Bumblebiber
44 verified skills759 total stars
o9k-curate
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.
tools19
o9k-session-start
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.
development19
o9k-update
Update flow for its-over-9k (hmem). Runs `npm update -g`, syncs skills, applies migrations, verifies hooks, shows the changelog. Use when the user asks to update/upgrade hmem, o9k, o9k-mcp, or its-over-9k (any language), or when the startup version-check flags a new release. Runs the npm update itself — don't assume it's already done.
tools19
o9k-using-hmem
Meta-skill that establishes how and when to use hmem skills. Loaded at session start. Defines mandatory habits for memory, dispatch, and lookup operations.
tools18
o9k-new-rule
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.
testing18
o9k-search
Search hmem memory for things referenced without an ID. Trigger when user refers to past conversations ("letzte Woche", "gestern", "remember when", "we talked about"), mentions proper names unknown this session, uses definite articles assuming shared context ("der Bug mit X", "the issue we had"), or seems to assume you know something. If you think "the user assumes I know this" — search first, ask second. Combines full-text search with time window from phrasing. Trigger on casual/vague references. Do NOT trigger for explicit ID lookups like "read P0048".
testing18
hmem-activate
Activate a project mid-session via load_project, then check for and fix misrouted O-entry exchanges. Use whenever the user says "aktiviere Projekt X", "lade Projekt X", "load project X", "wechsel zu Projekt X", or switches project context during a session. ALSO use when you are about to call load_project mid-session for any reason — even if the user didn't explicitly ask to switch projects.
testing18
hmem-context
Load specific context from hmem based on what is needed RIGHT NOW. Use when load_project output is not enough for the current question.
testing18
hmem-session-start
Load project context at session start via load_project. Includes recent O-Entry summaries automatically. Run at the beginning of every Cortex session.
tools18
hmem-search
Search hmem memory for things referenced without an ID. Trigger when user refers to past conversations ("letzte Woche", "gestern", "remember when", "we talked about"), mentions proper names unknown this session, uses definite articles assuming shared context ("der Bug mit X", "the issue we had"), or seems to assume you know something. If you think "the user assumes I know this" — search first, ask second. Combines full-text search with time window from phrasing. Trigger on casual/vague references. Do NOT trigger for explicit ID lookups like "read P0048".
testing18
hmem-using-hmem
Meta-skill that establishes how and when to use hmem skills. Loaded at session start. Defines mandatory habits for memory, dispatch, and lookup operations.
tools18
o9k-release
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'.
development18
o9k-consolidate
Merge all session checkpoint summaries into one final O-Entry summary. Run at end of sessions with 2 or more checkpoints.
testing18
o9k-context
Load specific context from hmem based on what is needed RIGHT NOW. Use when load_project output is not enough for the current question.
testing18
o9k-recall
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.
data-ai18
o9k-subagent
Template for sub-agents dispatched by o9k-dispatch. Receive one task, return ONLY the result. No preamble, no explanation, no sign-off.
data-ai18
o9k-setup
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'.
tools18
hmem-sync-setup
Set up hmem-sync for cross-device memory synchronization. Use when the user wants to sync memories between devices, says "sync einrichten", "setup sync", "hmem-sync", or when /hmem-config detects hmem-sync is not installed. Covers first-device setup, additional-device restore, and MCP auto-sync configuration.
tools17
o9k-write
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.
documentation17
o9k-search
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'.
testing17
hmem-write
Complete protocol for writing to hmem long-term memory. Covers tree navigation (find correct insertion point before writing), prefix selection (L/E/D/P/N/R/I/H/...), hashtag assignment, title/body formatting, deduplication, and append-vs-write decisions. Do NOT call write_memory or append_memory directly without this skill — skipping the protocol creates duplicates and misplaced entries. Invoke whenever you are about to persist anything: lessons learned, bug fixes, architecture decisions, project state, user preferences, E-entries, N-entries, or P-entry updates. Also invoke when the user says "remember this", "save this", "don't forget", "store this", "write that down", "add to memory", "create an E-entry", "log this", or invokes /hmem-write.
development17
o9k-activate
Switch active project mid-session via load_project, then fix any misrouted O-entry exchanges. Use when the user says 'aktiviere/lade Projekt X', 'switch to project Y', or whenever you'd otherwise call load_project mid-session.
tools17
hmem-curate
Curate hmem memory — your own or a foreign .hmem file. Systematically review entries, mark obsolete/irrelevant/favorite, fix titles, consolidate duplicates. Use when asked to "aufräumen", "clean up memory", "curate", "Speicher bereinigen", "tidy up", or when memory_health() shows issues.
tools17
hmem-subagent
Template for sub-agents dispatched by hmem-dispatch. Receive one task, return ONLY the result. No preamble, no explanation, no sign-off.
data-ai17
o9k-config
View and change hmem memory settings, hooks, sync, and checkpoints. Use on /o9k-config, or when the user asks why context is huge, how to change auto-save, how often checkpoints fire, or how to set up sync.
testing17
hmem-dispatch
Dispatch an isolated sub-agent for a specific task. Sub-agent receives only the task definition, returns only the result in [RESULT]...[/RESULT] format. ALWAYS use for: searching (codebases, files, skills, texts, plans, specs, docs — any 'does X exist?' or 'find Y' question); calculations; writing isolated sections. If the task is 'look something up', 'check if there's a plan', 'search for X', 'find the spec' — dispatch, never search yourself.
development17
o9k-subagent
Template for sub-agents dispatched by o9k-dispatch. Receive one task, return ONLY the result. No preamble, no explanation, no sign-off.
data-ai17
hmem-setup
Set up and configure the hmem memory system. Run this skill to install hmem, initialize the MCP server, deploy skill files, and register auto-memory hooks for Claude Code, Gemini CLI, or OpenCode. Covers first-time setup ('set up memory', 'initialize hmem', 'first-time setup', 'install hmem'), manual installation, and post-setup verification.
tools17
hmem-new-project
Create a new project (P-entry) in hmem. Use this skill whenever: the user asks to create/add/set up a new project in hmem ("neues Projekt", "new project", "Projekt anlegen", "add project", "P-Entry erstellen", "in hmem aufnehmen", "track this project", "create an entry for"); OR you are about to call write_memory with prefix="P"; OR any agent is told to register or document a project in memory. Never create P-entries manually — this skill handles schema enforcement, section setup, and O-entry linking automatically. Uses the create_project MCP tool.
tools17
o9k-new-error
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'.
documentation17
o9k-migrate-o
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.
development17
o9k-dispatch
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.
data-ai17
o9k-wipe
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.
data-ai17
o9k-sync-setup
Set up o9k-sync for cross-device memory sync. Use on 'sync einrichten', 'setup sync', or when /o9k-config detects o9k-sync is missing. Covers first-device setup, additional-device restore, and MCP auto-sync.
tools17
o9k-new-project
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'.
documentation17
hmem-update
Post-update checklist for hmem-mcp and hmem-sync. Run after npm update or when hmem detects a version change. Covers skill sync, entry migration, schema enforcement, O-entry curation, and smoke tests. Use when the user says 'update hmem', 'hmem updaten', or when the startup version-check detects a new version.
tools17
o9k-read
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().
tools17
hmem-wipe
Prepare for conversation context clear (/clear): save high-value knowledge, update project Next Steps, then instruct user to type /clear for automatic context restoration. Invoke when the user wants to clear the conversation window — not when deleting data/entries. Triggers: "/wipe", "clear context", "wipe context", "context is full/too big/getting large", "prepare for /clear", "start fresh", "context cleanup", approaching token limit. Do NOT invoke for: deleting hmem entries, clearing terminal output, cleaning up nodes/duplicates.
data-ai16
hmem-recall
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.
data-ai16
hmem-consolidate
Merge all session checkpoint summaries into one final O-Entry summary. Run at end of sessions with 2 or more checkpoints.
testing16
hmem-migrate-o
Migrate O-entries to the new project-bound 5-level structure (v5.3+). Each O-entry gets permanently bound to its P-entry by matching sequence numbers (O0048 <-> P0048). Run this once after updating to v5.3. Use when the user says "migrate O-entries", "O-Eintraege migrieren", "hmem migrate", or when hmem-update detects that the O-entry structure needs migration. Also use proactively if you notice O-entries are still using the old flat format (L2->L4->L5 without L3 batches).
development16
hmem-new-error
Create a new error/bug entry (E-entry) in hmem. Use this skill whenever: the user wants to log a bug, document an error, file a bug report, track a problem ("Bug loggen", "Fehler eintragen", "E-Entry anlegen", "log this error", "track this bug", "document this problem", "in hmem festhalten als Fehler"); OR you are about to call write_memory with prefix="E"; OR a bug or unexpected behavior has been found and should be persisted in long-term memory. Never write E-entries manually without this skill — the format is strict and the auto-scaffold handles structure automatically.
development16
hmem-read
Load long-term memory from hmem. Use when: user types /hmem-read or says 'load memory', 'check your memory', 'what do you remember', 'show me the project', 'continue where we left off', 'was weißt du über...'; starting work with no L1 summaries in context; after /compact or context reset to reload knowledge; before significant work to anchor with prior context; user asks about a specific project, error, or topic visible in L1 summaries; user says 'pick up where we left off', 'resume', 'Woran haben wir gearbeitet', 'Was war der letzte Stand'. Calls read_memory() or load_project() immediately. Also covers search, prefix filter, context_for, stale detection, find_related, memory_stats, memory_health. For cross-project context (reading a second project without switching the active one), use read_project() — e.g. when working on MAIMO but needing hmem API context.
development16
hmem-config
View and change hmem memory settings, hooks, sync, and checkpoint configuration. Use this skill whenever the user types /hmem-config, asks to change memory settings, adjust parameters, tune bulk-read behavior, configure auto-checkpoints, manage hmem-sync, or troubleshoot memory-related issues. Also trigger when the user asks things like 'how often does auto-save fire', 'why is my context so large', 'change checkpoint to auto', 'how many tokens does startup cost', or 'set up sync'.
testing14