Use when a task may push commits, wait on CI, tag, publish, or declare a release complete.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add ShugokiFable/Ultimate-AI-Starter-Bundle --skill ci-convergence --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ci Convergence?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/shugokifable-ci-convergence-4567ea42)More formats (shields.io, HTML) on the badges page.
---
name: ci-convergence
description: Use when a task may push commits, wait on CI, tag, publish, or declare a release complete.
---
# CI Convergence
## Core rule
A local green run is not release evidence. The authoritative unit is the **pushed SHA** and every required check attached to that exact SHA.
## Contract
1. Record the pushed SHA immediately after push.
2. Enumerate required checks for that SHA; never substitute “latest run”.
3. Wait while any required check is queued or running. **Pending is not success.**
4. Require every required check to reach a terminal successful state.
5. If one fails, inspect its log, fix the causal defect, push a new SHA, and restart convergence from step 1.
6. Tag, publish, or end the task only after the exact release SHA is terminal-green.
For a release, verify the tag resolves to the same green SHA and verify the uploaded artifacts after publication.
## Stop conditions
Do not release on cancelled, skipped-when-required, missing, unknown, pending, or stale checks. If the CI system cannot prove which SHA it tested, report that as unverified rather than inferring success.
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.
