Journal recommendation engine for medical manuscripts. 2-pass matching against a curated public profile library plus any user-local private profiles, enriched with detailed…
Score 70/100
Use Claude Code dedupe to summarize an issue, run several GitHub duplicate searches in parallel, filter false positives, and post only well-supported possible-duplicate links.
Score 70/100
Search for local events, activities, and happenings in a specified location and timeframe. Use when the user asks about events, concerts, festivals, meetups, or things to do in a…
Score 70/100
Determine the next sequential phase ID for creating a new phase. Use when planning a new phase.
Score 70/100
Find the next unimplemented step in a phase. Use when determining what to work on next.
Score 70/100
Searches journal for past work related to current task, finding relevant context, solutions, and decisions
Score 70/100
Modern find-and-replace using sd (simpler than sed) and batch replacement patterns. Triggers on: sd, find replace, batch replace, sed replacement, string replacement, rename.
Score 70/100
Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI.
Score 70/100
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new skills to install.
Score 70/100
Discover and rank media sources across platforms for an artist or specific content
Score 70/100
Search markdown files, Nextflow scripts, and config files for TODO/FIXME comments, categorize by priority, and provide actionable recommendations.
Score 70/100
Use when user wants to find, look up, or resolve a Telegram user by username, phone number, or ID, or get someone's Telegram profile info.
Score 70/100
Use when APIs fail repeatedly with version-related errors (method not found, wrong arguments, unknown flag) or when about to use library APIs with uncertain knowledge - guides…
Score 70/100
Detect profitable arbitrage opportunities across CEX, DEX, and cross-chain markets in real-time. Use when scanning for price spreads, finding arbitrage paths, comparing exchange…
Score 70/100
How to find, evaluate, and recommend the best ingestion method for changelog URLs — covers feed discovery, provider detection, GitHub API, markdown sources, and scraping fallback
Score 70/100
Finds similar implementations, usage examples, and existing patterns in the codebase - shows concrete code examples for modeling new work.
Score 70/100
Use when reviewing code changes, auditing new features, cleaning up PRs, or user says "find dead code", "find unused code", "check for unnecessary additions", "what can I remove".
Score 70/100
Use when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations.
Score 70/100
Finds and ranks expensive Snowflake queries by cost, time, or data scanned. Use when: (1) User asks to find slow, expensive, or problematic queries (2) Task mentions "query…
Score 70/100
Help users build relationships with mentors and sponsors for career growth. Use when someone is looking for career guidance, wants to find a mentor, needs an advocate at work, is…
Score 70/100
Use when optimizing existing pages for SEO, hunting low-hanging keyword opportunities, analyzing pages that get impressions in Google Search Console but few clicks, or planning a…
Score 70/100
Track Apple devices and AirTags via FindMy.app on macOS using AppleScript and screen capture.
Score 70/100
Automate Findymail tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Score 70/100
Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets,…
Score 70/100
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Score 70/100
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of…
Score 70/100
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Score 70/100
Automate Finerworks tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Use when preparing to fine-tune an LLM for multi-turn conversations, before generating any training data.
Score 70/100
Use when generating synthetic training data for multi-turn conversation fine-tuning. Triggers - have design artifacts ready, need to generate conversations, ready to assess…
Score 70/100
Use when training a fine-tuned model and evaluating improvement over base model. Triggers - have filtered training data, ready to submit training job, need to convert to GGUF.
Score 70/100
Model fine-tuning with PyTorch and HuggingFace Trainer. Covers dataset preparation, tokenization, training loops, TrainingArguments, SFTTrainer for instruction tuning, evaluation,…
Score 70/100
Guide for using FinFocus CLI to analyze cloud infrastructure costs. Use when running projected or actual cost commands, interpreting cost output, configuring Pulumi integration,…
Score 70/100
Automated FinFocus CLI and plugin setup workflow. Use when installing finfocus, setting up plugins for cloud providers, initializing configuration, bootstrapping a new finfocus…
Score 70/100
Identifies binary file characteristics including compiler signatures, version information, and build environment details.
Score 70/100
Automate Fingertip tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Use after review-pack has returned `yes` and the user has explicitly signed off on the diff. Presents the user with concrete integration options (merge, PR, keep branch, cleanup)…
Score 70/100
Prepare a GitHub issue branch for PR with quality checks, cleanup, and review recommendations.
Score 70/100
Manually complete a phase and update phase.md. Use when you want to manually review/edit phase completion, or when auto-detection didn't trigger.
Score 70/100
Finish current task. Use when user says "dokonči task", "task hotový", "mergni do main", or runs /finish-task.
Score 70/100
End-of-day wrap up - analyzes all work done, creates detailed daily update log, commits all changes, and pushes to remote.
Score 70/100
Completes feature branch work by rebasing, pushing, monitoring CI, and squash merging to main
Score 70/100
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…
Score 70/100
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…
Score 70/100
Final completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.
Score 70/100
Automate Finmei tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Detect and remove AI-generated markers from Finnish text, making it sound like a native Finnish speaker wrote it.
Score 70/100
Cost optimization for AI workloads - model selection, GPU sizing, commitment strategies, and multi-cloud cost management
Score 70/100
Use when legacy prompts or older framework flows reference `finops-manager` and you need the modern runtime to resolve that capability cleanly.
Score 70/100
Provides FinOps practices for cloud cost optimization, budget management, and resource rightsizing. Use when analyzing cloud spend, optimizing costs, or when user mentions…
Score 70/100
Diagnose and fix common Finta CRM issues with email sync, deal rooms, and pipeline. Trigger with phrases like "finta error", "finta not working", "fix finta".
Score 70/100
Manage a fundraise pipeline end-to-end with Finta. Use when running a fundraise, tracking investor conversations, managing deal rooms, or collecting commitments.
Score 70/100
Manage ongoing investor relations and updates with Finta. Use when sending investor updates, tracking cap table changes, or maintaining LP relationships post-close.
Score 70/100
Optimize Finta plan selection and feature usage. Trigger with phrases like "finta cost", "finta pricing", "finta plan selection".
Score 70/100
Set up your first fundraise pipeline in Finta with investors and deal stages. Use when starting a new fundraise, importing investor lists, or learning Finta's pipeline management…
Score 70/100
Set up Finta fundraising CRM account and configure integrations. Use when onboarding to Finta, connecting email/calendar, or configuring investor pipeline automation.
Score 70/100
Optimize Finta fundraise workflow efficiency. Trigger with phrases like "finta performance", "finta efficiency", "optimize finta".
Score 70/100
Fundraise launch checklist using Finta CRM. Trigger with phrases like "finta checklist", "finta launch", "finta go-live".
Score 70/100
Handle Finta platform updates and data migration. Trigger with phrases like "finta upgrade", "finta migration".
Score 70/100