Packs

4 packs

Email Productivity Toolkit

For professionals who want to manage their inbox, draft replies, and send emails with delivery confirmation.

12 skills · pack

Kanzlei Allgemein

Kanzlei-Allgemein-Plugin (fusioniert mit Cowork): edles Kommandocenter Mandatsannahme/GwG Klage/Replik Vertrag Rechtsprechung Handelsregister beA-Journal Rechnung UStVA Fristenbuch Timesheet RVG Versand-Vor-Check Posteingang Mandantenakte Mahnwesen Tagesbrief Geburtstage Weihnachtskarten.

4 skills · pack

Sam Superpowers

Fork of obra/superpowers 5.0.7: the 14 core skills (TDD, debugging, collaboration patterns) with the mandatory-gate SessionStart injection replaced by a short judgment-based router. Skills are tools, not gates.

14 skills · pack

Plugin full-stack de contencioso civel brasileiro (Civil Litigation Master) — 64 skills em 9 camadas: procedimento comum (inicial, contestacao, replica, saneamento, instrucao, sentenca), tutelas de urgencia/evidencia, a gama de acoes civeis (indenizatoria, obrigacao de fazer/nao fazer, resolucao/revisional contratual, cobranca/monitoria, consignacao, declaratoria, anulatoria, possessorias, usucapi

64 skills · pack

Results for “repl”

56 skills

configure-replication-agent

Configure AEM 6.5 LTS replication agents for content publishing, dispatcher cache flushing, and reverse replication.

reply-automation

Automate Reply operations through Composio's Reply toolkit via Rube MCP, with dynamic tool discovery and connection management.

reply-io-automation

Automate Reply IO operations through Composio's Reply IO toolkit via Rube MCP, including tool discovery, connection management, and execution.

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

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on Codex -p.

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

More results

alpaca-a-strong-replicable-instruction-following-model-stanf

Alpaca: A Strong, Replicable Instruction-Following Model

replicate-automation

Automate Replicate AI model operations: run predictions, upload files, inspect model schemas, list versions, and manage prediction history via the Composio MCP integration.

Forces a second, harder escalation pass using the original glazer prompt words verbatim, pushing for a sharper replacement thesis rather than more polish.

baoyu-image-gen

Generates images via OpenAI, Google, DashScope, and Replicate APIs, supporting text prompts, reference images, aspect ratios, and quality presets.

remember-interactive-programming

Reminds the agent to act as an interactive programmer using a live REPL for exploration and modification, with structural editing and todo list management.

Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.

skill-gmail-auto-reply-for-client

This skill enables the agent to automatically answer Gmail messages on behalf of a client. The agent drafts and (when the user approves or when configured) sends replies using the client’s tone, si...

cli-anything-hermes

Builds, refines, tests, or validates a CLI-Anything harness for a GUI application or source repository, producing a Python-based Click CLI with REPL mode and JSON output.

jrennie99-glitch

Voice/audio-enabled AI chat interface forked from HuggingFace Chat UI with RVF document store replacing MongoDB

Check all outreach channels for replies using Chrome DevTools MCP. Scans Zoho webmail, LinkedIn messaging, and Instagram DMs.

joint-multi-tf-v560

v5.6.0 joint multi-TF model: single model per symbol with broadcast 1Hour context replaces dual 15Min/1Hour models. Trigger: (1) replacing weighted-voting model aggregation, (2) adding broadcast features to vectorized env, (3) limited training data + worried about overfitting from doubling obs_dim, (4) backtest builder mismatch with newer feature counts.

netanel-abergel

commitment-tracker

Enforce immediate execution of any commitment made in a reply. Use this skill before finalizing ANY reply that contains a promise to act — phrases like "אדווח", "אעדכן", "אשלח", "אחזור אליך", "I'll send", "I'll report", "I'll follow up", "I'll update". Prevents the agent from saying it will do something and then not doing it.

message-queue-design

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

email-validator

Find and validate email addresses using Snov.io via Chrome DevTools MCP. Takes LinkedIn profile URLs and returns verified emails. Replaces ZeroBounce.

autonomous-loops

Run Claude Code autonomously in loops, from simple sequential pipelines to multi-agent DAG orchestration.

concise-response

Invoke when the agent's conversational replies have gotten too long or wordy and the user wants shorter answers for the rest of the conversation.

book-sft-pipeline

Convert books into supervised fine-tuning datasets and train style-transfer models that replicate an author's voice.

16.9k · bundle

Unified multimedia generation API for images, videos, and text-to-speech, replacing separate providers for a single workflow.

orchestra-research

fine-tuning-with-trl

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

10.4k · bundle

orchestra-research

grpo-rl-training

Expert guidance for implementing GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

10.4k · bundle

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

orchestra-research

verl-rl-training

Train LLMs with reinforcement learning using verl (Volcano Engine RL), supporting RLHF, GRPO, PPO, and other algorithms for scalable post-training with flexible infrastructure backends.

10.4k · bundle

specialized-specialized-model-qa

Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

browser-use-to-stagehand

Convert browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase, replacing opaque agent loops with deterministic pipelines where possible.

copilot-pr-autopilot

Automates repeated rounds of Copilot code review on GitHub pull requests: triggers review, triages threads, dispatches parallel fix agents, commits, replies, and loops until convergence.

36.2k · bundle

pytorch-common-pitfalls

Fixes common PyTorch bugs including percentile calculations, LayerNorm for Conv1d, and buffer edge cases in reinforcement learning and neural network code.

baoyu-image-gen

Generates images using multiple AI providers including OpenAI, Google, Azure, and others. Supports text-to-image, reference images, aspect ratios, and batch generation from prompt files.

23.1k · bundle