Loading...
Loading...
Found 57 Skills
Write and save an OpenSEO report as one self-contained HTML page. Use when a skill has finished its research, and whenever the user asks for a report, check-in, or summary, or names a report template.
Runs the "¿Qué tan AI First sos?" self-assessment with one person, in Spanish — 9 multiple-choice questions, one at a time, plus "Si fueras un animal, ¿cuál serías?" — computes their AI adoption level (1 to 6) with fixed rules, writes a short read per area, saves the result as a dated Markdown file in their node, and builds their profile page (level, journey, five areas and a 3D mascot dressed as their animal) as a self-contained HTML that works offline and downloads as PDF. Use it when someone says "hagamos el test", "test de madurez", "qué tan AI First soy" or asks to measure their AI adoption at the start or end of a course.
Turn complex explanations into a one-page visual HTML explainer: the model writes only an extended Markdown content draft, while the skill’s bundled CLI handles templates, components, automatic SVG layout, and STE controlled-writing checks to produce a single-file page in one call. Use this skill as well when the user says `/answer-me-with-html config` or wants to change settings (automatically opening the browser, always-on mode, default theme). Proactively use it, without waiting for the user to ask, whenever an answer involves any of the following: ≥3 interrelated concepts; a flow/protocol/architecture with branches or multiple participants; a comparison or trade-off across ≥3 dimensions; a hierarchy (table of contents, modules, taxonomy); an evolutionary history or stages; or the user says "explain the principles / I didn’t get it / draw a diagram / explain this codebase / explain it with HTML / explain visually." Do not use it for: short Q&A that can be answered in under 200 characters, commands that need to be copied and executed immediately, pure code modifications, or when the user explicitly requests plain text.
Generate a self-contained HTML report that debugs what is in a Claude Code or Codex session's context window and how every token is spent — context budget, the hidden cost of retained thinking, the dumb-zone cutoff, loaded CLAUDE.md/skills, and the full history.
Turn a YouTube video, a web article, or several sources at once into one set of didactic study notes, written as a self-contained HTML page under ~/take-notes/html_reports and opened in the browser.
Run a Karpathy-style LLM council (3-stage multi-agent evaluation) on top of the existing orca orchestration: N seats independently answer a question, the answers are BLIND peer-ranked (identities stripped so a model can't favour its own), and a chairman synthesizes the final answer. The orchestration makes the model calls; harness/scripts/council.py does the deterministic protocol math (anonymization, mean-rank aggregation, dissent, anchor guard, transcript). Use when the user says "run a council", "llm-council", "panel of models", "blind peer-rank these answers", "ensemble + chairman", or invokes /council. Stage-4 is a MANDATORY HTML report, rendered inside council.py itself (offline, no CDN, no external skill): every `rank` writes a NEW versioned self-contained report (llmwiki/html/council/council-report-NNN-seed<seed>.html) — opinion cards (persona name + lens), a blind-vote table, and a dashboard. Isolated in try/except so a render bug never kills the core transcript.
Generate HTML artifacts for code review, PR explanation, and codebase understanding — rendered diffs with inline annotations, severity-coded findings, refactor risk maps, before/after migration views, and subsystem walkthroughs. Use whenever the user wants to review, explain, or understand a PR, refactor, codebase area, or subsystem — especially before merging, when onboarding others to a change, or when the GitHub diff view doesn't show enough context. Default to attaching an HTML explainer to every non-trivial PR.
Find where the repo's own instructions, the user's global instructions, hooks, lint and CI contradict or duplicate what skilly installed. Writes an HTML report, edits nothing.
Restructure and rewrite articles and notes into skeletal bullet lists in telegraph style, omitting words that can be inferred from context and conveying one idea per line. Use for requests such as “write a report,” “turn it into an HTML report,” “use telegraph style,” or “shorten the bullet points.” Do not use for requests that merely ask to proofread or refine a report while retaining paragraph format. Do not invoke independently for technical slides; act only as a dependency of the `shunk031-writing-technical-slides` skill, handling style alone. Do not use to create slide files.