Create Claude Code marketplace

.claude-plugin/marketplace.json

@@ -0,0 +1,40 @@
+{
+    "name": "mintlify-workflows",
+    "owner": {
+      "name": "Mintlify",
+      "email": "support@mintlify.com",
+      "url": "https://mintlify.com"
+    },
+    "metadata": {
+      "description": "Ready-to-use Claude Code templates for documentation workflows using Mintlify components and technical writing best practices.",
+      "version": "1.0.0"
+    },
+    "plugins": [
+      {
+        "name": "doc-reviewer",
+        "source": "./",
+        "description": "Workflow for reviewing documentation updates",
+        "version": "1.0.0",
+        "author": {
+          "name": "Denzell Ford"
+        },
+        "license": "MIT",
+        "keywords": ["documentation", "docs", "mintlify", "review"],
+        "category": "documentation",
+        "strict": false,
+        "commands": [
+          "./.claude/commands/review.md",
+          "./.claude/commands/lint.md"
+        ],
+        "agents": [
+          "./.claude/agents/document-reviewer.md"
+        ],
+        "mcpServers": {
+          "Mintlify": {
+            "type": "http",
+            "url": "https://mintlify.com/docs/mcp"
+          }
+        }
+      }
+    ]
+  }

.claude/agents/document-reviewer.md

@@ -1,5 +1,5 @@
 ---
-name: docuemnt-reviewer
+name: document-reviewer
 description: Document reviewer trained for Mintlify docs.
 model: sonnet
 ---
@@ -8,23 +8,20 @@ model: sonnet
 
 You are an experienced, pragmatic technical writer with robust content strategy and content design experience. You elegantly create just enough docs to solve users' needs and get them back to the product quickly.
 
-Rule #1: If you want an exception to ANY rule, YOU MUST STOP and get explicit permission from Ethan first. BREAKING THE LETTER OR SPIRIT OF THE RULES IS FAILURE.
+Rule #1: If you want an exception to ANY rule, YOU MUST STOP and get explicit permission from whoever invoked you. BREAKING THE LETTER OR SPIRIT OF THE RULES IS FAILURE.
 
 ## Working relationship
 
-
 - We're colleagues working together your name is "Claude"
-- You can push back on ideas-this can lead to better documentation. Cite sources and explain your reasoning when you do so
+- You can push back on ideas. This can lead to better documentation. Cite sources and explain your reasoning when you do so
 - ALWAYS ask for clarification rather than making assumptions
 - NEVER lie, guess, or make up information
-- You are much better read than I am. I have more experience of the physical world than you do. Our experiences are complementary and we work together to solve problems.
-- When you disagree with my approach, YOU MUST push back, citing specific technical reasons if you have them. If it's just a feeling, say so.
-- YOU MUST call out bad ideas, unreasonable expectations, and mistakes - I depend on this.
-- NEVER be agreeable just to be nice - I need your honest technical judgment.
-- NEVER tell me I'm "absolutely right" or anything like that. You can be low-key. You ARE NOT a sycophant.
-- We can be humorous and playful, but not when it gets in the way of the task at hand. Save it for when a project is finished or we need levity during a tough project.
-- YOU MUST ALWAYS ask for clarification rather than making assumptions.
-- If you're having trouble, YOU MUST STOP and ask for help, especially for tasks where human input would be valuable.
+- When you disagree with my approach, YOU MUST push back, citing specific reasons if you have them
+- YOU MUST call out bad ideas, unreasonable expectations, and mistakes
+- NEVER be agreeable just to be nice. Give your honest technical judgment
+- NEVER tell me I'm "absolutely right" or anything like that. You can be low-key. You ARE NOT a sycophant
+- YOU MUST ALWAYS ask for clarification rather than making assumptions
+- If you're having trouble, YOU MUST STOP and ask for help, especially for tasks where human input would be valuable
 - If you are making an inferrance, stop and ask me for confirmation or say that you need more information
 
 ## Project context
@@ -34,7 +31,7 @@ Rule #1: If you want an exception to ANY rule, YOU MUST STOP and get explicit pe
 - Components: Mintlify components
 
 ## Content strategy
-- We document just enough so that users are successful. Too much content makes it hard to find what people are looking for. Too little makes it too challenging to accomplish users' goals.
+- We document just enough so that users are successful. Too much content makes it hard to find what people are looking for. Too little makes it too challenging to accomplish users' goals
 - Prioritize accuracy and usability of information
 - Make content evergreen when possible
 - Search for existing information before adding new content. Avoid duplication unless it is done for a strategic reason
@@ -62,10 +59,9 @@ Rule #1: If you want an exception to ANY rule, YOU MUST STOP and get explicit pe
 - Remove unnecessary words while maintaining clarity
 - Break complex instructions into clear numbered steps
 - Make language more precise and contextual
-- Use [Lucide](https://lucide.dev) icon library
 
 ### Language and tone standards
-- **Avoid promotional language**: Never use phrases like "rich heritage," "breathtaking," "captivates," "stands as a testament," "plays a vital role," or similar marketing language in technical documentation
+- **Avoid promotional language**: Never use phrases like "breathtaking," "captivates," "stands as a testament," "plays a vital role," or similar marketing language in technical documentation
 - **Be specific, not vague**: Replace vague attributions like "industry reports suggest" or "some experts argue" with specific, citable sources
 - **Reduce conjunction overuse**: Limit use of "moreover," "furthermore," "additionally," "on the other hand" - favor direct, clear statements
 - **Avoid editorializing**: Remove phrases like "it's important to note," "this article will," "in conclusion," or personal interpretations

.claude/commands/document-pr.md

@@ -6,7 +6,7 @@ argument-hint: [pr-number] [repository]
 
 I need to document a new feature. Please:
 1.a Analyze the code changes in pull request on #$1 in repo $2.
-1.b If the github cli exists, utilize the github cli `gh pr diff` command if ito get the code changes
+1.b If the GitHub CLI exists, utilize the GitHub CLI command `gh pr diff` to get the code changes
 2. Search through the docs to see if any existing pages need updates
 3. Identify what pages need to be updated and if new documentation is needed
 4. Suggest the best location for new content (prefer updating existing pages)

.claude/commands/lint.md

@@ -1,11 +1,15 @@
 ---
-allowed-tools: Bash(mint *)
-description: Lint the mintlify docs and fix errors
+allowed-tools: Bash(mint *), Bash(vale *)
+description: Lint the docs and fix errors
 ---
 
-Run `mint broken-links` and check the given git diff. For an openapi reference updates run `mint openai-check`.
+Run `mint broken-links` and check the given git diff. For OpenAPI reference updates run `mint openai-check`.
 
-For more details on the `mint` cli. Look at the details here.
+If the Vale CLI exists, run a Vale check on all changed files.
+
+Make a plan to resolve any broken links or Vale errors.
+
+For more details on the `mint` CLI, look at the details here:
 
 ```
 mint <command>
@@ -29,3 +33,50 @@ Options:
   -h, --help     Show help                                             [boolean]
   -v, --version  Show version number                                   [boolean]
 ```
+
+For more information on the Vale CLI, look at the details here:
+
+```
+vale - A command-line linter for prose.
+
+Usage:	vale [options] [input...]
+	vale myfile.md myfile1.md mydir1
+	vale --output=JSON [input...]
+
+Vale is a syntax-aware linter for prose built with speed and extensibility in
+mind. It supports Markdown, AsciiDoc, reStructuredText, HTML, and more.
+
+To get started, you'll need a configuration file (.vale.ini):
+
+Example:
+
+	MinAlertLevel = suggestion
+
+	[*]
+	BasedOnStyles = Vale
+
+See https://vale.sh for more setup information.
+
+Flags:
+
+ --config         A file path (--config='some/file/path/.vale.ini').    
+ --ext            An extension to associate with stdin (--ext=.md).     
+ --filter         An expression to filter rules by.                     
+ --glob           A glob pattern (--glob='*.{md,txt}.')                 
+ -h, --help       Print this help message.                              
+ --ignore-syntax  Lint all files line-by-line.                          
+ --minAlertLevel  The minimum level to display (--minAlertLevel=error). 
+ --no-exit        Don't return a nonzero exit code on errors.           
+ --no-global      Don't load the global configuration.                  
+ --no-wrap        Don't wrap CLI output.                                
+ --output         An output style ("line", "JSON", or a template file). 
+ -v, --version    Print the current version.                            
+
+Commands:
+
+ ls-config        Print the current configuration to stdout.             
+ ls-dirs          Print the default configuration directories to stdout. 
+ ls-metrics       Print the given file's internal metrics to stdout.     
+ ls-vars          Print the supported environment variables to stdout.   
+ sync             Download and install external configuration sources.   
+```

.claude/commands/review.md

@@ -9,7 +9,6 @@ Please review the changes I'm about to commit and check:
 3. Are any code examples accurate?
 4. Is the frontmatter complete and correct?
 5. Does the content match our existing style?
-6. Run vale on the files being updated and make a plan to resolve any errors, warnings, and suggestions.
-7. Are there any links that need testing?
+6. Are there any links that need testing?
 
 $ARGUMENTS

.claude/commands/update-change-log.md

@@ -12,10 +12,11 @@ argument-hint: [...repo]
 5. We do not use releases. Only look at closed Pull Requests within the next daterange.
 6. For each pull request, invoke @agents-pr-summarizer in parallel to generate a summary of the pull request.
 7. Read each file from this in @summaries and generate a synopsis for each PR.
-8. Tell me a summary of what was changed
-9. Update @channgelog.mdx with the summary from all previous pull requests. Use Mintlify components and follow the existing style of @changelog.mdx
+8. Tell me a summary of what was changed.
+9. Update @channgelog.mdx with the summary from all previous pull requests. Use Mintlify components and follow the existing style of @changelog.mdx.
 
 This summary should be a high level overview.
 - Bug fixes should be highlighted.
 - New features should be highlighted.
-- Any other small details or incremental pr's should be excluded.
+- Any other small details or incremental PRs should be excluded.
+- Only include information relevant to end users. For example, don't include information about internal tooling, bumping package versions, or similar.