Run TypeScript type checking for this repository. Use when the user asks to typecheck, validate TypeScript changes, or inspect compiler errors. Execute `bun run typecheck`, summarize any errors, and suggest targeted fixes when type errors remain.

Sync `messages/en.json` and `messages/ja.json` for this repository. Use when the user asks to update translations, fill missing Japanese strings, or remove stale i18n keys. Run `bun run build` before reading translations, then add missing Japanese entries, fill empty values, remove stale keys, preserve key order from `en.json`, and keep placeholders, ICU syntax, and brand names unchanged.

Run repository linting and formatting with auto-fix. Use when the user asks to fix lint issues, run formatting, or clean up code style. Execute `bun run lint:fix`, then `bun run format`, and report any remaining issues that need manual attention.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Start the local development server for this repository. Use when the user asks to run the app locally, start the Next.js dev server, or check whether the dev server boots. Execute `bun dev` and report when the server is ready or if startup errors occur.

Generate and optionally apply Drizzle database migrations for this repository. Use when the user asks to create migrations from schema changes, inspect generated SQL, or run database migrations. Execute `bun run db:generate`, show the generated SQL for review, and only run `bun run db:migrate` if the user explicitly asked to apply migrations.

Create a git commit for staged and unstaged changes in this repository. Use when the user asks to commit the current work, prepare a commit message, or stage and commit changes. Review git status and diffs, follow recent commit message style, avoid staging secrets such as .env files, create a concise conventional commit message, make the commit, and verify the result.

Hmem write protocol — picks prefix (L/E/D/P/N/R/I/H…), tree location, and tags, and detects duplicates before persisting. Use before any write_memory or append_memory call (skipping it creates duplicates and misplaced entries), or when the user says 'remember this', 'save this', 'log this', or invokes /o9k-write.

Prep for /clear: save high-value knowledge and update project Next Steps, then prompt the user to clear. Use on /wipe, 'clear/wipe context', 'context is full', or 'start fresh'. Not for deleting hmem entries, clearing terminal output, or cleaning up nodes.

Meta-skill that establishes how and when to use hmem skills. Loaded at session start. Defines mandatory habits for memory, dispatch, and lookup operations.

Template for sub-agents dispatched by o9k-dispatch. Receive one task, return ONLY the result. No preamble, no explanation, no sign-off.

First-time install of hmem: MCP server, skill files, and auto-memory hooks for Claude Code, Gemini CLI, or OpenCode. Use on 'set up memory', 'install hmem', 'initialize hmem', or 'first-time setup'.

Mandatory entry point for every Cortex session — invoke at conversation start, after /clear, and after any load_project call. All stable context (H-entries, projects, device, sync) is pre-injected by the hook — no read_memory(mode='essentials') needed. Surfaces pending git work, Next Steps + open T-tasks, and runs the O-entry routing check.

Search hmem when the user references something without an ID — past conversations ('letzte Woche', 'remember when'), unknown proper names, definite articles assuming shared context ('the bug we had', 'das Schema von gestern'), or asks whether a schema/rule/decision is documented. Search first, ask second. Skip for explicit ID lookups like 'read P0048'.

Pre-publish checklist for its-over-9k: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.

Dispatch a Haiku sub-agent to search hmem for relevant memories. Sub-agent returns matching entries as ID + one-line summary. Main agent context stays clean.

Load long-term memory from hmem via read_memory or load_project. Use when starting fresh with no L1 summaries, after /compact, when the user asks 'what do you remember', 'continue where we left off', 'was war der letzte Stand', or about a project/topic visible in L1 summaries. Covers search, prefix filter, find_related, stale detection, and cross-project read_project().

Add a new rule and place it correctly — decide between a cross-project R-entry and a project-specific subnode under the active project's Rules section. Use whenever the user says 'neue Regel', 'Regel hinzufügen', 'new rule', 'add a rule', or invokes /o9k-new-rule. Critical safeguard: project-specific rules placed as R-entries pollute the session-start Rules listing across every project — get the scope right BEFORE writing.

Create a new P-entry (project) in hmem via create_project — handles schema, section setup, and O-entry linking. Use when the user asks to add/register/track a new project ('neues Projekt', 'P-Entry erstellen'), or before any write_memory with prefix='P'.

Create a new E-entry (bug/error) in hmem with the strict 5-level scaffold. Use when the user wants to log a bug, file a report, or document an error ('Bug loggen', 'log this error', 'Fehler eintragen'), or before any write_memory with prefix='E'.

Migrate O-entries to the v5.3+ project-bound 5-level structure (each O00XX bound to its P00XX). Use on 'migrate O-entries', when o9k-update flags a structure migration, or when you notice O-entries still in the old flat L2→L4→L5 format.

Dispatch an isolated sub-agent that returns only [RESULT]...[/RESULT]. Use for any search, lookup, 'does X exist?', 'find Y', calculation, or isolated writing — never do these inline when dispatch fits.

Curate an .hmem file (your own or foreign) — mark obsolete/irrelevant, fix titles, consolidate duplicates, repair broken links. **Requires the `hmem-curate` MCP server** (skill prompts the user to enable it on entry). Use whenever the user says 'aufräumen', 'memory aufräumen', 'Speicher aufräumen', 'hmem aufräumen', 'clean up memory', 'tidy up hmem', 'curate memory', 'consolidate duplicates', 'merge duplicate entries', 'fix broken links', 'kümmer dich um die Memory', or invokes /o9k-curate. Also trigger when `memory_health()` flags BLOCKER/WARNING issues, when a P-entry's load_project output exceeds 4k tokens (session-start noise check defers to this skill), or before any batch cleanup of L, E, D, P entries. Skipping this skill and editing memory directly bypasses health checks, severity triage, and obsolete-chain integrity — never curate without it.

Load specific context from hmem based on what is needed RIGHT NOW. Use when load_project output is not enough for the current question.