Commands
Commands Reference
The Linguistic Agent Skills suite provides 10 slash commands. Every command has a natural-language equivalent — the linguistic-orchestrator routes both identically.
Command Overview
| Command | Purpose | Natural Language Equivalent |
|---|---|---|
/linguistic:lifecycle | Enter the 5-phase pipeline | "help me build an LLM for Yoruba" |
/linguistic:explore | Investigate a language/corpus interactively | "what's in this CulturaX subset?" |
/linguistic:decide | Force a strategic decision | "decide on the transfer source" |
/linguistic:propose | Generate a 5-phase plan | "propose a roadmap for Khmer" |
/linguistic:findings | List findings by severity | "what are the issues" |
/linguistic:review | Full state + findings + history | "where are we?" |
/linguistic:status | One-line phase summary | "current phase?" |
/linguistic:spec | Create/edit a workspace spec | "draft a tokenizer spec" |
/linguistic:rollback | Restore prior workspace state | "rollback to last good state" |
/linguistic:help | Show this list | "help" |
Usage Pattern
Commands are used at decision points in the pipeline:
- Start:
/linguistic:lifecycleor natural-language trigger - Explore before committing:
/linguistic:explore [language] - Check status mid-session:
/linguistic:status - Force a pending decision:
/linguistic:decide [topic] - Generate a plan:
/linguistic:propose - Review all findings:
/linguistic:findings - Full briefing:
/linguistic:review - Document decisions:
/linguistic:spec [type] - Undo a wrong turn:
/linguistic:rollback
Was this page helpful?
Edit on GitHub
Last updated on
linguistic-lexicon
Lexicography for ML — dictionary-building methodology, sense splitting/lumping decisions, MWE inventories for RAG glossary injection and MT post-edit, citation-form conventions, variant handling. Optional Mindset specialist.
/linguistic:help
Show all linguistic commands and their natural-language triggers.