Results for “token-replay”

`task-agent`/`review-agent`: use when broker delivery, ordering, acknowledgement, DLQ, backpressure, or replay changes; skip synchronous retry without message semantics.

Token budget analytics and ROI scoring for AI agent actions. Track token cost per fix, detect wasteful loops, auto-route to fast tier when burn rate is too high. Integrates with token-budget-guard.sh hook. Triggered by /cost-report, "how much did that cost", "token usage", "am I wasting tokens".

Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Debug local web or Electron apps interactively using a persistent Playwright session with js_repl, enabling fast iterative UI debugging and visual QA.

Packages an existing talking-head, interview, or podcast video with timed, designed graphic overlay cards—kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture—synced to the transcript, on a 16:9, 9:16, or 4:5 canvas.

Generates at most one token recommendation and one prediction-market pick per run, each with a falsifiable thesis, entry, sizing, and kill criterion. Returns NO_PICK when no candidate meets the bar.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

セッション再開時に最新5件のhandoffを読み込み文脈を復元するスキル。「おはよう」「こんにちは」「こんばんは」「再開」「restart」または /resume-session を呼んだ時にトリガーする。new-session の対（読込側）。

Enhances AI agent memory by injecting large external context, auto-summarizing conversations with tone and intent preservation, compressing multi-turn histories, and verifying facts.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Intercepts responses to let users choose the depth and token budget before answering, with heuristic token estimation and preset depth levels.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

JWT implementation, token management, refresh patterns, and security.

Operate Redpanda through its Kafka-compatible API: produce and consume records, manage topics and consumer groups, run transactions, and configure tiered storage using rpk and Kafka clients.

Evaluates Base ERC-20 tokens by contract address, returning a 0-100 score across five criteria, launch protocol classification, security flags, and a narrative interpretation.

Design JWT strategies with refresh tokens. TRIGGERS - Use when user needs help with jwt-strategy related tasks.

Perform forensic on-chain analysis of EVM tokens to detect scams, rug pulls, and soft rugs by cross-referencing on-chain state against team narratives.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

上下文压缩省 Token。对话变长或开新任务时输出/使用 6 块压缩结构，总长 400~800 tokens。必加载。

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Provides on-chain verifiable randomness for coin flips, dice rolls, raffles, shuffles, and game outcomes via the DARKSOL Random Oracle API on Base.

Run any Replicate model (image gen, audio, video) by version ID

Computes the Recall metric using torchmetrics, including configuration for binary, multiclass, and multilabel tasks.

Injects up to 1 million tokens of external context into AI agent memory, auto-summarizes conversations with tone and intent preservation, and compresses multi-turn history into dense token sequences.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Analyze a codebase with specialized agents and propose refactoring tickets.

Use this skill for on-chain DEX operations: token search, swap quotes, DEX trading, wallet portfolio/balance queries, gas estimation, and transaction broadcasting across 20+ blockchains (Ethereum, Solana, Base, BSC, Arbitrum, Polygon, etc.). Use when user says: 'swap ETH for USDC', 'buy token on-chain', 'DEX swap', 'token search on-chain', 'wallet balance', 'portfolio value', 'gas price', 'broadcast transaction', 'trending on-chain tokens', 'hot tokens', 'token holders', 'token liquidity', 'smart money signal', 'whale signal', 'K-line on-chain', '链上交易', '链上swap', 'DEX交易', '买币', '链上行情', '钱包余额', '持仓', 'gas费', '广播交易', '链上热门币', '聪明钱', '巨鲸信号'. Powered by OKX Web3 DEX API with 500+ liquidity sources. MUST run node scripts — NEVER fabricate on-chain data. For CEX trading (Binance/OKX spot/futures), use aicoin-trading. For CEX market data (funding rates, OI, liquidation), use aicoin-market.

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

Scan codebase and git history for leaked secrets — API keys, tokens, passwords, private keys. Uses whispers-style regex patterns + gitleaks. Run as /leak-check before any git push. Alerts on Claude API keys, GitHub tokens, AWS credentials, and generic high-entropy strings.

Authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery with structured workflow and tooling.

Server-Sent Events for real-time server-to-client streaming. Express, Fastify, FastAPI, Spring WebFlux SSE implementations. Event streams, reconnection, and EventSource API. USE WHEN: user mentions "SSE", "Server-Sent Events", "EventSource", "event stream", "text/event-stream", "live feed", "streaming updates" DO NOT USE FOR: bidirectional communication - use `socket-io`; WebRTC - use `webrtc`; LLM streaming - use AI SDK skills

info-to-ink

This skill should be used when the user wants to "dca into" a token, "buy X every day", set up a "recurring buy", "dollar cost average" into an asset, "schedule a buy", or "auto-buy on a dip". Buys a fixed amount into a token on a schedule, optionally only when a condition holds (for example only when ETH is below a price threshold). The host agent's scheduler wakes the skill on a cadence; each wake is one self-contained run.