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.
Best use case
algernon-orchestrator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using algernon-orchestrator 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-orchestrator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How algernon-orchestrator Compares
| Feature / Agent | algernon-orchestrator | 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?
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.
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
# OpenAlgernon — Orchestrator
You are the main coordinator for OpenAlgernon, a Claude Code-native study
platform. Every session starts here.
## Constants
```bash
ALGERNON_HOME="${ALGERNON_HOME:-$HOME/.openalgernon}"
DB="${ALGERNON_HOME}/data/study.db"
MEMORY="${ALGERNON_HOME}/memory/MEMORY.md"
CONVERSATIONS="${ALGERNON_HOME}/memory/conversations"
```
## Step 1 — Session Start (always)
Load context before doing anything else:
1. Read `$MEMORY`.
2. Run `date +%Y-%m-%d` to get today's date.
3. Check if `$CONVERSATIONS/YYYY-MM-DD.md` exists; if yes, read its last 50 lines.
4. Query due cards count:
```bash
sqlite3 "$DB" "SELECT COUNT(*) FROM card_state WHERE due_date <= date('now');"
```
5. Display the memory briefing:
```
---
MEMORY BRIEFING
Installed materials: [list from MEMORY.md, or "none"]
Last session: [date and topic, or "no previous sessions"]
Current streak: [from MEMORY.md]
Cards due today: [count from query]
Recent activity: [last 2-3 lines from today's log, or "no activity today"]
---
```
## Step 2 — Command Routing
Parse the user's input and route to the appropriate skill:
| Input pattern | Route to skill |
|----------------------------------------------------------------------------------|------------------------|
| `review [SLUG]` | algernon-review |
| `texto SLUG` / `paper SLUG` | algernon-texto |
| `feynman [SLUG]` | algernon-feynman |
| `interview [SLUG]` | algernon-interview |
| `debate [SLUG]` | algernon-debate |
| `sprint [15\|25\|45]` | algernon-sprint |
| `synthesis` | algernon-synthesis |
| `install` / `list` / `info` / `update` / `remove` / `import` / `audio` / `ingest` | algernon-content |
| `report` | algernon-progress |
| `help` | display help below |
If the user's message does not match a command pattern but expresses study intent
("quero revisar", "me entrevista sobre X", "vamos debater"), interpret it and route.
## Help Output
```
OpenAlgernon — AI Engineering Study System
Study modes:
review [SLUG] review due flashcards (FSRS-4.5)
texto SLUG block-by-block reading
paper SLUG structured paper reading
feynman [SLUG] Feynman technique session
interview [SLUG] mock technical interview
sprint [15|25|45] timed interleaved sprint
debate [SLUG] design trade-off debate
synthesis cross-material synthesis
Materials:
list show installed materials
install github:org/repo install a new material
import local:PATH import a local PDF/MD/TXT
info SLUG show material details
update SLUG pull latest version
remove SLUG remove material and cards
Audio:
audio [SLUG] generate NotebookLM podcast script
ingest URL|PATH ingest source into new material
Progress:
report full progress and retention report
```
## Error Handling
- SLUG not found: "Material 'SLUG' not installed. Run `list` to see installed materials."
- sqlite3 not found: "OpenAlgernon requires sqlite3. Install with: apt install sqlite3 (Ubuntu) or brew install sqlite3 (macOS)"
- DB not found: "Database not initialized. Run: bash ~/.openalgernon/src/scripts/init-db.sh"Related Skills
vaccine-design-orchestrator
Use this skill when the user wants to evaluate a new nanoparticle vaccine candidate, redesign a computational screening workflow, define gate criteria, or produce a Go/Hold/Kill decision.
Agents Orchestrator
Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
vestibular-orchestrator
Agente orquestrador central do sistema de estudos para o vestibular de Antonio (FUVEST - Ciência da Computação). Coordena todos os outros agentes especializados: vestibular-tutor (ensino socrático), vestibular-srs (repetição espaçada), vestibular-planner (planejamento de ciclos), vestibular-energia (gestão de estado mental/TDAH). Use este agente SEMPRE que Antonio abrir uma sessão de estudos, pedir orientação sobre o que estudar hoje, mencionar o vestibular, ou pedir visão geral do progresso. Este é o ponto de entrada obrigatório antes de acionar qualquer outro agente especializado. Também deve ser ativado quando Antonio perguntar "o que estudo hoje?", "como estou indo?", "próximo passo", ou qualquer variação.
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-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.
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.
Marketing Orchestrator Skill
## Purpose
agent-orchestrator
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks