Routing rules for the cockpit skills. Auto-injected at session start so the other skills trigger reliably. Read first.
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add elitongadotti/cockpit --skill using-cockpit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Using Cockpit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/elitongadotti-using-cockpit)More formats (shields.io, HTML) on the badges page.
---
name: using-cockpit
description: Routing rules for the cockpit skills. Auto-injected at session start so the other skills trigger reliably. Read first.
when_to_use: injected by the session-start hook on startup / clear / compact
---
# Using Cockpit
This project has the **cockpit** plugin installed. Before acting, check whether the task matches one of the skills below and invoke it.
| If the task is... | Use skill |
|---|---|
| A multi-step task / "build X" / long job | `spec-first` — write `PROMPT.md` first |
| A crash, exception, or stack trace | `read-the-trace` |
| A new/changed SQL query or migration | `sql-review` |
| A PySpark job or a query on Iceberg tables | `pycegerb-yoda` |
| Checking a branch against a ticket's acceptance criteria | `acceptance-audit` |
| Committing, or pasting anything somewhere public | `leak-check` |
| Writing a commit message | `writing-commit-messages` |
| Opening a pull request | `pr-from-diff` |
| Long session, big files, accuracy dropping | `context-budget` |
| Ending or resuming a multi-session project | `shift-notes` |
| Starting a session after a "done" feature | `broken-window-check` |
After any code change, invoke the `verifier` agent against the diff and the spec.
Skills are guidance, not gates — apply judgement. If none match, proceed normally.
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.
