when-to-query
Decision guide for when to query Bluera Knowledge stores vs using Grep/Read on current project. Query BK for library/dependency questions and reference material. Use Grep/Read for current project code, debuggin...
Découvrez les skills Tests et sécurité, comparez leurs dépôts et consultez leurs instructions.
Decision guide for when to query Bluera Knowledge stores vs using Grep/Read on current project. Query BK for library/dependency questions and reference material. Use Grep/Read for current project code, debuggin...
Load .bonfire/index.md context to understand ongoing work, previous decisions, blockers, and session history. Use when user references past work or asks about project status.
Manages project plans with rmplan. Use any time the user mentions rmplan, asks to "generate plan 123" (or any number), "work on plan 123", or when you are working on an rmplan task.
Create interactive HTML5 Canvas visualizations, graphics, and animations with modern JavaScript
Generate and manipulate Microsoft Word (.docx) documents programmatically using modern libraries
Select and configure appropriate Azure RBAC roles following the principle of least privilege for secure access control
Visualize Azure resources, dependencies, and infrastructure architecture with diagrams and documentation tools
Automates the integration of Azure Application Insights telemetry into web applications for monitoring, diagnostics, and performance tracking
Build Model Context Protocol (MCP) servers to extend GitHub Copilot and AI agents with custom tools and data sources
Create production-grade, distinctive frontend interfaces with modern UX/UI patterns for web applications
Plan LLM fine-tuning and evaluation experiments. Use when the user wants to design a new experiment, plan training runs, or create an experiment_summary.yaml file.
Create weekly software meeting agenda in the wiki repo.
Create a lightweight summary of experiment results from a completed (fine-tuned and evaluated) experiment. Use after run-experiment to capture key metrics from the experiment in textual form.
Set up complete experimental infrastructure for all runs in a designed experiment. Orchestrates parallel generation of fine-tuning configs (via scaffold-torchtune) and evaluation configs (via scaffold-inspect)....
Execute the complete experimental workflow - model optimization followed by evaluation - for all runs in a scaffolded experiment. Use after scaffold-experiment to submit jobs to SLURM.
Create custom inspect-ai evaluation tasks through interacted, guided workflow.
Reviews code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.
Execute an outlined plan step by step, tracking progress and updating the status of each step as you go. Use this skill whenever you need to execute an outlined plan.
Clarify and structure the requirement first, then generate an implementation plan for the requirement; Use this skill when user submits a requirement to add new functionalities.
Clarify the scope, objectives, and constraints of the refactor request first, then generate a refactoring plan for the refactor request. Use this skill when the user submits a refactor request to refactor exist...
First, determine the root cause of the reported bug. Then, create a clear, step-by-step plan for the bug fixing. Use this skill whenever a user reports a bug.
This skill should be used when the user asks to "add an MCP server", "install an MCP tool", "add a capability to Jarvis", "integrate an MCP server", "set up meme generation", "add web search to Jarvis", or ment...
This skill should be used when the user asks to "register a phone number with Signal", "set up signal-cli", "verify Signal registration", "troubleshoot Signal registration", "fix user not registered error", or...
Create custom slash commands for Claude Code. Use when the user wants to create, add, or build a new slash command, custom command, or save a prompt as a command.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.