MUST activate when intent is unclear, or cannot follow or deviate from original intent, or easily or reliably solve the problem, something came as SURPRISE or UNEXPECTED, you cannot bet $100 on solution, unknowns or assumptions critically affect solution, you panic, or user asked to UNDO.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add griddynamics/rosetta --skill deviation --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Deviation?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/griddynamics-deviation-e5ac3384)More formats (shields.io, HTML) on the badges page.
---
name: deviation
description: "MUST activate when intent is unclear, or cannot follow or deviate from original intent, or easily or reliably solve the problem, something came as SURPRISE or UNEXPECTED, you cannot bet $100 on solution, unknowns or assumptions critically affect solution, you panic, or user asked to UNDO."
license: Apache-2.0
user-invocable: false
baseSchema: docs/schemas/skill.md
---
<deviation>
<process>
1. STOP all changes immediately. Undoing is also the change.
2. DOUBLE CHECK against original intent.
3. "THINK THE OPPOSITE" — challenge current direction.
4. Escalate: subagents → orchestrator → user.
5. State briefly: understood, conflicted, unresolvable.
6. Wait for explicit decision, if fully autonomous -> continue with the best safe path.
7. Update AGENT MEMORY.md with root cause.
8. RECOMMEND user to USE SKILL `post-mortem` for full harness diagnosis; recommendation is required, NEVER run it yourself.
</process>
<pitfalls>
- Rationalizing deviation as "improvement".
- Continuing "just a bit more" after detection.
</pitfalls>
</deviation>
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. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
