qq-email-ground-truth

qq-email-ground-truth is a skill for Codex from EthanYoQ/Skill-hub. It costs 71 tokens per session (450 once invoked), scanned A, original, MIT.

A project-specific workflow for building and checking invoice reference datasets from a QQ email mailbox. It uses the repository’s existing scripts and evidence files to establish which emails and fields are correct.

In plain words
What is it for?
Use it to build or rebuild QQ mailbox invoice datasets, compare batch results with verified data, inspect invoice evidence, and investigate missing or incorrectly classified emails.
Why use it?
It reduces guesswork when validating automated invoice extraction from email. It also helps prevent old examples or fixed assumptions from being treated as universal rules.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to build or rebuild QQ mailbox invoice datasets, compare batch results with verified data, inspect invoice evidence, and investigate missing or incorrectly classified emails.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ethanyoq/skill-hub/qq-email-ground-truth
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add EthanYoQ/Skill-hub --skill qq-email-ground-truth
Clone the repo
git clone --depth 1 https://github.com/EthanYoQ/Skill-hub

Made for: Codex.

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 qq-email-ground-truth

README.md
[![agentmods](https://agentmods.dev/badge/skills/ethanyoq/skill-hub/qq-email-ground-truth/github.svg)](https://agentmods.dev/skills/ethanyoq/skill-hub/qq-email-ground-truth)
Your own site
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/qq-email-ground-truth"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/qq-email-ground-truth/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 qq-email-ground-truth

Your own site · 80×15
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/qq-email-ground-truth"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/qq-email-ground-truth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 450 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.
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 $0.00071 $0.00450
Opus 5 $0.00036 $0.00225
Sonnet 5 $0.00014 $0.00090
Haiku 4.5 $0.00007 $0.00045

Measured 11d ago against content hash 5294e07ed36b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

qq-email-ground-truth 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 11d ago.

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.

projects/codex-invoice/qq-email-ground-truth/SKILL.md · 33 lines

What it actually says

QQ Email Ground Truth

Use this project-level skill for QQ mailbox ground truth work in this repository.

Read references/workflow.md and references/pitfalls.md first. Read references/case-study-qq-20260201-20260311.md and references/project-artifacts.md when you need a validated example, current artifact paths, or prior evidence.

Hard Boundaries

  • Treat this as a project-local skill, not a global mailbox skill.
  • Treat the current case-study counts, type distribution, and mail IDs as one validated example only. Do not reuse them as fixed thresholds for future QQ runs.
  • Treat the currently known reimbursable types as a reference range, not a closed list. If a new type, provider, attachment pattern, or procurement scenario appears, send it to review instead of auto-excluding it.
  • Reuse build_truth_dataset.py and audit_email_truth.py. Do not create a parallel truth-building flow unless the user explicitly asks for one.

Required Workflow

  1. Confirm the mailbox account, mailbox folder, and time window.
  2. Follow references/workflow.md for the build and validation sequence.
  3. Use references/pitfalls.md as the default debug checklist when counts or fields look wrong.
  4. Use references/case-study-qq-20260201-20260311.md only as a worked example and evidence sample.
  5. Use references/project-artifacts.md to find the current canonical manifests, reports, and diagnostics.

Output Expectations

  • Prefer truth_manifest.json for machine comparison.
  • Prefer ground_truth_report.md for human review.
  • Require pending_review_count = 0 before calling a dataset final.
  • Keep excluded-email and excluded-document audit trails instead of silently dropping evidence.
Files

What ships with it

5 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. 11d ago First seen · 33 lines · 71 tokens per session scan A 5294e07ed36b

Subscribe to this mod's changes

qq-email-ground-truth is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed 4d ago), licensed MIT. It adds 71 tokens to every session and 450 once invoked, about $0.0004 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 2026-08-31.