Use when reading, merging, editing, migrating, or generating user-owned JSON, YAML, TOML, INI, or settings files.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add ShugokiFable/Ultimate-AI-Starter-Bundle --skill config-preservation --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Config Preservation?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/shugokifable-config-preservation-0026c1a8)More formats (shields.io, HTML) on the badges page.
---
name: config-preservation
description: Use when reading, merging, editing, migrating, or generating user-owned JSON, YAML, TOML, INI, or settings files.
---
# Config Preservation
## Core rule
User configuration is data, not a template target. **Merge** only the keys you own and preserve everything else.
## Safe update contract
- Read using the file’s real encoding; prefer explicit UTF-8 for modern configs.
- Parse before changing.
- **Backup** the original bytes before a destructive rewrite.
- Modify the smallest owned subtree.
- Serialize to a temporary sibling file when possible, then atomically replace.
- Parse the result again and verify the owned values.
- Preserve or deliberately normalize line endings/encoding only when the format contract allows it.
- On any failed write/verification, restore the original bytes.
A successful write requires a verified **round-trip**, not merely a zero exception.
Never replace a live config wholesale with a developer-machine template. Never delete unknown keys because the local schema does not recognize them.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.