oaustegard

86 mods in 9 plugins, 2 repositories, 164 stars between them.

opening-prs

49

oaustegard/claude-skills

Skill Claude CodeCodex

Open a GitHub PR via API as a flowing graph — branch + push + createpr + mergeable poll, with structural protection against pushing to main/master/etc. Use when a Claude Code or Claude.ai container needs to land changes on GitHub via the API (no git CLI required) and the prose "create branch, push, open PR, wait for…

not rated 153 +3 yesterday A SkillSpector: warn 86 tokens original MIT

optimizing-skills

50

oaustegard/claude-skills

Skill Claude CodeCodex needs its repo

Disciplined, validation-gated revision of an EXISTING skill so each edit is a measured improvement rather than a guess. Use when editing, revising, or tuning a skill that already exists and there is evidence it underperforms (observed failures, drift, complaints) — invoke by name, or have versioning-skills /…

not rated 153 +3 changed 1mo ago A SkillSpector: pass 104 tokens original MIT

oaustegard/claude-skills

Skill Claude CodeCodex

DEPRECATED, renamed to orchestrating-chat-agents. Kept so existing imports of its scripts keep working; every module here loads the same module from orchestrating-chat-agents. Use orchestrating-chat-agents for parallel Claude calls over the API from claude.ai, and dispatching-subagents for fan-out in Claude Code.

not rated 153 +3 changed 5d ago A 72 tokens original MIT

parsing-video

52

oaustegard/claude-skills

Skill Claude CodeCodex

Interpret video content visually by sampling frames into timestamped contact sheets that can be read as images. Use when: user asks what happens in a video; asks to summarize, describe, review, or QA video content or footage; asks about scenes, actions, people, or objects in a video; needs a storyboard-style overview…

not rated 153 +3 yesterday A SkillSpector: pass 160 tokens original MIT

ai-and-reasoning

53

oaustegard/claude-skills

Plugin Claude Code

Bundles 4 skills · 576 tokens together

AI model invocation, multi-agent orchestration, prompt distillation, and structured reasoning frameworks.

not rated 153 +3 changed 2d ago A tokens not measured original MIT

code-intelligence

54

oaustegard/claude-skills

Plugin Claude Code

Bundles 5 skills · 651 tokens together

Codebase exploration, navigation, mapping, and static analysis tools for understanding unfamiliar codebases.

not rated 153 +3 changed 9d ago A tokens not measured original MIT

development-tools

55

oaustegard/claude-skills

Plugin Claude Code

Bundles 1 skill · 108 tokens together

Software development utilities: MCP servers, bookmarklets, frameworks, patching, and environment validation.

not rated 153 +3 changed 1mo ago A tokens not measured original MIT

oaustegard/claude-skills

Plugin Claude Code

Bundles 3 skills · 240 tokens together

Research methodology, corpus search, persistent memory, iterative workflows, and project knowledge management.

not rated 153 +3 changed 1mo ago A tokens not measured original MIT

media-processing

58

oaustegard/claude-skills

Plugin Claude Code

Bundles 6 skills · 854 tokens together

Image manipulation, video/audio processing, file format conversion, SVG conversion, and computer vision augmentation.

not rated 153 +3 changed 9d ago A tokens not measured original MIT

lexical-kb

62

oaustegard/claude-skills

Skill Claude CodeCodex

Query a portable, embedding-free lexical knowledgebase bundled as a .skill. Use when the user references this KB or asks a question whose answer is in its corpus ({{SOURCE}}). Retrieval is BM25 over a precomputed inverted index — there is no embedding model, so YOU expand the query into search terms before searching.…

not rated 153 +3 yesterday A 95 tokens original MIT

informed-patient

63

oaustegard/claude-skills

Skill Claude CodeCodex

Use when the user explicitly asks to use the informed-patient skill to prepare for a medical appointment, organize symptoms before seeing a doctor, or evaluate the evidence behind a diagnosis or treatment. Do not trigger automatically from health questions or symptom mentions alone — requires an explicit request by…

not rated 153 +3 changed 1mo ago A 61 tokens original MIT

dunking-anonymously

64

oaustegard/claude-skills

Skill Claude CodeCodex

Renders a Bluesky post as an anonymised screenshot so its words can be criticised without a link back to whoever wrote them. Blacks out avatar, display name, handle and any at-mentions in declassified-document styling, then emits a PNG and its alt text. Use for anonymous dunk-quoting, "dunk on this without linking…

not rated 153 +3 yesterday A 125 tokens original MIT

ocring-pdfs

65

oaustegard/claude-skills

Skill Claude CodeCodex

Adds a searchable text layer to a scanned PDF with ocrmypdf. Installs the toolchain at runtime in 18s. Use when a PDF's pages are images and the deliverable is a file to keep, grep, or hand to another tool: 'make this PDF searchable', 'OCR this scan', 'I can't select the text in this PDF', 'search across these scanned…

not rated 153 +3 yesterday A 123 tokens original MIT

oaustegard/claude-skills

Skill Claude Code

Delegates work to a subagent or spawned session by writing only the task, while a PreToolUse hook pages the parent transcript through Jev and appends the chunks that task needs. Use before writing any Agent tool prompt or createsession prompt, and when asked to delegate this, hand this off, use a subagent, spawn an…

not rated 153 +3 changed 5d ago B 93 tokens original MIT

oaustegard/claude-skills

Skill Claude CodeCodex

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 booleans, stroke-to-outline, and Gouraud-shaded 3D. Use when writing pycairo or cairo drawing code, generative art…

not rated 153 +3 yesterday A 109 tokens original MIT

listening-to-music

68

oaustegard/claude-skills

Skill Claude CodeCodex

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 pitch lines, chroma, roughness and semitone-rub meters; engrave notes as a score with beat-by-beat harmony; transcribe a…

not rated 153 +3 yesterday A 251 tokens original MIT

oaustegard/claude-skills

Skill Claude Code

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 (is this tool call grounded, should the agent ask first, is the customer angry), and how severe or urgent it is on a…

not rated 153 +3 yesterday A 162 tokens original MIT

decider

70

oaustegard/claude-skills

Agent Claude Code

Haiku 5.5 decision sampler for the deciding-with-confidence skill. Answers one sample prompt from decide.py emit --agent decider with a probability per option, as JSON, with no tools and no prose. Dispatch several in parallel, then pool the replies with decide.py aggregate; one reply alone is not a calibrated answer.

not rated 153 +3 yesterday A 74 tokens original MIT

oaustegard/claude-skills

Skill Claude CodeCodex

Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a headless fan-out from one background command. Use for "fan this out to 50 agents", "run these tasks in parallel", "launch subagents for each file", "should I spawn agents or write a…

not rated 153 +3 changed 2d ago A 165 tokens original MIT

oaustegard/claude-skills

Skill Claude CodeCodex

Fans Claude work out over the Anthropic API from surfaces with no native subagents, chiefly claude.ai chat and projects, with parallel calls with a shared cached context, streaming, long-lived conversation threads with cached history, and named agent pools; also delegates to Gemini through the Cloudflare AI Gateway on…

not rated 153 +3 yesterday A 104 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: