Agent Skills

---

name: brand-setup

description: Set up or update the brand profile every skill reads: voice, audience, compliance. "set up a new brand"

---

name: budget-optimizer

description: Optimize channel budget with diminishing-returns models. Pacing → budget-tracker. "is our channel split right"

---

name: budget-tracker

description: Project ad budget pacing by script from live accounts or given numbers: month-end overspend. "are we overspending this month"

---

name: c2pa-metadata

description: Embed C2PA provenance in AI-generated images, video or PDF by script. "add content credentials to this asset"

---

name: campaign-audit

description: Audit all campaigns running for a brand across channels, with 4-tier triage. "we just inherited this account"

---

name: campaign-orchestrator

description: Orchestrate a campaign lifecycle: briefs, budget models, UTMs, post-mortems. "set up UTM naming conventions"

---

name: campaign-plan

description: Write a multi-channel campaign plan: objectives, channel mix, budget, timeline, KPIs. "build the Q3 campaign plan"

---

name: campaign-status

description: Show status of every tracked campaign: health, spend, executions, pending approvals. "what campaigns are running right now"

---

name: case-study-plan

description: Plan a case study: narrative, interview questions, formats. "turn this client win into a case study"

---

name: check

description: Run the scored pre-publish gate via eval-runner.py: claims, brand voice, compliance, AI tells. "check this before we publish"

---

name: churn-risk

description: Score churn risk per segment by script, with tiered retention playbooks. "which customers are about to churn"

---

name: claude-authenticity

description: Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.

---

name: client-onboarding

description: Build a client onboarding pack: kickoff agenda, discovery questions, 30-60-90. "we just signed a new client"

---

name: client-proposal

description: Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. "respond to this RFP"

---

name: client-report

description: Write a white-labeled report for one client from tracked data. All clients → agency-dashboard. "prepare the monthly client report"

---

name: client-validation-document

description: Produce the Part 5 client validation document: evidence-cited findings for client decisions. "prepare v1 findings for client review"

---

name: eval-design

description: Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial examples, extract eval dimensions from traces/specs, or build a labeled evaluation set. Also use when the user mentions test data design, eval coverage, difficulty stratification, synthetic data generation for eval, or "how to create good evaluation data." Outputs datasets in OpenJudge-compatible format.

---

name: eval-report

description: Use when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit, ship readiness, evaluation maturity, or "how good is my evaluation system itself." This is a read-only analysis skill.

---

name: find-skills-combo

description: Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — **Maximum Quality** (best skill per subtask) and **Minimum Dependencies** (fewest installs). Use this skill whenever the user wants to find skills, asks "how do I do X", "find a skill for X", or describes a task that likely requires multiple capabilities working together. Also use when the user mentions composing workflows, building pipelines, or needs help across several domains at once — even if they only say "find me a skill". This skill supersedes simple single-skill search by decomposing the task into subtasks and assembling an optimal skill portfolio.

---

name: meta-eval

description: Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.

---

name: metric-design

description: Use when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.

---

name: mmx-cli

description: Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and web search. Use when the user needs to create AI-generated multimedia content, produce narrated audio from text, compose music, or search the web through MiniMax AI services.

---

name: prompt-regression

description: Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt regression testing. Outputs per-dimension win rates with statistical significance using OpenJudge PairwiseAnalyzer.

---

name: rag-eval

description: Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.