What's on the bench.
Analytics Tracking
Set up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Use when building a tracking plan from scratch, auditing existing analytics for gaps or errors, debugging missing events, or setting up GTM. Trigger keywords: GA4 setup, Google Tag Manager, GTM, event tracking, analytics implementation, conversion tracking, tracking plan, event taxonomy, custom dimensions, UTM tracking, analytics audit, missing events, tracking broken. NOT for analyzing marketing campaign data — use campaign-analytics for that. NOT for BI dashboards — use product-analytics for in-product event analysis.
Ad Creative
When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
Ab Test Setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
Cs Md Review
Convert a markdown PR writeup or code review (with ```diff blocks and > [!BLOCKER]/[!MAJOR]/[!MINOR]/[!NIT] severity callouts) into a single-file 2-column HTML review. Top jump-nav lists every finding by severity. Diff on the left, severity-tagged annotation cards on the right, mandatory named reviewer footer. Refuses without --reviewer (a code review must name a human) or if no diff hunks present.
Cs Md Document
Convert long-form markdown (specs, RFCs, reports, plans, explainers) into a single-file interactive HTML document. Runs the md-document pipeline (parser → renderer → injector) with the user's design-system tokens. Sticky TOC, search filter, code-copy buttons, scrollspy, WCAG-AA palette. Refuses input < 100 lines (Shihipar) or unfinished onboarding. Output is a single .html file (Google Fonts + Prism.js CDN as the only externals).
Cs Grill Markdown HTML
Matt-Pocock-style forcing-question grill for markdown-html conversions. Walks 5 cited-canon questions (purpose, line-count threshold, design-system onboarding, output path, doctype confidence) one at a time with a recommended answer. Run before /cs:markdown-html when you want clarity about what the HTML is for, not just a route to the closest sub-skill.
Cs Design System
Run the one-time markdown-html design-system onboarding wizard. Captures brand primary/accent (HEX) + heading/body Google Fonts + design style (editorial/technical/minimal/playful) + default output directory + syntax theme + TOC behavior + optional logo/company. WCAG-AA validates body-text contrast; refuses if it fails. Stores at ~/.config/markdown-html/design-system.json (or project-scoped with --scope project). Every converter reads this config via config_loader.py before rendering.
Md Review
Converts a markdown PR writeup or code review (one with ```diff fenced blocks and severity-tagged > [!BLOCKER]/[!MAJOR]/[!MINOR]/[!NIT] callouts) into a single-file 2-column HTML review — unified-diff on the left, severity-tagged annotation cards on the right, top jump-nav listing every finding, mandatory named reviewer footer. Triggers when the markdown-html-orchestrator classifies an input as REVIEW, or when invoked directly via /cs:md-review. Refuses without explicit --reviewer (a code review must name a human), refuses if no diff hunks present (route to md-document instead), and refuses to encode severity in color only (every badge ships color + icon + aria-label per WCAG 1.4.1). Use after orchestrator routing.
Md Document
Converts long-form markdown (specs, RFCs, reports, plans, explainers) into a single-file, lightly-interactive HTML document with sticky TOC, scrollspy, search filter, code-copy buttons, and design-system-driven brand tokens. Triggers when the markdown-html-orchestrator classifies an input as DOCUMENT, or when invoked directly via /cs:md-document. Reads the design-system config via config_loader.py and inlines the user's 12 derived CSS custom properties; refuses to render if onboarding hasn't run. Single-file output — Google Fonts + Prism.js CDN are the only externals; no framework runtime, no build step. Use after orchestrator routing or after design-system onboarding is confirmed.
Markdown HTML Orchestrator
Use when a user wants to convert any markdown file in their Claude project into a single-file, lightly-interactive HTML — long-form documents (specs, plans, RFCs, reports, explainers), code reviews with diffs and severity-tagged annotations, or slide decks. Triggers on "convert this markdown to HTML", "make this an HTML file", "turn this into an interactive document", "render this report as HTML", "PR writeup as HTML", "slides from this markdown". Forks context to route to one of three converter sub-skills (md-document, md-review, md-slides) based on a deterministic doctype classifier, after the user has run the design-system onboarding once. Refuses if input is under 100 lines (per Shihipar — markdown still wins below the threshold) or design-system isn't onboarded. Distinct from Anthropic's official Playground plugin (which is interactive prompt-tuning controls with sliders/knobs/prompt-copy-back) and from marketing/landing/ (which is a landing-page generator).
SaaS Metrics Coach
SaaS financial health advisor. Use when a user shares revenue or customer numbers, or mentions ARR, MRR, churn, LTV, CAC, NRR, or asks how their SaaS business is doing.
Business Investment Advisor
Business investment analysis and capital allocation advisor. Use when evaluating whether to invest in equipment, real estate, a new business, hiring, technology, or any capital expenditure. Also use for ROI calculations, IRR, NPV, payback period, build vs buy decisions, lease vs buy analysis, vendor evaluation, or deciding where to allocate limited budget for maximum return.
Cs Write A Skill
/cs:write-a-skill <name-or-description> — Author a new agent skill with Matt Pocock's 3-phase workflow (Gather → Draft → Review). Runs 6 review-checklist items + 3 validator tools as a gate. Use when starting a new skill in this repo.
Cs Workflow Build
/cs:workflow-build <task-description> — Design and write a deterministic Claude Code workflow (.js). Opens with intake questions, infers-and-proposes a topology when the request is vague, then scaffolds + validates the file. Use when building or running a custom Claude Code workflow.
Cs Scrape
Route, extract, and validate a scraping job (URL or local file) via the universal-scraping-architect skill — refuses to deliver unvalidated data.
Wiki Lint
Run a health check on the LLM Wiki vault — mechanical checks (orphans, broken links, stale pages, missing frontmatter, log gap, duplicates) plus semantic checks (contradictions, cross-reference gaps, concepts missing their own page). Outputs a markdown report with suggested actions. Usage /wiki-lint [--stale-days N] [--log-gap-days N]
Wiki Ingest
Ingest a source file from raw/ into the LLM Wiki — read, discuss, write summary page, update cross-references across 5-15 pages, regenerate index, append to log. Usage /wiki-ingest <path-to-source>
Cs Handoff
/cs:handoff <next-session-focus> — Compact the current conversation into a handoff document for a fresh agent. Tailored to next-session focus (deploy/review/debug/design/test). Replaces PRD/ADR/issue/commit content with references. Recommends specific skills for the next session.
Cs Grill With Docs
/cs:grill-with-docs <path-to-plan> — Start a docs-anchored grilling session. Pre-flights CONTEXT.md + docs/adr/ linters, then interrogates the plan one decision at a time, updating glossary + writing ADRs inline as they crystallise.
Cs Grill Me
/cs:grill-me <path-to-plan> — Start a relentless interrogation of a plan or design. Walks decision tree one branch at a time. One question per turn with recommended answer. Explores codebase before asking.
Cs Claude Coach
Activate the claude-coach skill — personal Claude power-user coaching for the rest of the conversation.
Cs Caveman
/cs:caveman — Activate persistent caveman-mode. Ultra-compressed responses with technical substance preserved. Auto-clarity exception for warnings + destructive ops. Stays active until 'stop caveman' / 'normal mode'.
Snowflake Development
Use when writing Snowflake SQL, building data pipelines with Dynamic Tables or Streams/Tasks, using Cortex AI functions, creating Cortex Agents, writing Snowpark Python, configuring dbt for Snowflake, or troubleshooting Snowflake errors.
Tech Stack Evaluator
Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.