ai-routing skills

ypollak2/llm-router

Skill Claude CodeCodex

Route a task to the best LLM based on task type and complexity.

ypollak2/llm-router

Skill Claude CodeCodex

Route tasks to the cheapest capable model automatically using llm-router MCP tools.

ypollak2/llm-router

Skill Claude CodeCodex

Track and report how much you've saved by routing tasks to cheaper models.

senda-labs/DQIII8

Skill Claude CodeCodex

Genera y entrega informes de internacionalización (Diagnóstico + Plan) para pymes españolas. Batch pipeline via Orchestrator v4 (core.cli) desde tmux externo. NUNCA empresa-a-empresa con Agent Haiku manual.

senda-labs/DQIII8

Skill Claude CodeCodex

Adversarial review of a plan file — a single Opus pass — before implementation of a ≥3-module or ambiguous-scope change.

senda-labs/DQIII8

Skill Claude CodeCodex

Adversarial security testing — attempts to break the codebase using real hacker techniques. Tests OWASP Top 10, prompt injection, MCP poisoning, dependency attacks, auth bypass, and vibe-coding-specific patterns. Generates exploit report. NEVER auto-invoked — user must explicitly request.

SeongwoongCho/adaptive-harness

Skill Claude CodeCodex

Manage the adaptive-harness pool: list, inspect, promote, demote harnesses. Use when user asks about harness status or wants to manage the pool.

SeongwoongCho/adaptive-harness

Skill Claude CodeCodex

Reference for the 6-axis task taxonomy used by adaptive-harness routing. Use when user asks how tasks are classified.

SeongwoongCho/adaptive-harness

Skill Claude CodeCodex

Auto-mode bootstrap for adaptive-harness. Intercepts tasks, routes to optimal harness, evaluates results. Use on every task when adaptive-harness auto-mode is active.

tellang/triflux

Skill Claude CodeCodex

A prompt-formatting helper that turns a rough idea written in everyday language into one Claude Code `/goal` instruction. It organizes the desired result, how to check it, limits, and when to stop.

tellang/triflux

Skill Claude CodeCodex

A question-driven workflow for turning a vague implementation request into specific requirements. It measures ambiguity—how much the goal, constraints, and success criteria are unclear—and asks questions to reduce it.

tellang/triflux

Skill Claude CodeCodex

A release workflow for publishing triflux versions through GitHub Releases, the npm package registry, and the Claude Code marketplace. It also supports version changes, dry runs, skipped tests, and no-publish runs.

cherninlab/ennodia

Skill Claude CodeCodex

Audit an answer or implementation against primary sources before recommending changes.

cherninlab/ennodia

Skill Claude CodeCodex

Evaluate benchmark design for fair baselines, measurable outcomes, leakage, cherry-picking, and reproducibility.

cherninlab/ennodia

Skill Claude CodeCodex

Review a large question by staying inside one assigned slice, then support synthesis across several focused shard answers.

clervo/clervo

Skill Claude CodeCodex

Continuously execute a scoped Clervo production build through implementation, developer experience, hardening, and proof without overstating public readiness.

clervo/clervo

Skill Claude CodeCodex

Inventory, stop, and remove only explicitly owner-approved Clervo cloud resources while preserving unrelated and legacy assets, costs, audit history, and recovery evidence. Use for cloud cleanup, cost-exposure shutdown, disposable qualification teardown, or zero-resource verification.

clervo/clervo

Skill Claude CodeCodex

Prepare, review, or implement Clervo Web design with the canonical brand language, truthful product-evidence boundaries, design tokens, responsive behavior, accessibility, reduced motion, visual QA, and performance budgets. Use for Clervo UI, website, design-system, Figma, cinematic layout, motion, screenshot…