Use when repository architecture, rules, skills, commands, context routing, manifests, or generated AI knowledge change and dependent sources may become stale.
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add ihabkhaled/AI-Psychiatry --skill knowledge-maintainer --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Knowledge Maintainer?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-knowledge-maintainer)More formats (shields.io, HTML) on the badges page.
---
name: knowledge-maintainer
description: Use when repository architecture, rules, skills, commands, context routing, manifests, or generated AI knowledge change and dependent sources may become stale.
---
# Knowledge Maintainer
## Core principle
Change the smallest authoritative source, regenerate dependents, validate references, and never synchronize prose copies manually.
## Procedure
1. Identify canonical and generated artifacts.
2. Inspect dependencies and instruction precedence.
3. Modify the smallest authoritative source.
4. Regenerate indexes, manifests, and runtime mirrors.
5. Validate JSON, schemas, links, IDs, conflicts, freshness, and cycles.
6. Update only affected documentation and maps.
## Required output
Canonical change, regenerated artifacts, validation proof, and resolved conflicts.
## Limits
No parallel knowledge system; routers stay thin.
## Common mistakes
Do not edit generated output against its generator or duplicate canonical rules across adapters.
## Stop condition
Stop when dependents are current, references resolve, and validation passes.
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!
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.
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', ...
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.
