getting-started
Guided introduction to Olympus — capabilities overview and your first /plan workflow
What this skill does
# Welcome to Olympus Olympus is a multi-agent orchestration layer for Claude Code. It gives you 20+ specialized AI agents, a structured development workflow (`/plan`), and a self-learning system that improves with every session. This guide walks you through the key capabilities and gets you to a real result in your project in under 5 minutes. --- ## What Olympus Can Do **Multi-agent orchestration** — Olympus automatically delegates work to specialist agents (architects, searchers, frontend engineers, QA testers) and routes each task to the right model tier (Haiku/Sonnet/Opus) to balance speed and quality. **`/plan <task>`** — The AI-DLC structured workflow. Olympus interviews you to clarify requirements, produces a written plan you approve, then delegates construction to the right agents. Best for features, refactors, and anything non-trivial. **`/ultrawork <task>`** — Maximum performance mode. Runs agents in parallel, doesn't wait for confirmation. Use when you need speed and the task is clear. **`/ascent <task>`** — Persistence loop. Olympus will not stop until every todo is complete. Use when you need guaranteed completion. **Self-learning** — Olympus records patterns and preferences across sessions. Future runs benefit from what past runs discovered. --- ## Your First Real Task Let's use `/plan` on your actual project right now. **Step 1 — Open Claude Code in your project directory** (you're likely already there). **Step 2 — Pick a real task.** Think of something you've been meaning to do: - Add a feature or endpoint - Refactor a messy module - Write tests for an untested area - Fix a known bug or improve error handling **Step 3 — Start the plan.** Type something like: ``` /plan add input validation to the user registration flow ``` or ``` /plan refactor the database layer to use the repository pattern ``` **What happens next:** 1. **Inception** — Olympus interviews you with targeted questions to clarify scope, edge cases, and constraints. Answer honestly; vague answers produce vague plans. 2. **Plan review** — You'll see a written plan before any code is touched. Request changes or approve it. 3. **Construction** — Olympus delegates implementation to specialist agents. You can watch progress or step away. The whole cycle for a medium feature takes 15-30 minutes of AI work, with you approving at key checkpoints. --- ## Quick Reference | Command | When to use | |---------|-------------| | `/plan <task>` | Features, refactors, anything that needs a plan first | | `/ultrawork <task>` | Well-defined tasks where speed matters | | `/ascent <task>` | Must-complete work — Olympus won't stop until done | | `/deepsearch <query>` | Find anything in the codebase | | `/analyze <target>` | Deep investigation of a file, function, or bug | | `/olympus-default` | Make Olympus your default mode for every session | --- ## Next Steps - Run `/olympus-default` to activate Olympus automatically in every Claude Code session. - Run `/plan` on your first real task. - Run `/deepsearch` or `/analyze` to explore unfamiliar parts of your codebase. For full documentation, see the README or run `olympus info`.
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.