{"id":50800618,"url":"https://github.com/jamdesk/skills","last_synced_at":"2026-06-12T19:03:53.414Z","repository":{"id":335538627,"uuid":"1146199922","full_name":"jamdesk/skills","owner":"jamdesk","description":"AI agent skills for Jamdesk documentation workflows","archived":false,"fork":false,"pushed_at":"2026-03-02T19:07:05.000Z","size":26,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-02T20:52:34.417Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jamdesk.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-30T18:52:51.000Z","updated_at":"2026-03-02T19:07:09.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/jamdesk/skills","commit_stats":null,"previous_names":["jamdesk/skills"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jamdesk/skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamdesk%2Fskills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamdesk%2Fskills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamdesk%2Fskills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamdesk%2Fskills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jamdesk","download_url":"https://codeload.github.com/jamdesk/skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamdesk%2Fskills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34258372,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-12T02:00:06.859Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-12T19:03:47.734Z","updated_at":"2026-06-12T19:03:53.387Z","avatar_url":"https://github.com/jamdesk.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Jamdesk Skills\n\n[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](./LICENSE)\n[![Claude Code](https://img.shields.io/badge/Claude_Code-skills-blueviolet?logo=anthropic)](https://www.jamdesk.com/docs/claude-code)\n[![AI Agent](https://img.shields.io/badge/AI_Agent-compatible-green)](https://github.com/jamdesk/skills)\n\nAI agent skills for [Jamdesk](https://jamdesk.com) workflows. These skills teach AI coding assistants to keep documentation in sync with code and handle common developer tasks like screenshot redaction.\n\n## What is Jamdesk?\n\n[Jamdesk](https://jamdesk.com) is a documentation platform that transforms MDX (Markdown + React components) into polished documentation websites. Write in Markdown, push to GitHub, and deploy globally in seconds.\n\n**Key features:**\n- MDX-based workflow with 25+ built-in components\n- Three professional themes (Jam, Nebula, Pulsar)\n- AI-powered search and LLM-ready output (`llms.txt`)\n- Built-in analytics and OpenAPI support\n- Custom domains with SSL\n\n**New to Jamdesk?** Check out the [documentation](https://jamdesk.com/docs) to get started, or try the [quickstart guide](https://jamdesk.com/docs/quickstart) to deploy your first docs site in minutes.\n\n## Why Use These Skills?\n\nAI coding assistants are capable but generic. Skills give them domain-specific knowledge — how your docs are structured, what tools to use, what steps to follow. Instead of explaining your workflow every time, the skill handles it.\n\n**update-jamdesk** keeps docs in sync with code. Implement a feature, run `/update-jamdesk`, and the skill analyzes your changes, writes documentation, and verifies it. No more \"I'll document it later.\"\n\n**blur-image** redacts sensitive data from screenshots before you share them. Point it at a screenshot and it scans for API keys, tokens, passwords, emails, names, and internal URLs using AI vision — then asks you in plain English what to blur. It handles everything from terminal screenshots with `.env` files to JSON API responses to faces in photos. You describe what to hide in words (\"blur the values after the = signs\"), and it handles the pixel math, coordinate calibration, and verification automatically.\n\n## Quick Start\n\n```bash\n# Install a single skill\nnpx skills add jamdesk/skills --skill blur-image\n\n# Or install all skills at once\nnpx skills add jamdesk/skills\n```\n\nThen use it in your AI assistant:\n\n```\n\u003e blur the sensitive data in screenshot.png\n```\n\nFor `update-jamdesk`, you'll also need a config file pointing to your docs repo:\n\n```bash\necho \"docs_path: ../my-docs\" \u003e .jamdesk-docs-path\n```\n\n## Installation\n\nInstall skills using the [skills CLI](https://github.com/vercel-labs/add-skill):\n\n```bash\n# Install a specific skill\nnpx skills add jamdesk/skills --skill update-jamdesk\n\n# Install globally (available in all projects)\nnpx skills add jamdesk/skills --skill update-jamdesk -g\n\n# Install all Jamdesk skills\nnpx skills add jamdesk/skills\n```\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| [update-jamdesk](./skills/update-jamdesk) | Automatically updates Jamdesk documentation when code changes |\n| [blur-image](./skills/blur-image) | Detects and blurs sensitive data (API keys, PII, credentials) in screenshots with per-line precision |\n\n## Supported AI Coding Assistants\n\nThese skills work with any AI coding assistant that supports the skills format:\n\n- **Claude Code** - Anthropic's CLI for Claude\n- **Cursor** - AI-first code editor\n- **Windsurf** - Codeium's AI IDE\n- **Codex** - OpenAI's coding assistant\n- **OpenCode** - Open-source AI coding tool\n- And 30+ more agents\n\nRun `npx skills add --help` for the full list of supported agents.\n\n## How They Work\n\n### update-jamdesk\n\nTeaches your AI assistant to find your docs repo, analyze code changes, write MDX pages following Jamdesk conventions, run `jamdesk validate`, and commit. Requires a `.jamdesk-docs-path` config file:\n\n```yaml\n# Path to your Jamdesk docs (relative or absolute)\ndocs_path: ../my-docs\ndocs_branch: main  # Optional, default: main\n```\n\n**Requirements:** A [Jamdesk](https://jamdesk.com) docs project with `docs.json`, an AI coding assistant, and optionally the [Jamdesk CLI](https://jamdesk.com/docs/cli/overview) for local validation.\n\n### blur-image\n\nDetects and blurs sensitive data in screenshots so you can share them safely. The skill:\n\n1. **Scans** the image with AI vision for credentials, PII, tokens, internal URLs, and other sensitive content\n2. **Discusses** what it found in plain English — you decide what to blur and what to keep\n3. **Calibrates** pixel coordinates using a grid overlay system, so blur regions land exactly on the right text (not one line above or below)\n4. **Blurs** with per-line precision — for a config file, it blurs each value individually while keeping the key names readable (`DATABASE_URL=` stays visible, the connection string disappears)\n5. **Verifies** by re-reading the output image and checking that every region is fully obscured\n\nSupports terminal screenshots (high-contrast text with double-pass blur), web pages, config files, JSON responses, and non-text content like faces and logos. Can use Gaussian blur (shows a visible smudge indicating redaction) or solid fill (completely removes the content) depending on your preference.\n\n**Requirements:** [ImageMagick 7+](https://imagemagick.org/script/download.php) (`brew install imagemagick` on macOS).\n\n## Documentation\n\n- [Jamdesk Documentation](https://jamdesk.com/docs) - Full platform docs\n- [Automated Doc Updates Guide](https://jamdesk.com/docs/development/ai-documentation) - Detailed skill usage\n- [MDX Basics](https://jamdesk.com/docs/content/mdx-basics) - Writing content in Jamdesk\n- [Components Reference](https://jamdesk.com/docs/components/overview) - Available MDX components\n\n## Contributing\n\nTo add a new skill:\n\n1. Create a directory: `skills/\u003cskill-name\u003e/`\n2. Add a `SKILL.md` file with YAML frontmatter (`name`, `description`)\n3. Write instructions in Markdown\n4. Submit a pull request\n\nSee [CLAUDE.md](./CLAUDE.md) for detailed guidelines.\n\n## License\n\nApache 2.0\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjamdesk%2Fskills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjamdesk%2Fskills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjamdesk%2Fskills/lists"}