Tashan-TopicLab: Skill for Codex

.codex/skills/youth-ted-activity-publisher/SKILL.md

youth-ted-activity-publisher is a skill for Codex from TashanGKD/Tashan-TopicLab. It costs 94 tokens per session (2,959 once invoked), scanned A, original, MIT.

A workflow for turning Youth TED meeting materials into activity records in TopicLab. It combines a poster image with a Tencent Meeting transcript and stores the resulting activity data for the website.

In plain words
What is it for?
Converting posters to WebP images, retrieving or summarizing recordings and transcripts, generating activity JSON, saving records to the youth TED database table, and verifying the published result.
Why use it?
It removes the manual work of converting posters, finding and summarizing meeting transcripts, creating structured activity content, and updating the database.

Skill for Codex

Written for Codex: installed under .codex/. Also seen: mentions Codex.

This is TashanGKD/Tashan-TopicLab's own configuration. It tells Codex how to work on Tashan-TopicLab 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 Tashan-TopicLab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TashanGKD/Tashan-TopicLab. 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/TashanGKD/Tashan-TopicLab/main/.codex/skills/youth-ted-activity-publisher/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/Tashan-TopicLab

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 youth-ted-activity-publisher

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashangkd/tashan-topiclab/youth-ted-activity-publisher/github.svg)](https://agentmods.dev/skills/tashangkd/tashan-topiclab/youth-ted-activity-publisher)
Your own site
<a href="https://agentmods.dev/skills/tashangkd/tashan-topiclab/youth-ted-activity-publisher"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-topiclab/youth-ted-activity-publisher/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 youth-ted-activity-publisher

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/tashan-topiclab/youth-ted-activity-publisher"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-topiclab/youth-ted-activity-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,959 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 $0.00094 $0.02959
Opus 5 $0.00047 $0.01479
Sonnet 5 $0.00019 $0.00592
Haiku 4.5 $0.00009 $0.00296

Measured 12d ago against content hash e175273d6644, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

youth-ted-activity-publisher 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 3 executable files (scripts/plan_latest_wednesday_activity.py, scripts/save_tencent_transcript.py, scripts/upsert_youth_ted_activity.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.

.codex/skills/youth-ted-activity-publisher/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Youth TED Activity Publisher

Overview

Use this skill to turn a Youth TED meeting package into a website activity card: poster image -> WebP blob, Tencent Meeting transcript -> local transcript artifact -> compact structured JSON, and both -> topiclab-backend database.

The default user request may contain only one poster image. In that case, do not ask for meeting IDs first. Assume the activity is the latest completed Wednesday 20:00 Asia/Shanghai Tencent Meeting, discover the transcript from Tencent Meeting, generate question-style topics with icons, and upsert the activity into topiclab.youth_ted_activities.

The canonical backend is topiclab-backend, not backend. The frontend activity list reads GET /api/v1/youth-ted/activities; do not edit the frontend fallback poster or fallback activity unless the user explicitly asks.

Local Secrets

Tencent Meeting tools require TENCENT_MEETING_TOKEN. Prefer the environment variable when it is already present. For local automations in this repo, a non-git-tracked fallback may exist at:

.codex/skills/youth-ted-activity-publisher/.secrets/tencent-meeting.env

When the token is not already exported, load it before Tencent Meeting calls:

set -a
source .codex/skills/youth-ted-activity-publisher/.secrets/tencent-meeting.env
set +a

Never print this file, include it in generated reports, copy it into tracked files, or commit it.

Workflow

Weekly Thursday Replay Update

Use this path for the recurring Thursday automation that updates the latest completed Wednesday 20:00 Youth TED replay.

  1. Treat the target event as the latest completed Wednesday 20:00 Asia/Shanghai slot:
topiclab-backend/.venv/bin/python .codex/skills/youth-ted-activity-publisher/scripts/plan_latest_wednesday_activity.py \
  --poster /absolute/path/to/current-week-poster.png

If the weekly automation does not have a current poster path, do not reuse an older poster and do not guess from unrelated images. Continue with Tencent Meeting discovery and transcript saving when possible, then report that the database upsert is blocked until the current poster image is provided.

Read the full file on GitHub · 220 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 · 220 lines · 94 tokens per session scan A e175273d6644

Subscribe to this mod's changes

youth-ted-activity-publisher is a skill published in the GitHub repository TashanGKD/Tashan-TopicLab (5 stars, last pushed 18d ago), licensed MIT. It adds 94 tokens to every session and 2,959 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 2026-08-31.