IDF semantic search.
Cross-context adversarial review for deliverables before shipping. Use when producing blog posts, technical recommendations, analysis briefs, code, or any artifact where accuracy…
Sort grocery lists by aisle order using store aisle sign photos. Build aisle maps from uploaded images, match items to aisles, and output optimized shopping routes.
Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference).
Systematic research methodology for building comprehensive, current knowledge on any topic. Requires web_search tool.
Open a GitHub PR via API as a flowing graph — branch + push + create_pr + mergeable poll, with structural protection against pushing to main/master/etc.
Ranked content search over any text corpus using BM25 (via xhluca/bm25s). Corpus-agnostic: works on cloned repos, project knowledge stores, uploaded files/archives, and any local…
Augmented vision tools for analyzing images beyond native visual capabilities. Use when tasked with describing images in detail, reproducing images as SVGs, identifying subtle…
Builds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained `.skill` bundle (BM25 index + bundled searcher + query protocol).
Guide for designing effective memory architectures in Letta agents. Use when users need help structuring memory blocks, choosing between memory types, or optimizing memory…
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller mod — from…
Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or…
Install and drive Google's Antigravity CLI (`agy`) as a non-interactive sub-agent. Use when orchestrating agy, running Antigravity agents from a script or sandbox, delegating a…
Creates browser-executable JavaScript bookmarklets with strict formatting requirements. Use when users mention bookmarklets, browser utilities, dragging code to bookmarks bar, or…
Image processing toolkit awareness. Use when: user uploads images for manipulation, requests format conversion, batch processing, compositing, resizing, optimization, analysis,…
Portrait Mode" for SVGs — foveated vectorization with 4-zone selective detail. Combines Claude vision annotations, MediaPipe segmentation/landmarks, and optional saliency.
Write effective instructions for Claude: project instructions, standalone prompts, and skill content.
GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when accessing private repos/writing files via API.
Interpret video content visually by sampling frames into timestamped contact sheets that can be read as images.
Generate navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all…
Create video from prompts by overseeing multi-clip AI generation end to end: write a shot list, generate each scene with Google Veo (via the Cloudflare AI Gateway), review the…
Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into…
Generate progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. Use when setting up projects referencing external documentation, creat — from…
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller mod — from…
Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterprise AI engineering lens.
Memory operations for Muninn (recall, remember, supersede, config). The canonical implementation has moved to oaustegard/muninn-utilities/remembering/.
Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK — from oaustegard/fork-letta-ai-skills
Audio and video processing with ffmpeg. Use when: user asks to convert, trim, merge, compress, or transcode video or audio files; extract audio from video; create GIFs or animated…
AST-powered code navigation via tree-sitter. Auto-scans codebases and provides progressive-disclosure tree views with symbol search, source retrieval, and reference finding.
DEPRECATED - Use browsing-bluesky skill instead. Sample and analyze Bluesky firehose to identify trending topics and content clusters.
Build and audit deterministic verification gates — checks that block a pipeline and can be shown to go red.
Execute programs on a compiled transformer stack machine where every instruction fetch and memory read is a parabolic attention head.
Reads the visual content of slides, pages, and images the way a human would, not just their embedded text.
Select the right Python charting library (seaborn, matplotlib, graphviz) and produce publication-quality static visualizations.
Debug Electron app UI, renderer, console, network, and runtime issues using chrome-devtools MCP attached to an Electron remote debugging port and playwright MCP for deterministic…
Decide which model (Haiku/Sonnet/Opus) and effort level each subagent gets, when to cascade cheap-first behind a verifier, and how to run improvement loops safely…
Boot (or recover a degraded boot of) the Muninn FUSE workspace — fetch skills + muninn-utilities, mount the /mnt/muninn memory corpus, and load Muninn identity.
Generate behavioral/feature documentation for web apps using code-first analysis. Reads source code and _MAP.md files to produce _FEATURES.md, with optional visual verifi — from…
Guidance for asking clarifying questions when user requests are ambiguous, have multiple valid approaches, or require critical decisions.
Maintain a structured task list for the current session. Use proactively when a request requires 3+ distinct steps, the user provides multiple items, or complex work benefits from…
Pre-change blast-radius report for a symbol or file. Walks tree-sitting references, augments with a plain-text scan over non-parsed files (configs, plain docs), and clusters…
Develop and run Mojo code in Claude.ai containers. Handles installation, compilation, and execution. Use when writing Mojo code, benchmarking Mojo vs Python, or when user mentions…
Generates WAFFLES Declarations for social media posts — preemptive lists of what a post does NOT say.
Meta-skill for recognizing learnings, validating improvements, and contributing back to the collective knowledge base.
Convert a file from one format to another inside the container — documents, images, audio, video. Routes to the right engine (pandoc, LibreOffice, ImageMagick, ffmpeg) by format…
Generate and maintain lat.md/ knowledge graphs with bidirectional source code anchoring. Docs link to code via [[src/file#symbol]] wiki links; code links back to docs via @lat:…
Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and…
Removes LLM prose tics from drafts — staged reveals, "it's not X, it's Y", significance tags, abstraction agency, coy headers, fragment cadence, plus the flatter slop patterns…
Generate navigable code maps for unfamiliar codebases. Extracts exports/imports via AST (tree-sitter) to create _MAP.md files per directory showing classes, functions, me — from…
Close a GitHub issue with a synthesis comment as a flowing graph — validate the synthesis, post the closing comment, close, then run a pluggable callback (e.g.
Multi-conversation methodology for iterative stateful work with context accumulation. Use when users request work that spans multiple sessions (research, debugging, refactoring,…
Preprocesses photographed sheets of many business cards — slicing each into overlapping high-resolution tiles and de-glaring them with container tooling (OpenCV/ImageMagick) —…
In-process semantic search over text files or in-memory strings, using Gemini embeddings via the CF AI Gateway.
Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting.
Read Bluesky/ATProto without depending on Bluesky's AppView — interactions on a user's posts, thread replies, any repo's records, and layer-by-layer outage diagnosis.
REQUIRED for all skill development. Automatically version control every skill file modification for rollback/comparison.
Composes single-file HTML artifacts (PR review writeups, status reports, incident postmortems, slide decks, design systems, prototypes, flowcharts, module maps, feature…
Query, filter, and transform Markdown structurally with mq — a jq-like CLI for Markdown. Use to extract headings/sections/code-blocks/links from .md files, build a table of…
Turn a short video into a narrated comic strip. Use when the user uploads a video (.mov/.mp4/etc.) and asks to make a comic from it, narrate it, draw it, Attenborough it,…