Use when choosing, ranking, curating, pruning, or de-duplicating Claude cybersecurity skills; when a broad cybersecurity task could match many skills; or when deciding which skill should be loaded first.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add 26zl/cybersec-toolkit --skill skill-curation-router --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Skill Curation Router?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/26zl-skill-curation-router)More formats (shields.io, HTML) on the badges page.
---
name: skill-curation-router
description: Use when choosing, ranking, curating, pruning, or de-duplicating Claude cybersecurity skills; when a broad cybersecurity task could match many skills; or when deciding which skill should be loaded first.
---
# Skill curation router
Use this skill to reduce noise when a task could activate too many cybersecurity skills.
## Routing workflow
1. Check `.claude/skills/CURATION.md` for tier and domain anchors.
1. For fuzzy prompts, run:
```bash
python3 scripts/curate_claude_skills.py --query "<user task>" --top 10
```
1. Start with one T0/T1 anchor skill, then add one specialist skill only when the target platform, tool, or technique is clear.
1. Prefer coverage anchor skills for GRC, AI/LLM, IoT/embedded, mainframe, telecom/5G, SAP/ERP, and supply-chain/product-security tasks.
1. Treat T3 skills as exact-match playbooks. Do not load several near-duplicate T3 skills just because their descriptions overlap.
## Selection policy
- Broad program question: use a T1 coverage anchor or project workflow skill.
- Specific tool/vendor/task: use the highest-ranked exact specialist from the query helper.
- Offensive/simulation task: confirm authorization and use the least invasive workflow first.
- Current regulation, standard, or product behavior: verify against current official sources before making a definitive claim.
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.
