MatrAIx-Persona-8B: Skill for Claude Code

.github/skills/persona-extraction-quality-check/SKILL.md

persona-extraction-quality-check is a skill for Claude Code from MatrAIx-ai/MatrAIx-Persona-8B. It costs 108 tokens per session (2,234 once invoked), scanned A, original, MIT.

A review method for checking whether an extracted persona matches its original source profile. A persona is a structured description of a person’s traits or behavior, and the source profile is treated as the factual reference.

In plain words
What is it for?
Use it to inspect individual fields, score evidence and descriptions using the defined M1–M7 rubric, compare independent reviewers, and identify identity mismatches.
Why use it?
It prevents reviewers from judging incomplete or mismatched records and keeps quality checks consistent across different persona extractions.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

This is MatrAIx-ai/MatrAIx-Persona-8B's own configuration. It tells Claude Code how to work on MatrAIx-Persona-8B itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MatrAIx-Persona-8B configures →

About the project

MatrAIx is an infrastructure for evaluating AI systems and interactive products with simulated users represented by language-model agents, each based on a distinct persona. It helps researchers test products across surveys, chatbots, websites, and native apps while studying results for individual groups and whole populations. The catalogue entry contains skills for working with this simulation system.

MatrAIx-ai/MatrAIx-Persona-8B · 1,881 stars · on GitHub · matraix.ai

Reuse

Borrowing it

Nothing to install: this file belongs to MatrAIx-ai/MatrAIx-Persona-8B. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MatrAIx-ai/MatrAIx-Persona-8B/main/.github/skills/persona-extraction-quality-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MatrAIx-ai/MatrAIx-Persona-8B

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for persona-extraction-quality-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/matraix-ai/matraix-persona-8b/persona-extraction-quality-check/github.svg)](https://agentmods.dev/skills/matraix-ai/matraix-persona-8b/persona-extraction-quality-check)
Your own site
<a href="https://agentmods.dev/skills/matraix-ai/matraix-persona-8b/persona-extraction-quality-check"><img src="https://agentmods.dev/badge/skills/matraix-ai/matraix-persona-8b/persona-extraction-quality-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for persona-extraction-quality-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/matraix-ai/matraix-persona-8b/persona-extraction-quality-check"><img src="https://agentmods.dev/badge/skills/matraix-ai/matraix-persona-8b/persona-extraction-quality-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,234 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.02234
Opus 5 $0.00054 $0.01117
Sonnet 5 $0.00022 $0.00447
Haiku 4.5 $0.00011 $0.00223

Measured 12d ago against content hash 876ef6b247de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

persona-extraction-quality-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/aggregate_reviews.py, scripts/prepare_persona_packets.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/persona-extraction-quality-check/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona Extraction Quality Check

Evaluate extraction quality one complete persona at a time. The source profile is ground truth. Never score an extraction without pairing it to its exact source record.

Canonical rubric

Before judging anything, read the complete canonical rubric at:

persona/human_extraction/docs/EXTRACTION_QUALITY_RUBRIC.md

Use its M1–M7 definitions and 1–5 anchors verbatim. Do not invent a replacement scale or silently reinterpret a metric. Read the judge protocol before dispatching reviewers.

Non-negotiable rules

  1. One judge task receives exactly one persona packet. Never ask one reviewer call to score several personas.
  2. Judge the full persona. Do not split one persona's fields across workers; M4–M7 require whole-record context.
  3. Inspect fields before record-level scoring. Check every emitted field for M1 value, M2 evidence, and M3 description, then score M4–M7.
  4. Parallelize across independent reviews, not within a persona. Multiple personas and/or independent model reviews may run concurrently.
  5. Keep reviewers independent. A reviewer must not see another review before producing its own result.
  6. Fail closed on identity mismatch. Never pair records by guessed position if ResponseId, response_id, row_index, or another stable ID conflicts.
  7. Do not treat confidence as correctness. Verify the value and evidence against the source even when confidence is 1.0.
  8. Resume safely. Skip an existing valid (persona_id, actual_model) review unless the user explicitly requests overwrite.
  9. Do not claim a model was used unless the runtime actually selected it. Record both requested and actual model names.
  10. Never expose one person's full source profile in aggregate reports. Keep source text in per-persona packets; aggregate only scores and concise issue summaries.

Inputs

Require these logical inputs:

  • Source profiles: CSV, JSONL, SQLite, or a directory containing them. For Stack Overflow 2025, prefer the exact filtered CSV used by extraction, normally results_2025_completeness_60.csv, not the broader raw CSV.
  • Extracted personas: one or more JSONL files, a ZIP containing JSONL shards, or a directory of shards.
  • Output directory: packets, independent reviews, consensus, and summaries go here.
  • Selection: explicit IDs, a deterministic sample, or all records.

Read the full file on GitHub · 172 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 172 lines · 108 tokens per session scan A 876ef6b247de

Subscribe to this mod's changes

persona-extraction-quality-check is a skill published in the GitHub repository MatrAIx-ai/MatrAIx-Persona-8B (1,881 stars, last pushed 3d ago), licensed MIT. It adds 108 tokens to every session and 2,234 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens