Skill Claude CodeCodex
A procedure for writing a technical blog post from a topic supplied by the user and saving it locally.
not rated 188
+4 4d ago A SkillSpector: pass 8 tokens
original MIT
zjp1997720/codex-model-routing-team
Skill Codex
A team-routing skill for assigning complex, independent knowledge or coding tasks to background workers with chosen models and reasoning levels. The main agent remains responsible for planning, combining results, and checking the final work.
not rated 159
+1 3mo ago A SkillSpector: pass 138 tokens
original MIT
octoclaw
03Skill Claude CodeCodex
OctoClaw is the TypeScript-first policy, delegation, status, and operator layer for OpenClaw. Use it when a turn should be routed through reply/delegate policy, WorkContract-backed delegation, runtime status, IM delivery, or feedback-loop tooling.
not rated 48 3mo ago A 57 tokens
original MIT
AlexAI-MCP/GPT5.6-SOLTELU-Model-Inverter
Skill Codex
Optimize quality per token across GPT Codex, GPT Work, and Codex CLI by automatically selecting the best-fit GPT-5.6 Luna, Terra, or Sol profile and reasoning effort for the main task and every delegated subtask. Prioritize direct visible Codex execution and importance-aware subagent routing. Use automatically for…
not rated 23 3mo ago A 123 tokens
Skill Codex
Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
not rated 8
changed 19d ago A SkillSpector: warn 35 tokens
original Apache-2.0
Skill Codex
Plan or revise the smallest reliable AI setup for a concrete project. Use when the user explicitly invokes $build-ai-team; asks whether one Agent or several Agents are needed; requests a team plan or an add, merge, replace, keep, ownership, or handoff change to an existing Agent team; or asks which model configuration…
not rated 5 1mo ago A 125 tokens
original MIT
Grails125/codex-sol-terra-luna-auto-orchestrator
Skill Claude CodeCodex
A structured software-development workflow that divides work among roles for planning, exploration, implementation, testing, review, and final approval.
not rated 4 2mo ago A 37 tokens
original MIT
Skill Claude CodeCodex
Risk-gated MoA escalation and model auto-tuning.
not rated 2 3mo ago A 16 tokens
Skill Claude Code
Complexity-based routing of tasks across four model tiers — frontier (T3), strong workhorse (T2), fast executor (T1), cheapest recon (T0). Use when planning any multi-step work, when deciding which subagent should execute a task, when writing a dispatch brief, or when an executor fails and escalation is needed.
not rated 1
changed 15d ago A 72 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: