Content
film-companion
Provides pre- and post-viewing context for a specific film to make it more rewarding to watch. Pre-viewing mode primes attention without spoilers — why the film matters, its moment…
Productivity
handoff
Use when ending or pausing a Claude Code session whose work must continue in a fresh session — user says "create a handoff", "write a handoff", "I'm ending this session", "prepare …
Productivity
context-saver
Token-saving execution layer for OpenClaw v2.0. Runs skill commands in sandboxed subprocesses where only compact summaries enter the context window. Provides session continuity via…
Productivity
memorylane
Zero-config persistent memory for Claude with automatic cost savings. Use when you need to remember project context, reduce API token costs, track learned patterns, manage memories…
AI / ML
integration-supermemory
Connect Supermemory (fast scalable memory + context engine for AI agents — add/search/graph memories with optional project scope) to a self-hosted Hermes Agent over SSH via Superme…
Productivity
total-recall
The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidate…
Productivity
context-engine
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and e…
DevOps
durable-context-maintenance
Keeps repo-local agent context accurate after code and workflow changes. Use when docs/ai, AGENTS.md, runbooks, or context entrypoints have drifted from the codebase, after major f…
AI / ML
ctx2skill
Faithful reproduction of Ctx2Skill (arXiv:2604.27660v2) — multi-agent self-play framework that autonomously discovers, refines, and selects context-specific skills from complex doc…
Automation
hermes-tag
Context-selection layer for Feishu/Lark and Slack groups: @-mention the agent and it replies in-thread from bounded per-chat memory plus selected evidence — replies only when menti…
Productivity
context-persistence
Pull what we already know about a topic before re-explaining. Say "what do we know about <topic>", "give me the prior context", or "remind me where we left off". Fires at session s…
Productivity
clawdi
Cross-agent long-term memory and session history capturing user preferences, coding habits, projects, past bugs, architecture decisions, and conversations across multiple agents. S…
Automation
agentfeeds
Use AgentFeeds as a ready-to-read cache of fresh local context before scanning skills, searching the web, or re-fetching APIs. It keeps subscribed streams like calendar, inbox, Git…
Engineering
prepare-branch-context
Use when starting work on a branch and needing full context before answering questions, reviewing code, or implementing changes. Analyzes the diff from the base branch, commit hist…
AI / ML
zeref-os
Zeref OS — local-first context and memory engine for AI-assisted work. Harness-agnostic, model-agnostic, privacy-first. Flat memory layout, per-project wiki, append-only pattern lo…
AI / ML
build-local-context-builder
Orchestrates a multi-agent team (infra-architect, schema-designer, collector-engineer, processor-engineer, integration-qa) to implement the full local-context-builder pipeline from…
AI / ML
Foundation Plr
It is clear you have built a sophisticated research pipeline, but "context amnesia" in LLMs often stems from context fragmentation—where the instructions are present but spread acr…
Productivity
Mcp Claude Code Browser Tools
mode: code instructions: general: - "Status Prefix: Begin EVERY response with either '[MEMORY BANK: ACTIVE]' or '[MEMORY BANK: INACTIVE]'" - "Implement features and maintain code q…
Productivity
Programming
mode: code instructions: general: - "Status Prefix: Begin EVERY response with either '[MEMORY BANK: ACTIVE]' or '[MEMORY BANK: INACTIVE]'" - "Implement features and maintain code q…
Productivity
capture-context
Captures reusable knowledge from conversations, documents, links, notes, and messages, then routes it into workspace files so future sessions begin with richer context. Triggers on…
Productivity
bettermemory
Verification-grade memory between sessions. Use bettermemory's MCP tools (memory_search, memory_show, memory_write, memory_verify, memory_record_use, etc.) instead of writing to fi…
Productivity
agent-recall
Use Agent Recall to find prior coding-agent conversations across Claude Code, Codex, and OpenCode. Use proactively when context may exist in another chat, session, or agent; when t…
Productivity
context-bundler
Interactively creates technical bundles of code, design, and documentation for external review or context sharing. Conducts brief discovery to confirm targets and format, then pack…
Productivity
draft-learn
Captures learnings, decisions, or reminders into the Draft workspace. Accepts free-form text, structured tags, or runs a short conversational flow when invoked without arguments. R…
Documentation
grill-with-docs
立てた計画を、既存ドメインモデル・用語集 (CONTEXT.md) と決定記録 (ADR) に照らして 1 問ずつ容赦なく詰める「グリル」セッション。曖昧な語を正規語に研ぎ、コードとの矛盾を炙り出し、確定するたび CONTEXT.md / ADR をその場で更新する。「計画を docs に照らして詰めたい」「設計をグリルして」「用語を整理しながら計画をstr…
Productivity
claude-md-customizer
Conducts conversational interviews to understand technical background, development style, and AI collaboration preferences, then generates an optimized context file. Use when users…
Productivity
context-restoration
Restore previous session state from Serena MCP checkpoints. Retrieve checkpoint by ID or auto-select the most recent, deserialize context, and restore command/skill/phase/wave stat…
Productivity
hermes-context-compressor
Compresses agent context across phases by pruning stale tool results, safeguarding key segments, and applying structured LLM summarization with iterative refinement and fallback mo…
Productivity
claude-history
Deep investigation tool for past Claude Code sessions. Use when you need to understand what work was done, reconstruct decisions, find prior implementations, or build context from …
Automation
Context Mixer
After building your knowledge library by [ingesting prompts from your projects](ingesting-prompts.md), Context Mixer's most powerful feature is its ability to intelligently assembl…
AI / ML
Personality Engine
Behavior engine that adds lifelike presence to any agent: editorial voice, selective silence, timed urgency, ambient pings, context memory, and adaptive response tracking. Works ac…
Productivity
project-context-bootstrap
Bootstraps usable project context for new or unfamiliar repositories. Detects stack, summarizes understanding, proposes compact context artifacts, and updates only with approval be…
Productivity
context-router
Intelligent intent detection and skill routing gateway. Analyze user prompts for keywords, patterns, and project context to automatically activate the correct specialized skill. Fa…
Productivity
deep-recall
Recall conversation history via a 4-layer procedure (durable memory, semantic index, PostgreSQL, daily notes) before responding "no context". Activates only on explicit recall trig…
Productivity
opencode-memory
Access and retrieve local project memory including past sessions, plans, conversations, and context stored on disk. Use for resuming work, recalling prior decisions, or investigati…
Engineering
spec-anchor
工程上下文管理技能——在含有 anchor.yaml 或 .specanchor/ 的项目中必须调用。适用于代码修改、代码审查、Spec/上下文管理、对齐检查、交接、发现记录或沉淀工作之前。加载编码标准、模块合约和活跃任务。当用户提到 spec-anchor、specanchor 脚本、Spec 管理、上下文装配、对齐检查、boot 流程、Assembly …
Productivity
lean-ctx
Context runtime providing 48 MCP tools, 10 read modes, 90+ shell patterns, and tree-sitter AST support for 18 languages. Compresses context up to 99%. Use for file operations, shel…
Automation
mm-bridge
Hands off work to another agent instance by generating a ready-to-copy prompt. Auto-injects project context from passport.md and supports standard prompt frameworks. Outputs to a s…
Productivity
onboarding-to-a-project
Determines whether a session requires onboarding to an existing codebase before any brainstorming or implementation work begins. Skips onboarding for purely abstract discussions or…
Productivity
openai--google-calendar--google-calendar-meeting-prep
Create a practical meeting prep brief from a connected Google Calendar event and nearby context. Use when the user needs to understand required reading, pull linked notes or docs, …
Productivity
draft-profiles
Manages Draft profile lifecycle including listing, creating, renaming, and deleting named workspaces. Each profile maintains an independent context directory at ~/.draft/workspaces…
Productivity
draft-load-team
Imports the latest team context from the shared GitHub repository into the local context directory. Reads CHANGES.jsonl, filters entries since the last load, and writes updated con…
Productivity
exploration-session-brief
Interactive co-authoring skill that captures and refines core intent—whether for a software app, process improvement, research analysis, or strategic roadmap—through context gather…
Documentation
claude-md-manager
Create, edit, and organize project context files. Recommends keeping files under 50 lines with detailed rules modularized into separate rule or skill files. Handles requests to cre…
Productivity
memory-manager
Implements the 3-step Memory-First Protocol (Research, Response, Learning). Apply at task start to retrieve past context and at completion to persist new conventions, architectural…
Productivity
compaction-handoff
Prepares a minimal, reconstructible checkpoint before context compaction by persisting durable facts, decisions, and Git/PR state while emitting one concrete next action. Idempoten…
General
canil-k9-context
Maintains institutional context for Canil K9 GCM Limeira across development tasks, covering K9 handler protocols, compliance audits, gamification, dog medical records, incident tra…
Productivity
persona
Unified entry point for AI Persona OS — setup wizard, in-chat commands, context protection, monitoring, and learning system. Say 'persona setup' to start, 'persona status' for dash…
AI / ML
syke
Local-first cross-harness memory for agents. Syke observes activity across supported harnesses, keeps a current memex in context, and gives agents `syke ask`, `syke memex`, and `sy…
Productivity
xantham-memory
Retrieves relevant project, feedback, and profile context from memory before generating non-trivial replies on Telegram. Grounds responses in actual state rather than assumptions a…
Productivity
prevail-chief-task-meeting-prep
Prepares a concise one-page brief for an upcoming meeting by pulling relevant context from prior discussions, recent updates, domain state, and open items. Structures output as con…
Research
wiki-plan
Researches project and cross-project wikis to gather context before planning features, bug fixes, or refactors; synthesizes prior knowledge and produces a structured plan or delega…
Web
react-composition
Scale React composition patterns for components with many boolean props. Refactor to flexible APIs using compound components, render props, context providers, and modern component …
Automation
agentforce-multi-turn-patterns
Designs Agentforce conversations that span multiple turns without losing context: session variable scoping, conversation memory, clarifying-question patterns, topic-to-topic handof…
Productivity
engagement-handoff
Captures the live state of a pentest engagement—findings, coverage, next steps, open issues—so work can resume seamlessly in any later session or agent. Use for mid-engagement paus…
Productivity
session-refresh
Maintains long-running agent sessions by performing periodic retrospectives, synthesizing progress into a daily journal, then restarting the session with preserved context to clear…
AI / ML
ai-memory
Access a personal knowledge graph of ~5,850 entities covering projects, people, finances, and relationships. Trigger at session start, before creating entities, or when recalling c…
Productivity
chat
Handle context-aware project discussion, navigation, and lightweight edits. Covers plans, retrospectives, status updates, and routine chores without invoking heavier skills. Opens …
Productivity
context-chunks
Creates autonomous context-chunk drafts (passages + questions) that expand a resolved reading. Invoke via /context-chunks <resolved-reading-id>; outputs stay parked as drafts witho…
Productivity
skill-manager
Detect project tech stack and disable irrelevant skills to reduce context usage. Activate on requests to manage skills, optimize skills, disable irrelevant skills, or identify rele…
Showing the top 60 of 1,204. See the full list →