Skill collection
oaustegard/claude-skills agent skills
- skills
- 67
- GitHub stars
- 150
GitHub description: “My collection of Claude skills”
- Stars
- 150 (7 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Oct 2025
- claude
- claude-skill
- claude-skills
Install all skills
npx skills add oaustegard/claude-skillsAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in oaustegard/claude-skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Builds interactive Vega-Lite charts from uploaded data: analyzes the fields, picks five to ten fitting chart types, and produces a React artifact with the data embedded inline. | oaustegard/ | 150 | — | ~2.1k | Automated safety check: Pass | MIT | yesterday |
| 2 | Builds self-contained single-file HTML pages such as reports, decks, postmortems, flowcharts and prototypes from a small spec using a bundled Python composer and templates. | oaustegard/ | 150 | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 3 | Routes, triages, flags and rates a piece of text with a probability for every option: which department or queue a ticket goes to, which intent a message expresses, whether a yes/no condition holds… | oaustegard/ | 150 | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 4 | Rewrites model-sounding prose into plain technical writing and checks that every claim survives, for PR text, docs, commit messages and similar drafts. | oaustegard/ | 150 | — | ~5.2k | Automated safety check: Pass | MIT | yesterday |
| 5 | Guides building standards-based Preact apps with native-first choices, HTM syntax, import maps and vendored ESM, from single-file demos to larger builds. | oaustegard/ | 150 | — | ~4.6k | Automated safety check: Pass | MIT | yesterday |
| 6 | Deprecated sampler that captures short windows of the Bluesky firehose, clusters trending terms and builds an HTML report; replaced by the browsing-bluesky skill. | oaustegard/ | 150 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 7 | Has a fresh-context adversary attack a blog post, recommendation, analysis brief or piece of code before you ship it, using a profile suited to that kind of artifact. | oaustegard/ | 150 | — | ~3.4k | Automated safety check: Pass | MIT | yesterday |
| 8 | Control Spotify playback and manage playlists via MCP server. | oaustegard/ | 150 | — | ~2.8k | Automated safety check: Notes | MIT | yesterday |
| 9 | Creates production-ready MCP servers using FastMCP v2. An agent skill from oaustegard/claude-skills. | oaustegard/ | 150 | — | ~1.3k | Automated safety check: Pass | MIT | yesterday |
| 10 | Exploratory data analysis. An agent skill from oaustegard/claude-skills. | oaustegard/ | 150 | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 11 | 11.Flowing Runs a multi-step procedure as a Python DAG, so ordering, branching and retries are enforced by the runner rather than described in prose a model can generate past. | oaustegard/ | 150 | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 12 | Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). | oaustegard/ | 150 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 13 | 13.Gating Build and audit deterministic verification gates — a check that blocks a pipeline and can be shown to go red. | oaustegard/ | 150 | — | ~3.1k | Automated safety check: Pass | MIT | yesterday |
| 14 | Invokes Google Gemini models for structured outputs, image generation, text-to-speech narration, multi-modal tasks, and Google-specific features. | oaustegard/ | 150 | — | ~4.1k | Automated safety check: Pass | MIT | yesterday |
| 15 | Enables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments. | oaustegard/ | 150 | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 16 | Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. | oaustegard/ | 150 | — | ~4.8k | Automated safety check: Pass | MIT | yesterday |
| 17 | Skill-aware orchestration with context routing. An agent skill from oaustegard/claude-skills. | oaustegard/ | 150 | — | ~1.9k | Automated safety check: Pass | MIT | yesterday |
| 18 | Query, filter, and transform Markdown structurally with mq — a jq-like CLI for Markdown. | oaustegard/ | 150 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 19 | Securely manages API credentials for multiple providers (Anthropic Claude, Google Gemini, GitHub). | oaustegard/ | 150 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 20 | Renders a Bluesky post as an anonymised screenshot so its words can be criticised without a link back to whoever wrote them. | oaustegard/ | 150 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 21 | Pre-change blast-radius report for a symbol or file. An agent skill from oaustegard/claude-skills. | oaustegard/ | 150 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 22 | 22.Atprotoing Read Bluesky/ATProto without depending on Bluesky's AppView — interactions on a user's posts, thread replies, any repo's records, network-wide backlinks across every lexicon, an account's handle and… | oaustegard/ | 150 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 23 | 23.Bm25 Ranked content search over a text corpus you point it at, using BM25 (via xhluca/bm25s). | oaustegard/ | 150 | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 24 | Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and lists, analyze and categorize accounts. | oaustegard/ | 150 | — | ~3.3k | Automated safety check: Pass | MIT | yesterday |
| 25 | Generate progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. | oaustegard/ | 150 | — | ~994 | Automated safety check: Pass | MIT | yesterday |
| 26 | Analyze and categorize Bluesky accounts by topic using keyword extraction. | oaustegard/ | 150 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 27 | 27.Check Tools Validates development tool installations across Python, Node.js, Java, Go, Rust, C/C++, Git, and system utilities. | oaustegard/ | 150 | — | ~641 | Automated safety check: Pass | MIT | yesterday |
| 28 | 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. | oaustegard/ | 150 | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 29 | Authors and caches a personalized container environment from a Dockerfile- like spec, as a single layer or as a composition of independently cached layers. | oaustegard/ | 150 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 30 | Convert a file from one format to another inside the container — documents, images, audio, video. | oaustegard/ | 150 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 31 | 31.Creating Kb 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). | oaustegard/ | 150 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 32 | Create video from prompts by overseeing multi-clip AI generation end to end: write a shot list, generate each scene with Gemini Omni Flash (via the Cloudflare AI Gateway), review the results, and… | oaustegard/ | 150 | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 33 | Find tests that enumerate a domain by copying it, and declare the invariants a codebase depends on. | oaustegard/ | 150 | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 34 | Draws images, PDF/SVG vector files and animation frames with pycairo, and supplies what cairo lacks: shaped text for Arabic, Indic and other scripts, text along curves, blur/glow/drop shadows, path… | oaustegard/ | 150 | — | ~1.9k | Automated safety check: Pass | MIT | yesterday |
| 35 | 35.Featuring Generate hierarchical FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. | oaustegard/ | 150 | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 36 | Discover and load skills on demand from /mnt/skills/user/. An agent skill from oaustegard/claude-skills. | oaustegard/ | 150 | — | ~561 | Automated safety check: Pass | MIT | yesterday |
| 37 | Assign items to a CLOSED label vocabulary that is too large to put in a prompt — product taxonomies, category hierarchies, tag vocabularies, routing tables, ICD/SIC-style code lists. | oaustegard/ | 150 | — | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 38 | 38.Image To SVG Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. | oaustegard/ | 150 | — | ~5k | Automated safety check: Pass | MIT | yesterday |
| 39 | Discovers and indexes Python code in skills, enabling cross-skill imports. | oaustegard/ | 150 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 40 | Generate guardrailed UI from natural language. An agent skill from oaustegard/claude-skills. | oaustegard/ | 150 | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 41 | Listen to generated music by measuring it and by reading it as sheet music: render Strudel code or record a Web Audio page through the real engine in headless Chromium, then read spectrograms, pYIN… | oaustegard/ | 150 | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 42 | Generate navigable semantic maps from PDF documents. An agent skill from oaustegard/claude-skills. | oaustegard/ | 150 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 43 | Generate behavioral/feature documentation for web apps using code-first analysis. | oaustegard/ | 150 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 44 | 44.Muninn Boot Puts oaustegard/muninn-utilities on the container Python path — runs scripts/boot.sh, which shallow-clones the repo (codeload tarball as fallback) and writes the .pth. | oaustegard/ | 150 | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 45 | 45.Ocring Pdfs Adds a searchable text layer to a scanned PDF with ocrmypdf. | oaustegard/ | 150 | — | ~1.2k | Automated safety check: Pass | MIT | yesterday |
| 46 | 46.Opening PRs Open a GitHub PR via API as a flowing graph — branch + push + createpr + mergeable poll, with structural protection against pushing to main/master/etc. | oaustegard/ | 150 | — | ~1.3k | Automated safety check: Notes | MIT | yesterday |
| 47 | Interpret video content visually by sampling frames into timestamped contact sheets that can be read as images. | oaustegard/ | 150 | — | ~2.3k | Automated safety check: Pass | MIT | yesterday |
| 48 | 48.Python Lsp Semantic Python code queries via a stdio LSP client driving pyright-langserver. | oaustegard/ | 150 | — | ~1.9k | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill in oaustegard/claude-skills?
Vega-Lite Interactive Charts from oaustegard/claude-skills ranks first of the 67 skills in oaustegard/claude-skills listed here, with the highest score: its repository has 150 GitHub stars, its SKILL.md loads about 2.1k tokens and it passes the automated safety check with no findings. Next come Single-File HTML Composer and Deciding With Confidence.
Are the skills in oaustegard/claude-skills official?
None yet. All 67 skills in oaustegard/claude-skills listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from oaustegard/claude-skills?
Run npx skills add oaustegard/claude-skills in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.