[10] INIT. Session-start routine for this project. Use when beginning a new session or onboarding to this repo to load AGENTS.md, MEMORY.md and core project context (README), then summarize context and confirm readiness.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill 10-init-session-150 --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of 10 Init Session 150?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-10-init-session-150)More formats (shields.io, HTML) on the badges page.
---
name: 10-init-session-150
description: "[10] INIT. Session-start routine for this project. Use when beginning a new session or onboarding to this repo to load AGENTS.md, MEMORY.md and core project context (README), then summarize context and confirm readiness."
---
# Init-Session 150 Protocol
## Primary workflow
1. Read `AGENTS.md` in the repo root.
2. Read `MEMORY.md` in the repo root.
- Load Long-Term Memory protocols first.
- Check Lessons (Inbox) and Short-Term for active items.
- Treat Session State as volatile; update it only after confirming with the user.
3. Read core project context files (if present):
- `README.md` for project overview and commands.
4. Summarize in 5-8 bullets:
- Most relevant protocols that will affect the upcoming work.
- Any active lessons or warnings.
- Key project constraints (tests, tools, conventions).
5. Ask for confirmation before making changes:
- Confirm the planned next steps.
- Ask whether to update or clear Session State.
## Notes
- If any file is missing, state it briefly and proceed with what is available.
- Keep the summary concise; focus on constraints that change behavior.
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.