geminiignore-finops
Configure and optimize .geminiignore files for AI context window efficiency and token cost reduction (FinOps).
- License 许可
- MIT
- 最近更新
- 2026-11-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- geminiignore-finops
- risk
- safe
- tags
- [ "finops", "context-management", "token-optimization", "geminiignore" ]
- tools
- [ "gemini", "claude", "cursor" ]
- author
- iradoweck
- source
- community
- license
- MIT
- category
- context-optimization
- date_added
- 2026-05-25
- description
- Configure and optimize .geminiignore files for AI context window efficiency and token cost reduction (FinOps).
- source_repo
- iradoweck/antigravity-awesome-skills
- source_type
- community
- license_source
- https://github.com/iradoweck/antigravity-awesome-skills/blob/main/LICENSE
03 SKILL.md 正文
GeminiIgnore FinOps Setup & Optimization
Overview
A skill to construct, refine, and maintain high-performance .geminiignore files across diverse tech stacks. By filtering out machine-generated code, heavy logs, package locks, and binary assets, this skill optimizes the AI agent's context window, accelerates processing speed, and reduces token consumption costs (FinOps).
When to Use This Skill
- Use when initializing a new repository or workspace for pair-programming with AI agents.
- Use when the AI context window is reaching its limits or when billing optimization (FinOps) is a priority.
- Use when the AI agent is accidentally reading build outputs, lock files, databases, or binary media.
How It Works
Step 1: Analyze the Workspace Tech Stack
Detect the languages, frameworks, and dependency managers present in the project (e.g., Node.js, Python, PHP, Dart/Flutter, Rust).
Step 2: Initialize or Update the .geminiignore File
Create a .geminiignore file at the root of the active workspace. If one already exists, review it to add missing categories.
Step 3: Implement the 7 Core Rules
Add rules divided into the following categories to filter out unnecessary machine noise while keeping human-written code visible:
- System & Editor Noise: Block OS temp files (
.DS_Store,Thumbs.db) and user-specific IDE caches (.idea/,.vscode/*, Xcode user data). - Dependency Folders & Lock Files: Ignore third-party package directories (
node_modules/,vendor/) and giant machine-generated lock files (package-lock.json,yarn.lock,Cargo.lock,composer.lock). - Build & Target Output: Block compiled folders (
dist/,build/,.next/,.nuxt/). - Caches & Tool Metadata: Block compiler caches (
.tsbuildinfo,.vite/,.pytest_cache/,.eslintcache). - Binary & Rich Assets: Block media types (
*.png,*.pdf,*.mp4,*.woff2) to prevent triggering expensive vision/multimodal tokens. - Local Databases & Logs: Block log files (
*.log) and SQL dumps or local SQLite DBs (*.sqlite,*.db). - Compiled Binaries & Mobile Builds: Block mobile package files (
*.apk,*.ipa) and compiled binaries (*.class,*.pyc,*.dll).
Step 4: Validate Exclusions
Verify that the AI can still see critical configuration blueprints (like .env.example, package.json, composer.json, pyproject.toml) but ignores the actual .env files and compilation artifacts.
Examples
Example 1: Standard Universal .geminiignore Template
Here is a recommended baseline configuration for a multi-language project:
# ==============================================================================
# .geminiignore - BASELINE DE FINOPS E ARQUITETURA
# ==============================================================================
# 1. SISTEMA OPERACIONAL E IDEs
.DS_Store
Thumbs.db
Desktop.ini
$RECYCLE.BIN/
.vscode/*
!.vscode/settings.json
!.vscode/tasks.json
!.vscode/launch.json
.idea/
*.iml
.gradle/
local.properties
.history/
# 2. DEPENDÊNCIAS (ECONOMIA DE TOKENS EM LOCK FILES)
node_modules/
package-lock.json
yarn.lock
pnpm-lock.yaml
vendor/
composer.lock
venv/
.venv/
env/
.env
.env.*
!.env.example
poetry.lock
Cargo.lock
pubspec.lock
# 3. BUILDS E EXPORTAÇÕES
dist/
build/
out/
target/
.next/
.nuxt/
.output/
bin/
obj/
# 4. CACHES DE FRAMEWORKS
.vite/
.parcel-cache/
.eslintcache
.babel-cache/
.tsbuildinfo
.turbo/
.pytest_cache/
.ruff_cache/
storage/framework/
storage/logs/
# 5. ASSETS BINÁRIOS E MULTIMÍDIA EXTREMOS
*.png
*.jpg
*.jpeg
*.gif
*.webp
*.svg
*.ico
*.psd
*.fig
*.pdf
*.zip
*.tar.gz
*.woff
*.woff2
*.ttf
# 6. BANCOS DE DADOS E LOGS
*.log
*.db
*.sqlite
*.sqlite3
*.sql
*.sql.gz
# 7. ARQUIVOS COMPILADOS
*.apk
*.aab
*.ipa
*.jar
*.class
*.pyc
__pycache__/
*.so
*.dylib
*.dll
*.exe
*.js.map
*.css.map
Best Practices
- ✅ Ignore dependency lock files: Standard lock files (e.g.,
package-lock.json,yarn.lock) contain thousands of lines of redundant package resolution trees. Ignoring them is the single largest FinOps win. - ✅ Keep configurations visible: Ensure manifests like
package.json,composer.json,Cargo.toml, andpyproject.tomlare NEVER ignored, as the AI needs them to understand dependencies. - ✅ Whitelist config examples: Use rules like
!.env.examplealongside.envignores so the AI understands configuration structure without exposing credentials. - ❌ Do not ignore source code: Avoid overly broad folder patterns like
lib/orapp/if they contain primary source code. Be specific (e.g., blockvendor/bundle/but not your actual code).
Limitations
- A
.geminiignorefile only affects AI tools parsing the workspace; it does not replace.gitignorefor Git repository hosting. - Patterns must be formatted correctly according to gitignore-style globbing to avoid accidentally ignoring source files.
Related Skills
@context-optimization- Broad tactics for context window management.@clean-code- Architectural practices for clean, human-readable codebases.
04 同仓库更多 Skills
vss-summarize-video
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
vss-setup-video-analytics-api
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
vss-setup-behavior-analytics
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
vss-search-archive
Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).
vss-query-analytics
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
vss-manage-video-io-storage
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.