Lullabot

Use when asked to record demo videos or screenshots of a Drupal site (running under DDEV) to share with people — e.g. "make a demo video of <feature>", "record a walkthrough", "capture screenshots of this flow for the team", "show this working". Produces 1080p, narrated, validated, presentable captures driven through the real UI with e0ipso/ddev-playwright-cli. Do NOT use for writing automated/CI Playwright tests (use the playwright-cli skill) or for non-Drupal / non-DDEV recording.

Generate, compare, select, and refine multiple distinct ideas using the Idea Crucible Method. Use when the user wants to brainstorm several options for a task, weigh alternatives against criteria, pick the strongest one with clear justification, and iteratively refine it. Triggers on ideation, brainstorming, comparing options/approaches, decision-making between alternatives, and strategic problem-solving — even when the user doesn't name the method.

Produces a downloadable Markdown security review report evaluating a SaaS application or product for possible use at Lullabot, anchored to Lullabot's SaaS service evaluation guidance. Use this whenever someone asks for a Lullabot security review, a SaaS/vendor/tool security review for Lullabot, asks to evaluate or vet a cloud service or app for Lullabot use, or asks to revise/update an existing Lullabot security review. Trigger on phrases like "security review", "vendor review", "vet this tool", "is X safe to use at Lullabot", or references to the security review submissions spreadsheet, even when the word "skill" is not used.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on the comprehensive Wikipedia "Signs of AI writing" guide. Detects and fixes patterns including inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, excessive conjunctive phrases, and conversational tells like emphatic "real", announcing the rhetorical move, and anthropomorphized objects.

Reviews a Claude Code skill against skill-authoring best practices and produces a prioritized, non-blocking report. Use when creating, editing, or reviewing a SKILL.md, a skill's meta.yml, or a skill directory, or when asked whether a skill follows best practices.

Turn a Screaming Frog 'All Outlinks' CSV export into a clean broken-links report (Excel workbook). Use whenever the user has a Screaming Frog outlinks export and wants to find, triage, report on, or clean up broken links — including phrasings like 'broken link report', 'dead links', 'find the 404s', 'clean up this outlinks export', 'which links are broken', or 'report on bad links from this crawl'. Trigger even if the user hands over a CSV with From/To/Status Code columns and asks what's broken.

Deep security review of a Drupal site's CUSTOM code (modules + theme) running under DDEV, followed by recorded exploit-demonstration videos produced with the Playwright Agent CLI (playwright-cli) via the e0ipso/ddev-playwright-cli add-on. Use when the user wants to audit a DDEV Drupal codebase for vulnerabilities AND get reproducible video proofs-of-concept, especially on projects that do NOT already have a Playwright test harness. Not for diff-only PR review (use the built-in /security-review for that).

This skill should be used when managing Tugboat preview environments via the tugboat CLI. It applies when creating, listing, rebuilding, refreshing, debugging, or administering Tugboat previews, services, and repositories. Triggers on tugboat commands, preview environment management, .tugboat/config.yml editing, and Tugboat QA workflow questions.

Use when the user asks to run, execute, implement, or carry out a Strikethroo plan or its blueprint by plan ID in this repository — triggers include execute blueprint, run the plan, implement plan, build the plan. Do not use to create a plan, to only generate tasks, to run a single task, or for generic development outside Strikethroo.

Use when the user asks to run, execute, or implement one specific task ID within a Strikethroo plan in this repository — triggers include execute task, run task, implement task, do task N. Do not use to execute a whole plan or blueprint, to generate tasks, or for generic development outside Strikethroo.

Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or execute a blueprint); use the dedicated skill for that stage instead.

Use when the user asks to decompose, break down, or generate tasks for an existing Strikethroo plan ID in this repository — triggers include generate tasks, break down the plan, decompose plan, create the task blueprint. Do not use to create a new plan, to execute tasks, or for generic project planning outside Strikethroo.

Use when the user asks to review, refine, improve, interrogate, pressure-test, or update an existing Strikethroo plan by plan ID in this repository — triggers include refine plan, improve plan, review plan, red-team the plan, update plan. Do not use to create a new plan, to generate tasks, or for generic brainstorming outside Strikethroo.

This skill should be used when users need help with htmx development, including implementing AJAX interactions, understanding htmx attributes (hx-get, hx-post, hx-swap, hx-target, hx-trigger), debugging htmx behavior, building hypermedia-driven applications, or following htmx best practices. Use when users ask about htmx patterns, server-side HTML responses, or transitioning from SPA frameworks to htmx. (user)