Find the open-source solution that fits.

Run repeated improvement rounds over a real application by rotating lenses such as UX, code quality, security, performance, accessibility, and observability. Each round records evidence, prioritizes the highest-leverage change, checks whether the product's identity survives, and verifies the result before logging it. This is an ongoing loop rather than a one-off audit.

Use the pretext library to measure text height, wrap lines, shrink-wrap containers, render to canvas or SVG, virtualize long lists, and place inline chips or mentions without a DOM. The skill guides the fast prepare/layout path and richer segment APIs, while calling out font, line-height, letter-spacing, and font-loading details that affect accuracy.

Answer one question at a time while the skill routes the business to a stage-specific playbook. It uses revenue and unit-economics math to test the stated problem, identify a constraint, and prescribe the smallest high-leverage move. The approach is an independent educational use of published frameworks, not impersonation, financial advice, or an earnings promise.

Format and review Obsidian notes with shared rules for headings, separators, indentation, emphasis, stickers, tags, and PARA folders. The skill adds a CJK-specific check for Markdown delimiter edge cases, offers a delegation interface for other writing skills, and keeps the note language aligned with the user's request. It is convention infrastructure, not a content generator.

Find the queries consuming the most total time, inspect their actual execution plans and buffers, and identify the slow node rather than guessing at indexes. The workflow then applies one root-cause change, such as a sargable predicate, index, or statistics update, and reruns the plan to confirm the result. It also accounts for write and storage costs.

Apply a citation workflow to blog posts and web pages: add three to five named entities with precise claims and links, draw from a maintained claim bank, add JSON-LD mentions and citation fields, and finish with a Sources block and pre-publication checklist. The adaptation uses Québec-focused authorities and forbids invented figures.

Give the skill a paper, blog post, or whitepaper and it builds a self-contained HTML deck with foundation vocabulary, section-by-section explanations, analogies, math, tables, and figures. Readers can select text and ask questions through a local session layer. Python and Chrome are required, while optional image backends need their own credentials.

Turn a one-line product brief into a browser-ready static HTML and Tailwind page. The skill anchors each build to one real reference site, then chooses a page archetype, typography, color, and micro-grammar so the result does not default to the same generic layout. It can hand-build dashboards, tables, charts, and code-like UI elements.

For work likely to touch many files or require repeated exploration, record a timestamp and short Git commit at the start, delegate the heavy work, and collect only a structured summary of up to 200 words. The workflow helps limit context and editor memory growth during large refactors, but adds overhead to small edits or tightly coupled reasoning.

Inspect a code project read-only, identify its stack and heuristic learning gaps, and match them to Turing books or public resources with reasons. The skill can produce a trackable weekly plan and aggregate gaps across repositories, while keeping book content and paid access boundaries intact. Prices, stock, and course status should be checked on the official site.

Research a company by opening its site, verifying funding with at least two independent sources, checking customer overlap, and separating technology from packaging, sales, brand, and network effects. Recommendations receive a six-dimension score, while fundraising references stay separate from practical learning targets. Historical judgments are marked when they were not re-verified.

Run First Principles, JTBD, 5 Whys, OKR, SWOT, Porter, BCG, Blue Ocean ERRC, and Inversion independently, then compare which conclusions recur across lenses. The output focuses on root diagnoses, blocked decisions, death scenarios, and questions only the team can answer, with anti-flattery checks throughout. The workshop takes about two hours and is heavier than a single-framework review.

Use the dove commands to import approved DLT templates, send individual or bulk messages, generate or verify OTPs, schedule campaigns, and decode delivery reports. The engine distinguishes gateway acceptance from actual delivery and explains DLT failures such as DND or template mismatch. Indian DLT registration is required, and bulk messages cost money and require consent.

Use the skill to scaffold Fabric Apps with TypeScript models, relationships, row-level authorization, GraphQL client calls, and Rayfin CLI configuration. It focuses on the preview workload and tells the agent to check current Microsoft documentation because decorators and signatures may change. Deploying a real app still requires a Fabric workspace, capacity, and an administrator-enabled preview workload.

Route web pages, PDFs, Office files, video, audio, and images through media-specific accessibility tools, then produce JSON and HTML reports with WCAG criteria, severity, source tool, and review status. The skill marks missing tools and out-of-scope checks instead of treating them as passes. Native mobile apps, formal conformance claims, and several interactive behaviors still need separate testing.

Turn an assignment prompt into a rubric that contains everything the evaluator needs, audits omissions and contradictions, and keeps score-bearing criteria separate from checklist subcriteria. The skill can also simulate a real correction locally with the Claude CLI and validate the result against backend rules. Python 3.10 is required, and TEST mode needs `claude` on PATH.

Fetch a YouTube transcript from a supported URL and save it as Markdown and plain text. Optional actions hand the saved transcript to the agent for a summary, bullet list, claim critique, or follow-up questions; the script itself does not run an LLM or require an API key. Python, the transcript package, and network access are required.

Ingest a resume, GitHub repository, or other documents into a reusable experience bank, then tailor an HTML resume to a job description with weighted keywords, STAR rewrites, and a match report. A mock interview probes the same claims from basics to technical and behavioral depth. The skill refuses invented metrics or credentials; browser-only use cannot persist the bank on your computer.