hookify
claudeEasily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
1 skill · 4 commands · 1 agent · hooks
LLM-maintained wiki skills — ingest, query, lint, extract
Plugin llm-wiki from marketplace llm-wiki-plugins in tom5610/llm-wiki. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
investigateRoot cause analysis for development issues — error messages, build failures, config problems, test failures, plugin errors, unexpected behavior. Use when the user pastes an error message, stack trace, or log output, says "investigate", "why is this failing", "debug this", "what's wrong with", "root
extractExtract and derive structured knowledge from wiki pages for downstream use — structured data, derivative documents, or compact knowledge packs. Use when the user asks to "extract", "export", "generate a checklist", "create a summary for", "build a reference", or produce any derivative output from wi
ingestProcess a raw source document into the wiki — read it, discuss key takeaways, create/update wiki pages, update index and log. Use when the user drops a new document, article, or notes into raw/ or asks to "add", "process", "import", or "incorporate" a source.
lintHealth-check the wiki — find contradictions, orphan pages, stale claims, missing cross-references, and content gaps. Categorized by severity. Use when the user asks to "check", "validate", "review", "clean up", "audit", or "fix" the wiki.
queryAnswer questions against the wiki or search it by keyword — synthesize an answer with citations, or return a navigational results list. Use when the user asks a question, says "what does the wiki say about", "explain", "summarize", or wants an answer drawn from wiki content. Also use when the user a
jq -r '.tool_input.file_path // .tool_response.filePath' | { read -r f; case "$f" in */wiki/*.md|wiki/*.md) python3 ${CLAUDE_PLUGIN_ROOT}/scripts/wiki-check.py "$f" ;; esac; } 2>&1 || true
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
1 skill · 4 commands · 1 agent · hooks
Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.
1 skill
Claude Skills for Obsidian
6 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
Personalized AWS guidance built on patterns from 350,000+ startups. Get architecture, cost, and security recommendations matched to your stage, from day-one account setup to production-ready infrastructure. Migrate to AWS from Azure, GCP, or Heroku with resource discovery, cost estimates, and generated Terraform. Move OpenAI, Azure OpenAI, and Gemini code to Amazon Bedrock, and plan and prototype AI agents on AgentCore and other AWS runtimes. Includes AWS Activate credits eligibility, 60+ exclusive startup offers, and multi-account, multi-region support. Built by AWS Startup Solutions Architects.
13 skills · 1 command · 7 agents · 1 MCP server
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...
21 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.