Explorez les skills IA publiés de Sounder25 et consultez leurs instructions source.
Skills indexés
24Étoiles des dépôts des skills indexés
312Forks du dépôt
72Moyenne des étoiles par skill indexé
13Les étoiles d’un dépôt peuvent se répéter entre ses skills.
Optimize information density by filtering workspace files based on relevance to the current task. Excludes high-noise files (lockfiles, assets) and prioritizes source code matching semantic queries.
Generate comprehensive dependency graphs to identify "single-points-of-failure" and impact analysis chains.
Identify duplicate files across the workspace using SHA256 hashing to reduce redundancy and confusion.
Enforces a structural planning phase before execution. Generates and validates PLAN.json to ensure every task has a clear objective, steps, verification method, and rollback strategy.
Structured logging and analysis of execution failures to prevent recurrence.
Generates a 'Red Team' critique of recent code or plans to identify weak assumptions and edge cases.
Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment.
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Updates standardized intent files (NEXT.md, STATE.json) to maintain context across agent sessions.
Detect and prevent state-visibility violations across execution contexts within a single transaction.
Convert mixed terminal output and instructions into safe, paste-ready command blocks.
Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
Wraps command execution in a self-healing loop. Uses heuristics to auto-fix common errors (missing deps, locked files) or escalates to the Agent with structured error context.
Removes ignored build artifacts (bin, obj, node_modules) to reclaim space and fix ghost build errors. Safely respects .gitignore.
Rapidly ingest documentation via the /llms.txt standard to gain "fast-track" understanding of libraries without scraping entire sites.
Create or update .gitignore files by fetching standard templates from the GitHub/gitignore repository.
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents.
Safely renames a .NET project (solution, projects, namespaces, directories) from one name to another. Supports Planned (clean) and Recovery (dirty) modes.
Generate comprehensive workspace profile with git signals, build configs, and forensics completeness tracking. Foundation skill for all other workspace operations.
Analyzes failures or user requests to automatically scaffold new skills, ensuring structural evolution.
A QA gate that validates potentially destructive or irreversible actions before execution.
Detects drift between multiple git repositories (e.g. forks, mirrors, or multi-module projects). Generates a drift report and optionally applies sync actions.
Detects when the agent is stuck in a reasoning loop or unproductive state by analyzing tool usage and sentiment patterns.
Automates running the Ethereum Execution Layer Specification (EELS) tests against a local EVM implementation. Handles venv setup, execution, and result parsing.
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.