Use when deciding what evidence is required, whether previous proof remains valid, or whether repeated testing has become reassurance rather than necessary verification.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill verification-controller --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Verification Controller?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-verification-controller)More formats (shields.io, HTML) on the badges page.
---
name: verification-controller
description: Use when deciding what evidence is required, whether previous proof remains valid, or whether repeated testing has become reassurance rather than necessary verification.
---
# Verification Controller
## Core principle
Verification is complete when each required condition has sufficient current proof; compulsive rechecking is prohibited.
## Procedure
1. List acceptance conditions requiring proof.
2. Choose the smallest sufficient command or observation for each.
3. Record result, scope, and timestamp or source state.
4. Check whether later changes invalidated the proof.
5. Reject equivalent reruns without relevant change or incomplete proof.
6. Mark verification sufficient and continue or complete.
## Required output
Condition-to-proof mapping, validity decision, and next unmet proof.
## Limits
At most 2 equivalent passes without relevant change.
## Common mistakes
Do not seek subjective certainty, recursively inspect unrelated paths, or repeat a check with different syntax.
## Stop condition
Stop verification when all required proof is current or a specific missing proof is named.
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.