algernon-debate
Design trade-off debate mode for OpenAlgernon. Use when the user runs `/algernon debate [SLUG]`, says "quero debater [topic]", "me desafia sobre trade-offs", "debate tecnico", "discutir decisoes de design", "quando usar X vs Y", or "argumento tecnico". Forces the user to defend a position and exposes nuances they may not have considered. Ends with a synthesis that is exactly what you would say in a technical interview.
Best use case
algernon-debate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Design trade-off debate mode for OpenAlgernon. Use when the user runs `/algernon debate [SLUG]`, says "quero debater [topic]", "me desafia sobre trade-offs", "debate tecnico", "discutir decisoes de design", "quando usar X vs Y", or "argumento tecnico". Forces the user to defend a position and exposes nuances they may not have considered. Ends with a synthesis that is exactly what you would say in a technical interview.
Teams using algernon-debate should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/algernon-debate/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How algernon-debate Compares
| Feature / Agent | algernon-debate | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Design trade-off debate mode for OpenAlgernon. Use when the user runs `/algernon debate [SLUG]`, says "quero debater [topic]", "me desafia sobre trade-offs", "debate tecnico", "discutir decisoes de design", "quando usar X vs Y", or "argumento tecnico". Forces the user to defend a position and exposes nuances they may not have considered. Ends with a synthesis that is exactly what you would say in a technical interview.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# algernon-debate You run a structured technical debate. The user picks a side, defends it, and you press from the opposing position. The synthesis at the end — not which side "won" — is the learning goal: precise conditions under which each approach is the right choice. ## Constants ``` DB=/home/antonio/Documents/huyawo/estudos/vestibular/data/vestibular.db NOTION_CLI=~/go/bin/notion-cli ``` ## Step 1 — Select a Debate Topic Query argumentative cards from the material (these already contain comparisons and trade-offs by design): ```bash sqlite3 $DB \ "SELECT c.id, c.front, c.back FROM cards c JOIN decks d ON d.id = c.deck_id JOIN materials m ON m.id = d.material_id WHERE m.slug = 'SLUG' AND c.type = 'argumentative' ORDER BY RANDOM() LIMIT 5;" ``` Select the card with the clearest two defensible sides. Good topics have no single correct answer — the right choice genuinely depends on context. Examples of strong debate topics: - Fine-tuning vs RAG for domain knowledge injection - Vector database A vs B for a specific use case - LangChain vs LlamaIndex for production pipelines - Centralized vs distributed embedding generation - Cosine similarity vs dot product for retrieval Present: "Debate topic: [TOPIC]. Which side do you take?" AskUserQuestion options: [SIDE_A, SIDE_B] ## Step 2 — Opening Argument AskUserQuestion (free text): > "State your opening argument for [CHOSEN_SIDE]. Be specific — give at least one concrete scenario where your side wins." ## Step 3 — Counter-Argument You now argue the opposing side with the strongest possible objections. Present 2-3 sharp, concrete counter-arguments — not generic ones. Bad counter: "But [SIDE_B] also has advantages." Good counter: "Your argument assumes [specific condition]. In systems where [different condition], [SIDE_B] outperforms because [specific reason]." AskUserQuestion (free text): > "How do you respond to these objections?" ## Step 4 — Rebuttal Round Identify the weakest point in the user's rebuttal and press it directly. AskUserQuestion (free text): > "Final argument — make your best case." ## Step 5 — Synthesis Regardless of who "won" the exchange, deliver a balanced synthesis: ``` Debate synthesis — [TOPIC] [SIDE_A] is the right choice when: - [concrete condition 1] - [concrete condition 2] [SIDE_B] is the right choice when: - [concrete condition 1] - [concrete condition 2] The critical factor is: [one sentence that resolves the trade-off] ``` This synthesis is exactly what a strong technical interview answer looks like — it names the conditions rather than picking a winner. ### Send to Notion ```bash ~/go/bin/notion-cli append --page-id PHASE_PAGE_ID --content "MARKDOWN" ``` Include the topic, the synthesis, and any gaps in the user's arguments. ### Save Memory Append to today's conversation log: ``` [HH:MM] debate session — MATERIAL_NAME Topic: [topic] | Key insight: [one sentence from synthesis] ```
Related Skills
Agent Debate Skill
Spawn multiple sub-agents to debate approaches and converge on the best solution.
algernon-texto
Block-by-block reading mode for OpenAlgernon materials. Use when the user runs `/algernon texto SLUG`, `/algernon paper SLUG`, says "quero ler [material]", "vamos ler [topic] bloco a bloco", "modo texto", or "leitura guiada". Also activates when the user is mid-session and selects /continue between blocks. Paper mode adds structured reflection between major sections.
algernon-synthesis
Cross-material knowledge synthesis session for OpenAlgernon. Use when the user runs `/algernon synthesis`, says "quero conectar os materiais", "sintese entre materiais", "como X se relaciona com Y", "visao geral do curriculo", "integrar o conhecimento", or "ver o quadro geral". Requires at least 2 materials with reviewed cards. Surfaces conceptual bridges across materials and ends with a production scenario challenge.
algernon-sprint
Timed interleaved study sprint for OpenAlgernon. Use when the user runs `/algernon sprint [15|25|45]`, says "sprint de estudo", "sessao cronometrada", "25 minutos de revisao", "modo pomodoro", "quero fazer um sprint", or "revisar varios materiais de uma vez". Cards from all installed materials are shuffled and interleaved. Ends with a post-sprint retrieval test to measure retention gain.
algernon-review
FSRS-4.5 flashcard review session for OpenAlgernon. Use when the user runs `/algernon review`, says "revisar flashcards", "quero revisar", "cards em atraso", "modo revisao", "review session", or asks to practice due cards. Handles all card types (flashcard, dissertative, argumentative), AI evaluation of open-ended answers, automatic FSRS scheduling, N1/N2/N3 promotion, and correction card generation.
algernon-orchestrator
Main orchestrator for the OpenAlgernon personal study system. Use this skill at the start of every study session, or whenever the user runs /algernon, says "quero estudar", "iniciar sessao", "abrir algernon", or asks what materials are available. Also handles the /algernon help command and routes any unmatched command to the right sub-skill.
algernon-interview
Mock technical interview mode for OpenAlgernon. Use when the user runs `/algernon interview [SLUG]`, says "me entrevista sobre [material]", "simula entrevista tecnica", "mock interview", "entrevista de emprego", "quero praticar entrevista", or "me faz perguntas tecnicas". Simulates a senior AI engineering interviewer with adaptive difficulty, follow-up probes, and a full scored report at the end.
algernon-feynman
Feynman Technique study session for OpenAlgernon. Use when the user runs `/algernon feynman [SLUG]`, says "feynman", "quero explicar conceitos", "me testa explicando", "tecnica feynman", "ensinar para aprender", or "quero consolidar [material]". The goal is to expose gaps in understanding by making the user teach concepts back in their own words.
---
name: article-factory-wechat
humanizer
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 Wikipedia's comprehensive "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, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.