coding-agent-plugins

This skill should be used when the user asks to "housekeep", "sweep stray transition dirs", "clean up agent-infra debris", "find misplaced .workspace or .claude dirs", or when auditing project trees for the class of debris caused by hooks writing to the wrong project root (nested repos, worker-pool worktrees, stub-only session files, doubled path prefixes). Do NOT use for general project cleanup (see `/system:cleanup`) or for memory garbage collection (see `/memory-gc`).

Write clear, impactful website content for scanners. Use when writing landing pages, service descriptions, CTAs, or above-the-fold content. Covers the 50% test, sentence surgery, power words, page-type guidelines, mobile-first brevity, and techniques for reducing wordiness while maintaining impact.

Match content to what users actually want when they search. Use when creating website pages, blog posts, or any content for search engines. Covers 4 intent types (informational, navigational, transactional, commercial investigation), SERP analysis, query modifiers, and buyer journey mapping.

Technical SEO writing techniques for web content. Use when writing website pages, landing pages, service descriptions, or blog posts for organic search traffic. Covers keyword placement, meta descriptions, heading hierarchy, E-E-A-T principles, internal linking, long-tail keywords, schema markup, and measuring SEO success.

Complete D2 language reference for creating diagrams. Covers shapes, connections, containers, special types (SQL tables, sequences), icons, styling, and advanced features. Use for all D2 diagram generation tasks.

Clarity and simplicity principles for effective diagrams. Focus on essential elements, minimize visual noise, maintain consistency, and use single abstraction levels. Ensures diagrams communicate clearly without clutter.

Visual hierarchy principles for effective diagrams. Use size, color, placement, and typography to guide the viewer's eye and communicate importance. Increases understanding by up to 73%. Apply to all diagrams for clarity.

This skill should be used when the user asks about "CME futures data", "session dates", "Sunday 5pm boundary", "forward returns", or when working with CME futures minute data, handling session vs calendar dates, or filtering invalid timestamps during breaks.

This skill should be used when the user asks to "train LightGBM", "lightgbm cv", "gradient boosting", "hyperparameter tuning LightGBM", or when training LightGBM models with time-series cross-validation, handling depth vs leaves relationships, or avoiding look-ahead bias from early stopping.

This skill should be used when the user asks about "time-series CV", "cross-validation setup", "walk-forward validation", "out-of-sample predictions", or when setting up ML cross-validation pipelines, computing labels/thresholds, or generating OOS predictions without look-ahead bias.

This skill should be used when the user asks to "create a tearsheet", "generate a PDF report", "strategy summary", "backtest report", "performance tearsheet", "factor tearsheet", or when producing single-page or multi-page PDF summaries of quantitative results.

This skill should be used when the user asks to "create a chart", "plot this data", "visualize results", "make a figure", "improve this plot", "publication-quality chart", or when creating matplotlib/plotly visualizations for quantitative finance data.

This skill should be used when the user asks about "citing papers", "adding references", "Zotero", "bibliography", "academic citations", "manage references", or when working with citation formats, paper lookups, or reference synchronization.

This skill should be used when the user asks to "write with research", "research-driven draft", "use papers to shape content", "write section with papers", "incorporate research into writing", or when writing ML4T book sections that should be shaped by academic paper findings rather than decorated with citations.

This skill should be used when the user asks to "make this distinctive", "avoid generic design", "create memorable UI", "bold aesthetic", or when designs feel generic, need to stand out, or require philosophy-driven creative direction.

Quality principles for clear, readable prose. Combines Excellent Writing (15 principles for density), Plain Language (active voice, short sentences), and Information Mapping (scannability, chunking). Use during drafting and editing for maximum clarity.

Documentation mode selection based on user intent. Use when writing technical documentation or educational content. Covers 4 modes: Tutorial (learning), How-To (tasks), Reference (information), Explanation (understanding).

Plan and write presentation CONTENT — narrative arc, one message per slide, headlines, supporting bullets/figures, speaker notes — in a sober, distilled, technical register (graduate textbook, not marketing deck). Use whenever the user wants to build, outline, draft, structure, tighten, or rewrite a deck, slides, talk, lecture, or teaching material — even if they don't say "skill," and even when the output is a .pptx. Establish deck thesis, audience, section arc, and per-slide contract BEFORE drafting slide text; ground every claim in a source; hand rendering and layout to a pptx/render skill.

Core frameworks for organizing arguments and content structure. Combines Pyramid Principle (answer-first hierarchy), SCQA (narrative engagement), and Topic Sentence Method (paragraph coherence). Use when planning outlines, structuring arguments, or drafting structured prose.

This skill should be used when the user asks to "analyze this code", "understand the architecture", "examine the codebase", "project structure", "how is this organized", or when exploring an unfamiliar codebase to understand its patterns, components, and design. Do NOT use for simple file reads or grep searches.

This skill should be used when the user asks to "document this", "add documentation", "write docs", "update the README", "generate API docs", "fetch library docs", or when working with project documentation, external library references, or documentation generation. Do NOT use for code changes or implementation.

This skill should be used when the user asks to "review this code", "check for bugs", "code review", "find issues", "review my changes", "look for problems", or when evaluating code quality, finding bugs, or identifying improvements.