benedictking/benedictking-skills
6 skills1.1k installs84 starsGitHub
Install
npx skills add https://github.com/benedictking/benedictking-skillsSkills in this repo
1Exa Searchexa-search is a BenedictKing Claude Code skill at version 1.0.2, MIT-licensed, requiring Node.js and network access to the Exa API. The skill maps user intent to specific Exa endpoints: semantic search with type auto by default, similar-page discovery, full result content retrieval, research-paper lookup, and GitHub discovery. Trigger conditions in the SKILL.md guide endpoint selection for deep structured research versus quick page finds. Developers reach for exa-search when Claude Code needs fresher, semantically ranked web evidence than built-in browsing alone, especially for technical research and repository discovery. Allowed tools are Bash and Read, keeping retrieval inside the standard agent shell workflow.579installs2Firecrawl ScraperFirecrawl Scraper is a MIT-licensed agent skill (version 1.0.2) that teaches Claude Code when and how to call Firecrawl API endpoints for single-page scrape, full-site crawl, batch URL processing, screenshots, and PDF parsing. The skill selects the correct endpoint from user intent—markdown, HTML, JSON, screenshot, or PDF output—and runs via Bash with network access to Firecrawl. Developers reach for Firecrawl Scraper when agents must fetch real page content, crawl documentation sites, or extract structured data without hand-writing scraper scripts or hallucinating page content. It is user-invocable and designed for Claude Code with Node.js as a runtime dependency.523installs3Tavily WebTavily Web performs current web research through the Tavily API, choosing among search, extract, crawl, map, and structured research endpoints based on intent. A developer uses it to find sources, extract or summarize URL content, map a site's pages, or produce schema-structured research output. It assembles the JSON payload in the main context and executes HTTP calls in a forked sub-skill.11installs4Context7 Auto ResearchContext7 Auto Research fetches current documentation, setup steps, and API references for a named library or framework from the Context7 API. A developer relies on it so Claude Code answers with up-to-date docs and code examples instead of stale training data. It resolves the library, selects the best match by trust score and version, then fetches and integrates relevant documentation snippets.4installs5Codex ReviewCodex Review runs a Codex-CLI-based code review of pending changes or the latest commit from within Claude Code. A developer invokes it to review uncommitted work, with the skill first recording intention, updating the CHANGELOG, staging new files, and running project linting. It scales the Codex model reasoning effort and timeout based on the size of the diff.2installs6Gpt Image 2 ApiThis skill generates and edits images with gpt-image-2 through a third-party OpenAI-compatible API endpoint. A developer uses it to create illustrations, visual assets, or image variations, and to edit reference images with optional masks and transparent backgrounds. It is configured via OPENAI_API_KEY and OPENAI_BASE_URL and driven by a Node.js script that calls the images generation and edit endpoints.2installs