setup-mmw
Configure mark-my-words for your blog. Sets up platform, source location, and preferences.
What this skill does
<purpose>
You are configuring the mark-my-words plugin for the user's blog. Your job is to check prerequisites, gather their blog settings, and write a plugin-specific preferences file.
</purpose>
<steps>
<step id="load-config" number="1">
<description>Load Configuration</description>
<load-config>
<action>Resolve the user's home directory.</action>
<command language="bash" output="home" tool="Bash">echo $HOME</command>
<constraint>Never pass `~` to the Read tool.</constraint>
<read path="<home>/.things/config.json" output="config" />
<if condition="config-missing">Tell the user: "Run `/things:setup-things` first." Then stop.</if>
</load-config>
<validate name="existing-preferences">
<action>Check if `<home>/.things/mark-my-words/preferences.json` already exists.</action>
<if condition="preferences-exist">Read it and show the user their current settings. Ask if they want to reconfigure.</if>
</validate>
</step>
<step id="select-platform" number="2">
<description>Select Platform</description>
<ask-user-question>
<question>Which blogging platform do you use?</question>
<option>Quartz -- Obsidian-compatible static site (wikilinks, callouts, Mermaid)</option>
<option>Hugo -- Popular Go-based static site generator</option>
<option>Jekyll -- Ruby-based, GitHub Pages default</option>
<option>Astro -- Modern web framework with content collections</option>
<option>Eleventy (11ty) -- Flexible JavaScript-based static site generator</option>
<option>Docusaurus -- React-based docs and blog platform (admonitions, MDX)</option>
<option>Zola -- Fast Rust-based static site generator (TOML frontmatter)</option>
</ask-user-question>
<constraint>Store the selection as the `platform` value (lowercase: `quartz`, `hugo`, `jekyll`, `astro`, `eleventy`, `docusaurus`, `zola`).</constraint>
<action>Read the platform template from `<plugin_root>/platforms/<platform>.md` to get platform-specific defaults for the steps below. Use the "Platform Info" table and "Frontmatter" section to inform your suggestions.</action>
</step>
<step id="gather-source-info" number="3">
<description>Gather Blog Source Info</description>
<ask-user-question>
<question>Where does your blog content live?</question>
<option>Remote git repo -- I'll provide a repo URL and branch</option>
<option>Local directory -- I'll provide a path to my content root</option>
</ask-user-question>
</step>
<step id="source-details" number="4">
<description>Source Details</description>
<if condition="source-type-remote">
<ask-user-question>
<question>Remote repo details</question>
<option-with-text-input>Repository URL (e.g., `[email protected]:user/blog.git` or HTTPS URL)</option-with-text-input>
<option-with-text-input>Branch name (suggest `main` as default)</option-with-text-input>
</ask-user-question>
</if>
<if condition="source-type-local">
<ask-user-question>
<question>Path to your content root directory</question>
</ask-user-question>
</if>
</step>
<step id="content-preferences" number="5">
<description>Gather Content Preferences</description>
<constraint>Use the platform template's "Platform Info" table to suggest sensible defaults.</constraint>
<ask-user-question>
<question>Content directory name (the root content directory)</question>
<platform-specific platform="quartz">`content`</platform-specific>
<platform-specific platform="hugo">`content`</platform-specific>
<platform-specific platform="jekyll">`_posts` (note: Jekyll also uses `_drafts` for draft posts)</platform-specific>
<platform-specific platform="astro">`src/content/blog`</platform-specific>
<platform-specific platform="eleventy">varies -- ask the user (common: `src/posts`, `content`, `posts`)</platform-specific>
<platform-specific platform="docusaurus">`blog`</platform-specific>
<platform-specific platform="zola">`content`</platform-specific>
</ask-user-question>
<ask-user-question>
<question>Default subdirectory (where new posts go within the content directory)</question>
<platform-specific platform="quartz">flexible (`blog/`, `notes/`, or empty)</platform-specific>
<platform-specific platform="hugo">`posts/` or `blog/`</platform-specific>
<platform-specific platform="jekyll">empty (posts go directly in `_posts/`)</platform-specific>
<platform-specific platform="astro">empty (posts go directly in blog collection)</platform-specific>
<platform-specific platform="eleventy">empty (posts go directly in posts directory)</platform-specific>
<platform-specific platform="docusaurus">empty (posts go directly in `blog/`)</platform-specific>
<platform-specific platform="zola">`blog/` (organized as sections)</platform-specific>
</ask-user-question>
<ask-user-question>
<question>Default tags (comma-separated list of tags you commonly use, suggested when creating posts)</question>
</ask-user-question>
</step>
<step id="git-workflow-preference" number="6">
<description>Git Workflow Preference</description>
<ask-user-question>
<question>Git workflow for blog changes</question>
<option>Always ask -- prompt before each commit/push</option>
<option>Auto-commit -- automatically commit and push after changes</option>
<option>Manual -- never auto-commit, I handle git myself</option>
</ask-user-question>
</step>
<step id="media-preferences" number="7">
<description>Media Preferences</description>
<ask-user-question>
<question>Where should images and media files be stored? (path relative to your content directory)</question>
<platform-specific platform="quartz">`assets/images`</platform-specific>
<platform-specific platform="hugo">`static/images` (note: Hugo serves `static/` at site root)</platform-specific>
<platform-specific platform="jekyll">`assets/images`</platform-specific>
<platform-specific platform="astro">`public/images`</platform-specific>
<platform-specific platform="eleventy">`img` or `images`</platform-specific>
<platform-specific platform="docusaurus">`static/img`</platform-specific>
<platform-specific platform="zola">`static/images`</platform-specific>
<option>Skip -- no local media management</option>
</ask-user-question>
<if condition="user-skips-media">Set `media_dir: null`.</if>
<ask-user-question>
<question>Should mark-my-words proactively suggest diagrams and images as it writes?</question>
<option>Yes -> `auto_suggest_visuals: true`</option>
<option>No -> `auto_suggest_visuals: false`</option>
</ask-user-question>
<ask-user-question>
<question>Do you want the option to generate images with AI tools?</question>
<option>Yes -> `ai_image_generation: true`</option>
<option>No -> `ai_image_generation: false`</option>
</ask-user-question>
</step>
<step id="write-preferences" number="8">
<description>Create Plugin Directory and Write Preferences</description>
<action>Create the plugin directory structure.</action>
<command language="bash" tool="Bash">mkdir -p <home>/.things/mark-my-words/voices</command>
<action>Write `<home>/.things/mark-my-words/preferences.json` with all blog settings.</action>
<schema name="preferences">
```json
{
"platform": "<platform>",
"source_type": "<remote|local>",
"repo_url": "<url or null>",
"repo_branch": "<branch or null>",
"local_path": "<path or null>",
"content_dir": "<dir>",
"default_subdirectory": "<subdir>",
"default_tags": ["<tag>", ...],
"git_workflow": "<ask|auto|manual>",
"workdir": "<home>/.mark-my-words",
"default_voice": null,
"media_dir": "<pRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.