Select the appropriate LLM model for each agent based on task complexity and role
원문 언어: 영어
메뉴
SkillsMP는 Hidden-History/ai-memory에서 43개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
수집된 skill 43개 중 40개를 표시합니다.
Select the appropriate LLM model for each agent based on task complexity and role
원문 언어: 영어
Detect content drift of an operator's scaffolded sanctum files (BOND, CAPABILITIES, CREED, INDEX, LORE, MEMORY, PERSONA, PULSE) against the evolving reference templates, and surface recommended add/remove WITH rationale — never a silent overwrite. Use on a…
원문 언어: 영어
Enforce oversight-file caps at session-close, rotate over-cap append-only-logs and registers into dated archive shards, and fix over-cap files non-interactively (including MEMORY.md lossless relocation).
원문 언어: 영어
Two-phase capped startup context loaders for Parzival (activation + session-start)
원문 언어: 영어
Scan oversight tracking files, regenerate bug/TD INDEX views, report STATUS divergences, verify phantom-open bug candidates against git history, and check decision-log body coverage.
원문 언어: 영어
Check ai-memory system status and collection stats
원문 언어: 영어
Check ai-memory system status and collection stats
원문 언어: 영어
Manually save current session context to ai-memory
원문 언어: 영어
Search ai-memory for relevant stored memories
원문 언어: 영어
Search ai-memory for relevant stored memories
원문 언어: 영어
Design agent team structure for parallel work execution
원문 언어: 영어
Research current best practices for any technology, pattern, or coding standard. Use when asking about best practices, conventions, coding standards, recommended approaches, or how should I questions. Searches local knowledge first, then web for current…
원문 언어: 영어
Search memory system with advanced filtering and intent detection
원문 언어: 영어
Research current best practices for any technology, pattern, or coding standard. Use when asking about best practices, conventions, coding standards, recommended approaches, or how should I questions. Searches local knowledge first, then web for 2024-2026…
원문 언어: 영어
Creates and maintains an up-to-date wiki of the user's current project, in-session, while you work — a dedicated wiki/ directory with a quickstart entrypoint plus section pages, grounded in source and git evidence. Claude Code itself authors the pages; a…
원문 언어: 영어
Tracks the source-of-truth for each part of the user's own project — registry schema, templates, and engine (consult / detect-propose / verify). Detects file and directory drift (content-digest and directory tree-digest), runs a machine-local shadow-git…
원문 언어: 영어
Generic and BMAD agent selection, instruction preparation, and activation routing
원문 언어: 영어
tmux agent lifecycle management for non-Claude providers
원문 언어: 영어
Load Parzival cross-session memory from Qdrant
원문 언어: 영어
Enforce hygiene on per-operator sanctum files (LORE/MEMORY compaction, PERSONA Evolution-Log section-cap, CREED/BOND cap-check) — line-cap enforcement, anchored-summarization compaction at ~80% of cap, the prune-vs-archive decision, and a conservation 0-lost…
원문 언어: 영어
Save a Parzival session decision to Qdrant for cross-session memory and L2 retrieval
원문 언어: 영어
Initialize sanctum directory for an agent. Runs deterministic First Breath scaffolding — creates folder structure and writes template-substituted files.
원문 언어: 영어
Search GitHub issues, PRs, commits, and CI results with semantic search and filters
원문 언어: 영어
Check AI Memory system status
원문 언어: 영어
Search GitHub issues, PRs, commits, and CI results with semantic search and filters
원문 언어: 영어
Synchronize GitHub issues, PRs, commits, and CI results to AI Memory
원문 언어: 영어
Search Jira issues and comments with semantic search and filters
원문 언어: 영어
Synchronize Jira issues and comments to AI Memory
원문 언어: 영어
Load Parzival behavioral constraints as context reminder
원문 언어: 영어
Scan code-patterns collection for stale memories by comparing against GitHub code blob data
원문 언어: 영어
Toggle auto_update_enabled kill switch for automatic memory updates
원문 언어: 영어
Purge old memories from Qdrant collections with safety guards
원문 언어: 영어
Manually re-evaluate freshness for code-patterns memories
원문 언어: 영어
Manually save current session to memory
원문 언어: 영어
Display current memory system configuration and settings
원문 언어: 영어
Save Parzival session handoff document to Qdrant for cross-session memory
원문 언어: 영어
Save a Parzival insight or learning to Qdrant for cross-session memory
원문 언어: 영어
Generic agent instruction preparation and activation -- Layer 3a
원문 언어: 영어
Shared agent lifecycle management -- send, monitor, review, accept/loop, shutdown, summary
원문 언어: 영어
Select the appropriate LLM model for each agent based on task complexity and role
원문 언어: 영어