Menu
Skills in this repository
SkillsMP has collected 5,485 skills from majiayu000/claude-skill-registry. Open a skill to review its source and details.
majiayu000/claude-skill-registryShowing 40 of 5,485 collected skills.
Manage current Claude Code session metadata — set project, tags, and summary on session.md via Obsidian CLI. Use this skill whenever the user wants to tag, categorize, name, label, summarize, or organize the current session. Triggers on phrases like "tag this…
セッション間の学習と記憶の永続化を管理。Use when user asks about previous sessions, history, or to continue from before. Do NOT load for: implementation work, reviews, or ad-hoc information.
Source text: Japanese
セッション間の学習と記憶の永続化を管理。Use when user asks about previous sessions, history, or to continue from before. Do NOT load for: implementation work, reviews, or ad-hoc information.
Source text: Japanese
Manages cross-session learning and memory persistence. Use when user asks about previous sessions, history, or to continue from before. Do NOT load for: implementation work, reviews, or ad-hoc information.
Source text: Japanese
セッション間の学習と記憶の永続化を管理。Use when user asks about previous sessions, history, or to continue from before. Do NOT load for: implementation work, reviews, or ad-hoc information.
Source text: Japanese
Migrate session logs from markdown to JSON format. Use when PRs contain markdown session logs that need conversion to the new JSON schema, or when batch-migrating historical sessions.
Migrate session logs from markdown to JSON format. Use when PRs contain markdown session logs that need conversion to the new JSON schema, or when batch-migrating historical sessions.
Builds session-scoped temporary memory palaces for extended conversations. Use when tracking state across interruptions in a multi-step project.
Capture session learnings and propose targeted improvements to docs, skills, or core agent instructions. Evidence-based only - no theoretical improvements. Closes the feedback loop directly by updating existing files.
Use when resuming work on existing project - lists registered projects, reads project_state.md, summarizes current state, identifies where to continue. Trigger: 'pick up where I left off', 'continue project', 'what was I working on', 'resume session'.
Resume previous work from archived session with full context restoration
Resumes work from a previous session using handoff notes, checkpoints, or compact state. Use at the beginning of a new session to restore context and continuity.
Context window auto-reset procedures for Ralph agents. Use when context approaches 70% capacity during long tasks. Use proactively to monitor token usage and create checkpoints.
Context window auto-reset procedures for Ralph agents. Use when context fills up during long tasks.
Prime context for a task — calls context_continue + context_retrieve to find relevant files before starting work. Minimizes token usage by reusing cached context and only reading what's needed.
Enforce line budgets and rotate or split large context files.
Memory management system for Claude Code — Student Loop, Smart Context, Auto Learn, Session Handoff, Correction Cycle. Triggered by memory commands (/save, /reflect, /handoff, /check) or memory-related questions. Not for general programming tasks.
Auto-detect and load minimal context from Skills folders using progressive disclosure, trimming 1400 tokens from system prompt through metadata-first loading. Use when optimizing token usage, managing multiple skills, or preventing context bloat. Load YAML…
Teaches the agent how to natively ingest and trust the V3 auto-synced memory files instead of hallucinating project state.
Chase down answers before asking. Hunt the archive. Forces Claude to search before questioning, preventing redundant questions about concepts already documented in theory/tiers/ and memory.
Smart Forking - Find and fork from relevant historical sessions using parallel memory search across claude-mem, memvid, handoffs, and ledgers
Use when reading files or command output of unknown size to avoid blind truncation and context loss. Triggers: 'this file is huge', 'output was cut off', 'large file', 'how should I read this', or when about to use head/tail to truncate output. Also loaded as…
Use when reading files or command output of unknown size to avoid blind truncation and context loss
Capture current session state without stopping
Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.
Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.
Store information in the hierarchical memory system. Supports three tiers: working (ephemeral), episodic (recent events), and semantic (permanent patterns). Use for learning from observations. Keywords: memory, store, learn, remember, episodic, semantic,…
策略性压缩 — 在逻辑边界手动压缩上下文，而非任意自动压缩。保留关键决策和约束，丢弃中间探索过程。
Source text: Chinese
Query the unified event stream for recent activity across all surfaces. Use when user asks about recent conversations, what happened on iMessage/CLI/wake cycles, or wants to see cross-surface activity. Trigger words: stream, recent activity, what happened,…
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, context-pack, task-ledger, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks,…
MANDATORY sync rules for CLAUDE.md and agents.md files. This skill MUST be activated whenever editing CLAUDE.md, agents.md, backend/CLAUDE.md, or backend/AGENTS.md. Failure to sync causes drift between AI tools.
Synchronize shared rules into agent context files and headers.
Promotes important observations from memory systems (Claude-mem, Serena) to SSOT (decisions.md, patterns.md). Use when user mentions SSOT promotion, sync memory, save learnings, or before Plans.md cleanup. Do NOT load for: ad-hoc notes, implementation work,…
Compressed communication using symbols and abbreviations. Use when context is limited or brevity is needed.
Semantic tool search with embeddings for scalable tool discovery. Enables on-demand tool loading to reduce context usage by 90%+ for large tool libraries.
Token hygiene and memory efficiency manager. Specializes in the "Pull, Don't Push" doctrine to maintain clean context windows and prevent token bloat.
Episodic memory manager. Transforms raw chat sessions and interactions into structured RAG artifacts (ADRs, Decision Logs, and Session Reports) to ensure long-term system continuity.
Search and analyze Claude Code transcripts for past decisions, solutions, and discussions. Use when recalling past context, finding solutions to previously-solved problems, understanding session history, or restoring context after compact/clear.
Analyzes current git status and work in progress. Use when: user wants to understand current state, check work status, or see what's changed.
Upstash context management and serverless Redis/Kafka