From atum-legion
Use when facing architecture decisions with trade-offs, choosing between multiple approaches, stuck on debugging after 2+ failed attempts, validating before irreversible actions (force push, drop table, migration), requesting a second opinion on a PR, or comparing frameworks/stacks/libraries. Runs multi-model consultation via OpenRouter (jury, debate, or expert mode) and synthesizes perspectives. Do NOT use for factual API questions — use Context7 instead.
npx claudepluginhub arnwaldn/atum-plugins-collection --plugin atum-legionThis skill uses the workspace's default tool permissions.
This skill teaches the General (Claude Code) HOW to use ATUM Legion effectively. Legion is a multi-model consultation layer via OpenRouter that deploys other LLMs as "soldiers" to bring cognitive diversity to strategic decisions.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Calculates TAM/SAM/SOM using top-down, bottom-up, and value theory methodologies for market sizing, revenue estimation, and startup validation.
This skill teaches the General (Claude Code) HOW to use ATUM Legion effectively. Legion is a multi-model consultation layer via OpenRouter that deploys other LLMs as "soldiers" to bring cognitive diversity to strategic decisions.
Activate this skill when:
resolve-library-id → query-docs)Determine whether the question is factual (→ Context7) or strategic (→ continue below).
Before consulting the soldiers, the General MUST analyze the problem in depth across four dimensions:
This produces a structured internal analysis (extended thinking) that will ground the Legion prompt.
Formulate a prompt enriched by the ultra-think analysis:
Contexte: [2-3 phrases sur le projet et la situation]
Analyse préliminaire du General: [points clés de l'ultra-think, hypothèses, angles morts identifiés]
Question précise: [1 phrase]
Contraintes: [limites techniques, budget, timeline]
Ce qui a été tenté: [approches déjà explorées]
Format attendu: [décision, hypothèses, critique, contre-arguments]
| Complexity | Indicators | Tool |
|---|---|---|
| Light | A vs B, quick opinion | consult_free_expert (1 model) |
| Medium | Review, validation, debug | consult_jury (3 models, 3 providers) |
| High | Architecture, multi trade-offs | consult_debate (5-6 candidates, 2 rounds) |
| Critical | Irreversible decision, precision needed | consult_expert (paid, best models) |
Model selection rules:
list_free_experts (or list_all_experts if paid is justified) BEFOREconsult_expert with paid modelsLaunch the consultation with the enriched prompt. Pick the agent:
legion-strategist for free-only consultations (jury, expert mode)legion-commander for critical decisions, fusion analysis, paid model routing, budget managementThe General ALWAYS synthesizes the results himself (never delegated to a weaker model):
Full Legion doctrine: plugins/atum-legion/rules/common/legion-doctrine.md
Commander agent: plugins/atum-legion/agents/legion-commander.md
Strategist agent: plugins/atum-legion/agents/legion-strategist.md
Command: plugins/atum-legion/commands/legion.md