Hold the caching.ai prompt cache warm for a while (default 2h, max 12h) so stepping away doesn't cost a cold cache re-write. Use when the user says things like "keep my cache warm", "hold the cache for 4 hours", "캐시 지켜줘", "점심 먹고 올게 캐시 유지해줘".
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add caching-ai/caching.ai --skill hold --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Hold?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/caching-ai-hold)More formats (shields.io, HTML) on the badges page.
---
name: hold
description: Hold the caching.ai prompt cache warm for a while (default 2h, max 12h) so stepping away doesn't cost a cold cache re-write. Use when the user says things like "keep my cache warm", "hold the cache for 4 hours", "캐시 지켜줘", "점심 먹고 올게 캐시 유지해줘".
argument-hint: "[duration — e.g. 4h, 90m, 3 hours, 2시간]"
allowed-tools: "Bash"
---
Send a warm-hold command to the caching.ai proxy and relay its answer.
1. Run exactly:
```bash
"${CLAUDE_PLUGIN_ROOT}/bin/cache-keeper.sh" --hold "$ARGUMENTS"
```
If the user gave no duration, omit the second argument (the proxy defaults
to 2 hours). Pass the duration in the user's own words/language — the proxy
parses "4h", "90m", "3 hours", "2시간", "media hora" and replies in kind.
2. Relay the script's output to the user verbatim (it is the proxy's reply,
already in the user's language, starting with 🔥 on success).
3. If the output starts with `not-connected:` or `no-key:`, tell the user this
session isn't routed through caching.ai yet and offer to run /cache:setup.
4. If the reply says the Cache Warmer is off for the key, point the user to
https://caching.ai/console → key settings to enable it.
Never send the hold as a chat message yourself — the script talks to the proxy
directly, which is reliable regardless of how this session is configured.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
