Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Docx
Word document processing. USE WHEN docx, Word document. SkillSearch('docx') for docs.
Steffen025/pai-opencode 114
-
Evals
Agent evaluation framework. USE WHEN eval, evaluate, test agent, benchmark, verify behavior.
Steffen025/pai-opencode 114
-
Scraping
Web scraping and data extraction. USE WHEN scrape website, extract data, web scraping, Twitter, Instagram, LinkedIn, TikTok, YouTube, Google Maps, Amazon, social media scraping.
Steffen025/pai-opencode 114
-
Apify
Social media scraping, business data, e-commerce via Apify actors. USE WHEN Twitter, Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon scraping.
Steffen025/pai-opencode 114
-
BrightData
Progressive URL scraping. USE WHEN Bright Data, scrape URL, web scraping tiers. SkillSearch('brightdata') for docs.
Steffen025/pai-opencode 114
-
Media
Media creation and processing skills. USE WHEN create visuals, generate images, video production, thumbnails, art, illustrations.
Steffen025/pai-opencode 114
-
Art
Visual content system. USE WHEN art, illustrations, diagrams, visualizations, mermaid, flowchart.
Steffen025/pai-opencode 114
-
Remotion
Programmatic video creation with React. USE WHEN video, animation, motion graphics, video rendering, React video, intro video, YouTube video, TikTok video, video production, render video.
Steffen025/pai-opencode 114
-
Thinking
Deep thinking and analysis skills. USE WHEN be creative, deep thinking, extended reasoning, first principles, decompose, red team, critique, stress test, council, debate, perspectives, science, research methodology, threat model, world analysis.
Steffen025/pai-opencode 114
-
WorldThreatModelHarness
Persistent world model system across 11 time horizons (6mo→50yr) for adversarial analysis of ideas, strategies, and investments. USE WHEN threat model, world model, test idea, test strategy, future analysis, test investment, how will this hold up, test against future, update world models, view world models, time horizon analysis, adversarial future test, stress test idea.
Steffen025/pai-opencode 114
-
RedTeam
Adversarial analysis with 32 agents. USE WHEN red team, attack idea, counterarguments, critique, stress test. SkillSearch('redteam') for docs.
Steffen025/pai-opencode 114
-
museum-search
Search the Met Museum Open Access Paintings collection using semantic search, find similar artworks, and search by image. Use this when users ask about art, paintings, museum collections, or want to find artworks by description, visual similarity, or artist.
derekphilipau/museum-semantic-search 6
-
terraform-module
Inspect Terraform module specs from cache when seeing module sources.
n4vysh/dotfiles 5
-
skill-creator
Create effective skills. Use when creating or updating skills.
n4vysh/dotfiles 5
-
tasks-system
zby/llm-do 18
-
ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
zby/llm-do 18
-
decomplect-py
Architectural code analysis for Python design quality. Evaluates simplicity (Rich Hickey), functional core/imperative shell (Gary Bernhardt), and coupling (Constantine & Yourdon). Use for design review or architectural assessment of Python code.
zby/llm-do 18
-
refactor
Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval. Triggers on "/refactor", "restructure vault".
zby/llm-do 18
-
validate
Schema validation for notes. Checks against domain-specific templates. Validates required fields, enum values, description quality, and link health. Non-blocking — warns but doesn't prevent capture. Triggers on "/validate", "/validate [note]", "check schema", "validate note", "validate all".
zby/llm-do 18
-
tasks
View and manage the task stack and processing queue. Shows pending work, active tasks, completed items, and queue state. Triggers on "/tasks", "show tasks", "what's pending", "task list", "queue status".
zby/llm-do 18
-
ralph
Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".
zby/llm-do 18
-
pipeline
End-to-end source processing -- seed, reduce, process all claims through reflect/revisit/review, archive. The full pipeline in one command. Triggers on "/pipeline", "/pipeline [file]", "process this end to end", "full pipeline".
zby/llm-do 18
-
connect
Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after /extract creates notes, when exploring connections, or when a topic needs synthesis. Triggers on "/connect", "/connect [note]", "find connections", "update MOCs", "connect these notes".
zby/llm-do 18
-
tasks-system
zby/llm-do 18