sounder25/google-antigravity-skills-library
Overview
This skill optimizes an agent's working set by filtering workspace files to a concise, relevance-ranked list. It excludes high-noise files and directories, respects .gitignore, and produces a deterministic RELEVANT_FILES.txt for downstream reading. The result reduces token waste and focuses the agent on source files most likely to help the current task.
How this skill works
The pruner scans the repository tree while honoring .gitignore and skipping binaries, lockfiles, large assets, and other high-noise paths. It scores files by filename and content against the provided focus keywords, applies caps and safety gates, and emits a limited, ordered list of absolute file paths plus a token-savings summary. Execution is implemented as a PowerShell script for deterministic, testable behavior.
When to use it
- Preparing an agent to work on a specific feature or bug in a large repository
- Reducing context window usage before generating embeddings or code summaries
- When many irrelevant assets (images, node_modules, lockfiles) crowd the workspace
- Integrating into a pipeline to feed only high-value files to downstream models
- Before running high-cost analysis that should avoid scanning the entire repo
Best practices
- Provide concise, descriptive focus keywords that reflect the task intent
- Set max-files to a practical limit (e.g., 20–100) based on model context size
- Run the pruner early in the agent workflow and treat its output as authoritative
- Combine filename matching with semantic content match for better precision
- Keep the .gitignore up to date so the pruner avoids irrelevant files
Example use cases
- Focus on 'auth' to surface authentication-related source files for a security fix
- Prune context to 'EVM opcode' before analyzing smart-contract bytecode handling
- Limit to 50 files when generating embeddings to stay within token budgets
- Filter out assets and lockfiles before a refactor that targets TypeScript modules
- Use within CI to give analysis agents a compact, deterministic input set
FAQ
It checks file types and sizes and explicitly skips binaries and large assets; it also respects .gitignore to avoid irrelevant content.
Can I rely on the ordering of RELEVANT_FILES.txt?
Yes. Files are ranked by relevance to the focus query so the top entries are highest priority for the agent.
16 skills
This skill prunes repository context to relevant files based on focus topics, reducing noise and preserving essential code.
This skill rapidly ingests llms.txt documentation to provide fast, accurate context for libraries and APIs.
This skill safely removes build artifacts like bin and obj, respects gitignore, and frees disk space while avoiding source deletion.
This skill creates isolated swarm sub-workspaces and prepares task-specific prompts and context for parallel worker agents to execute immediately.
This skill enforces a deterministic planning phase by generating and validating PLAN.json with objectives, steps, verification, and rollback guidance.
This skill validates high-stakes actions before execution, preventing data loss by ensuring safety rules align with the current plan.
This skill generates a red-team critique of recent code to reveal weaknesses, edge cases, and overlooked assumptions before finalization.
This skill detects drift across multiple git repositories, reports ahead/behind status, and optionally applies safe sync actions.
This skill records and analyzes failures to identify root causes and preventive rules, ensuring durable postmortems and reduced recurrence.
This skill generates comprehensive dependency maps across codebases to identify single points of failure and reveal impact chains for safer refactoring.
This skill generates a complete workspace profile with git signals and build configs, enabling downstream tools to verify forensics completeness.
This skill detects and prevents state-visibility violations across execution contexts within a transaction to ensure consistent code and storage visibility.
This skill exposes an MCP server interface to Antigravity, enabling external agents to invoke skills as native tools.
This skill updates standardized breadcrumbs across sessions by maintaining NEXT.md and STATE.json to preserve context and streamline agent work.
This skill safely renames a .NET solution, projects, and namespaces, with planned and recovery modes to prevent data loss.
This skill enables mid-task course correction by monitoring FEEDBACK.md and applying user guidance without restarting.
