Why it is worth attention

It offers a reusable, agent-agnostic workflow that produces both machine-readable JSON and human-readable reports, with a strong emphasis on source-attributed data and clear marking of inferred information.

Who it is for

Researchers and academics submitting to AI/ML conferences
Developers using coding agents to track deadlines
Conference organizers monitoring competitive venues
Students planning submission timelines

Use cases

Track submission deadlines for top NLP, CV, or general AI conferences
Compare acceptance rate trends across multiple venues over five years
Generate a structured conference calendar for project planning
Automate deadline reminders via coding agent chat responses

Strengths

Zero-configuration: no API keys or build steps needed
Multi-agent support: works with Codex, Claude Code, and any fetch-capable agent
Source-transparent: marks confirmed vs. approximate data with citations
Rich output: produces both structured JSON and a formatted Markdown report

Considerations

Requires the host agent to have web search/fetch capability and filesystem write access
Inferred future deadlines are approximate and may shift
Acceptance-rate data may vary by source (main track vs. all tracks); sources are noted but not guaranteed

README quick start

ConferenceWatch

An Agent Skill that watches upcoming AI/ML conferences and reports, for each one: submission deadlines (every stage), dates, location, special sessions / call for papers, official web links, and a 5-year acceptance-rate trend. It is written to be reusable across common coding agents that can search the web — Claude Code, Codex, and similar.

What it produces

Every run yields two artifacts:

conferences..json — the structured source of truth. One object per conference (keyed by acronym), each holding the upcoming edition (deadlines, location, special sessions, links) and a 5-year acceptance-rate trend. Schema: references/json-schema.md.
conference-report..md — a human-readable report with a short summary, a nearest-deadlines table, a per-conference breakdown, and a clearly separated "approximate / inferred" section. Template: assets/report.template.md.

The agent also answers directly in chat with the most time-sensitive items.

How to use

This skill is plain Markdown + JSON, so it can be used by Codex, Claude Code, or any agent that can read SKILL.md, search/fetch the web, and write files.

Install for Codex

Clone directly into Codex's personal skills directory:

git clone https://github.com/Zsun79/ConferenceWatch.git ~/.codex/skills/conference-watch

If you already cloned the project somewhere else, run this from the root of this cloned skill repository to link the current checkout into Codex:

mkdir -p ~/.codex/skills
ln -s "$(pwd)" ~/.codex/skills/conference-watch

Then ask Codex naturally for AI/ML conference deadlines, venue comparisons, or submission planning. Codex will use SKILL.md as the workflow when the request matches the skill description.

Install for Claude Code

Clone directly into Claude's personal skills directory:

git clone https://github.com/Zsun79/ConferenceWatch.git ~/.claude/skills/conference-watch

If you already cloned the project somewhere else, run this from the root of this cloned skill repository to link the current checkout into Claude:

mkdir -p ~/.claude/skills
ln -s "$(pwd)" ~/.claude/skills/conference-watch

If this checkout is the project where you want Claude to load the skill, run th

Description

An Agent Skill to watch the deadlines of latest AI conference.

Related repositories

Similar projects matched by category, topics, and programming language.

HezaoHezao

Featured

poirot

Poirot is a deep research agent kernel with a middleware-first architecture, five-layer long-term memory, multi-agent orchestration, sandbox isolation, and a three-layer skill self-evolution system, backed by 2400+ tests.

AI & Machine LearningLarge Language Models

AgriciDaniel

Featured

anti-slop

Anti-slop is a tool for detecting and repairing substance defects in AI-assisted prose, code, documentation, and agent output using deterministic scanners and structural procedures that produce verifiable artifacts rather than authorship judgments.

AI & Machine LearningLarge Language Models

Vincentwei1021

video-shotcraft

An AI agent skill that turns Claude Code or Codex into a motion-design studio for crafting cinematic product videos with Remotion, offering 106 shot recipe cards, 162 styles, 161 motion previews, and a production-ready template.

TypeScript

2,432