gongshichen/luminacode/persistence-plan
Claude Code and agent skill by gongshichen/luminacode
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Plan durable state, data model, migrations, caching, and recovery behavior.
Install
npx vskill@latest install gongshichen/luminacode/persistence-planSKILL.md
Cover the product's actual storage model:
- Data entities, ownership, retention, privacy, and deletion expectations.
- Storage location: database, object store, local files, browser storage, cache, queue, or external service.
- For CLI/TUI/local tools, define exactly how the storage path is resolved in real execution: project root, current working directory, user config directory, environment variable, command flag, or package-relative path. Prefer a testable override such as an environment variable or explicit config path when subprocess integration tests need isolated data.
- Do not ship a package-relative-only data path for a CLI tool if tests, smoke commands, or users need isolated workspaces. Provide a concrete override or cwd convention and document it in
INTERFACE_CONTRACT.md. - Schema shape, indexes, uniqueness, migrations, and compatibility with existing records.
- Atomicity, consistency, locking, transaction boundaries, crash recovery, and backup/restore expectations.
- Read/write paths, performance hot spots, LRU/TTL/compaction policies, and query patterns.
- Isolation between users, tenants, sessions, environments, and test data.
- Test isolation must work across real processes. If frontend/CLI tests run the product in a subprocess, monkeypatching an in-process module global is not a valid isolation mechanism; provide a subprocess-visible mechanism such as env var, cwd convention, fixture file path, or command option.
- A function parameter-only storage override is valid for in-process unit tests, but it is not sufficient for subprocess CLI integration unless the CLI exposes that override through a flag, environment variable, config path, fixture path, or cwd convention.
- If the contract or frontend plan asks for subprocess tests and only offers monkeypatching, treat the contract as incomplete and return it for correction before implementation.
- Validation or smoke checks that prove persistence survives restart/resume when required.
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 repositoryChecking.Lumina/TEAM/product-development/backend/skills/persistence-plan/SKILL.md
Popularity
- Repository stars
- 9
- Repository forks
- 1
- 7-day trend score
- 0
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/gongshichen/luminacode/persistence-plan)