escoffier-labs/solos-cookbook/ops-deck-lite
Claude Code and agent skill by escoffier-labs/solos-cookbook
- community
Checking that the SKILL.md file is still in the repository.
Local agent productivity stack: one small semantic code search service. Lightweight, cheap to run, and useful long before you need a giant ops dashboard.
Install
npx vskill@latest install escoffier-labs/solos-cookbook/ops-deck-liteSKILL.md
Ops Deck Lite
Build one small local service before you build a giant agent dashboard.
Goal
Give the agent a capability that pays off immediately: semantic code search.
Component: Semantic code search
Search code by meaning, not only exact text.
Useful for queries like:
- authentication middleware
- retry logic
- database pooling
- error handling
Core design
- chunk source files
- generate embeddings locally or through a provider you control
- store chunks, metadata, and optional summaries in a small database
- expose one search endpoint with a few modes:
hybrid,code,summary
Why this stack works
- cheap to run
- private by default
- easy to back up
- useful to both humans and agents
- much smaller blast radius than a full operations suite
Minimal setup guidance
Use any stack you like, but keep the shape simple:
- one code-search API
- one small database
- one lightweight process manager or service supervisor
Agent integration pattern
Teach the agent one habit: check semantic code search before grepping dozens of files.
Suggested API shape
POST /api/searchGET /api/healthPOST /api/index
Keep POST /api/index behind a credential or off the network. It rewrites the index, and an agent with tool access will find and call it.
Verification
A good smoke test:
- query a concept not literally present in source code
- confirm semantic search still finds the right area
Anti-pattern
Do not start with a full control plane, analytics wall, sprint board, and seven side panels. Start with the one tool that actually saves tokens and time.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/ops-deck-lite/SKILL.md
Popularity
- Repository stars
- 5
- 7-day trend score
- 9
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/escoffier-labs/solos-cookbook/ops-deck-lite)