Official agent skill

Update Conferences

by huggingface in huggingface/ai-deadlines

Prioritize and run Modal conference-deadline agents on high-ROI conferences only.

OfficialMITAuto-check passedAI & LLM Engineering

Install Update Conferences

skills CLI

$ npx skills add huggingface/ai-deadlines --skill update-conferences -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install huggingface/ai-deadlines update-conferences --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/huggingface/ai-deadlines.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/update-conferences .claude/skills/update-conferences && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "update-conferences" agent skill from https://github.com/huggingface/ai-deadlines/tree/main/.agents/skills/update-conferences into .claude/skills/update-conferences/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "update-conferences", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/huggingface/ai-deadlines/tree/main/.agents/skills/update-conferences

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add huggingface/ai-deadlines --skill update-conferences -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install huggingface/ai-deadlines update-conferences --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huggingface/ai-deadlines.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/update-conferences .agents/skills/update-conferences && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "update-conferences" agent skill from https://github.com/huggingface/ai-deadlines/tree/main/.agents/skills/update-conferences into .agents/skills/update-conferences/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "update-conferences", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add huggingface/ai-deadlines --skill update-conferences -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install huggingface/ai-deadlines update-conferences --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huggingface/ai-deadlines.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/update-conferences .cursor/skills/update-conferences && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "update-conferences" agent skill from https://github.com/huggingface/ai-deadlines/tree/main/.agents/skills/update-conferences into .cursor/skills/update-conferences/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "update-conferences", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/huggingface/ai-deadlines.git --path .agents/skills/update-conferences

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add huggingface/ai-deadlines --skill update-conferences -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install huggingface/ai-deadlines update-conferences --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huggingface/ai-deadlines.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/update-conferences .gemini/skills/update-conferences && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "update-conferences" agent skill from https://github.com/huggingface/ai-deadlines/tree/main/.agents/skills/update-conferences into .gemini/skills/update-conferences/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "update-conferences", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install huggingface/ai-deadlines update-conferences

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add huggingface/ai-deadlines --skill update-conferences -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/huggingface/ai-deadlines.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/update-conferences .github/skills/update-conferences && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "update-conferences" agent skill from https://github.com/huggingface/ai-deadlines/tree/main/.agents/skills/update-conferences into .github/skills/update-conferences/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "update-conferences", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add huggingface/ai-deadlines --skill update-conferences -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install huggingface/ai-deadlines update-conferences --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huggingface/ai-deadlines.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/update-conferences .opencode/skills/update-conferences && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "update-conferences" agent skill from https://github.com/huggingface/ai-deadlines/tree/main/.agents/skills/update-conferences into .opencode/skills/update-conferences/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "update-conferences", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: update-conferences
GitHub stars: 350
Token cost: ~1.3k tokens
SKILL.md length: 631 words
Files: 1
Skills in repo: 1
Repo updated: Sep 23, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Prioritize and run Modal conference-deadline agents on high-ROI conferences only.

Works in 4 steps: Scan src/data/conferences/*.yml for… → Cross-check typical CFP timing only as a… → Present a short ranked table (conference… → …
Updating conference YAML via agents/modalagent.py
SKILL.md covers When to use, Selection rules (high ROI only), Running the agent and Data conventions, plus 4 more sections
Calls uv; needs GH_TOKEN and HF_TOKEN

What it does

Update Conferences is an agent skill from huggingface/ai-deadlines, published by the product's own GitHub organization. Prioritize and run Modal conference-deadline agents on high-ROI conferences only. Use when updating conference YAML via agents/modalagent.py, choosing which conferences to refresh, running deadline agents, or avoiding expensive all-conference Modal runs.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. It works with Hugging Face. The repository describes itself as: ⏰ AI conference deadline countdowns. The licence is MIT.

When your agent uses it

Updating conference YAML via agents/modalagent.py
Choosing which conferences to refresh
Running deadline agents
Avoiding expensive all-conference Modal runs

Example prompts

“/update-conferences”

Requirements

Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Scan src/data/conferences/*.yml for signals: deadlines: [], venue: TBA, to be announced, near-term date: values, missing fields on an…
Cross-check typical CFP timing only as a soft prior — YAML + calendar proximity win.
Present a short ranked table (conference stem, why now). Aim for ~10–15, not all ~67.
Confirm with the user before launching runs.

What it can do on your machine

Read from SKILL.md and the folder at commit f9642a1. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- GH_TOKEN
- HF_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Update Conferences loads about 1.3k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 631 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~69
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from huggingface/ai-deadlines at commit f9642a1, republished under its MIT licence (© huggingface). 631 words, ~1,344 tokens.

Download SKILL.mdSave it as .claude/skills/update-conferences/SKILL.md (or your agent's skills folder).

name: update-conferences
description: Prioritize and run Modal conference-deadline agents on high-ROI conferences only. Use when updating conference YAML via agents/modal_agent.py, choosing which conferences to refresh, running deadline agents, or avoiding expensive all-conference Modal runs.
disable-model-invocation: true

Update Conferences

Cost-aware workflow for refreshing src/data/conferences/*.yml via agents/modal_agent.py on Modal. Prefer a short priority list over --all-conferences.

When to use

User asks to update conference deadlines / run the Modal agent
User wants conferences “likely to have new data”
Full-repo runs look too expensive (~$2–4 per conference)

Selection rules (high ROI only)

Rank by actionable now, not “missing next year.”

Run when:

Active cycle: a deadline or milestone falls in the next ~8 weeks
A milestone just passed and remaining dates may have changed (venue: TBA, wrong camera-ready, missing rebuttal/notification)
YAML is incomplete for a conference already in flight (e.g. empty deadlines: [] while CFP is open)

Skip when:

Far-future CFPs (e.g. CVPR/ICLR 2027 months before CFP typically opens)
Conference was just successfully updated in a recent run
Archival gaps only (missing old years) with no imminent news
Complete past/current year data with no near-term milestones

Do not treat “no year: N+1 block yet” as sufficient reason to run.

How to build the list

Scan src/data/conferences/*.yml for signals: deadlines: [], venue: TBA, to be announced, near-term date: values, missing fields on an active year.
Cross-check typical CFP timing only as a soft prior — YAML + calendar proximity win.
Present a short ranked table (conference stem, why now). Aim for ~10–15, not all ~67.
Confirm with the user before launching runs.

Running the agent

Default runner: Modal (agents/modal_agent.py). Pushes to huggingface/ai-deadlines main.

bash

# Prefer one conference at a time
uv run modal run --detach agents/modal_agent.py --conference-name <stem>

# Small smoke test only
uv run modal run --detach agents/modal_agent.py --limit 1

# Avoid unless explicitly requested (expensive)
uv run modal run --detach agents/modal_agent.py --all-conferences

There is no --conferences a,b,c flag — run sequentially with --conference-name, waiting for each to finish (or getting user OK) before the next.

Preflight

Check for already-running apps: uv run modal app list
Stop stale/stuck runs before starting a new one if the user wants a clean test
Required Modal secrets: anthropic, github-token (GH_TOKEN with repo), exa
anthropic is HF Inference Providers config (not a raw Anthropic key). Do not replace it with a bare huggingface secret that only has HF_TOKEN.

Monitor and report

After each run, report briefly:

Modal app URL / app id
Status: pushed | no_changes | error | timeout
commit_sha when status is pushed
Cost and approx duration if available
Concrete YAML changes (or that push was skipped)
Whether any retrieval agent hit error_max_turns / budget limits / wall-clock timeout

Watch logs for: Result:, pushed, no_changes, timeout, commit_sha, Total pipeline, Limit reached, Wall-clock timeout, Authentication failed.

Show full SKILL.md (252 more words)Show less

Data conventions

Deadline timezone: always AoE. Never write UTC-12 or UTC+12.
Conference stem = YAML filename without .yml (e.g. emnlp, wacv, 3dv)
Leave past conference years unchanged unless the user asks for archival fixes
YAML is validated in Python before push (parse, required fields, AoE, past years byte-for-byte). Failures return error and do not push.

Timeouts

Per-conference Modal function timeout: 3600s, overridable at deploy with MODAL_CONFERENCE_TIMEOUT
Per retrieval/aggregation agent wall-clock: 300s (AGENT_WALL_CLOCK_SECONDS)
Retrieval agents fail closed: last-turn hook asks for structured output; empty error_max_turns gets one no-tools follow-up. Do not treat a hang until the function cap as no_changes.

Cost intuition

Typical single-conference run: ~$2–4 and ~5–15 minutes
Prefer confirming the next conference with the user after each successful run when iterating a priority list
no_changes is a success (agents verified; push skipped)

Troubleshooting

Symptom	Action
401 / wrong Claude model id	Refresh Modal `anthropic` secret (HF router + model env vars); do not switch the app to the plain `huggingface` secret
`GH_TOKEN` / push failed	User must refresh Modal `github-token`; do not invent tokens from guesses
Hang / no log progress	Check Modal dashboard; local stream can stall while cloud work continues
Agents burn all turns	Note it; last-turn hook should force structured `requires_update: false`. Pipeline can still succeed if ≥1 retrieval agent returns structured output
Status `timeout`	Per-agent 5 min cap or Modal 3600s function timeout; not the same as `no_changes`

Local alternative

Only if the user asks to run locally instead of Modal:

bash

uv run --env-file keys.env -m agents.agent --conference_name <stem>

For HF Jobs debugging, see agents/README.md / agents/hf_jobs_agent.py — not the default path.

Files

Just SKILL.md in .agents/skills/update-conferences of huggingface/ai-deadlines.

Open the folder on GitHubat commit f9642a1

Compare with similar skills

Update Conferences next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Update Conferences compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Update Conferences this skillhuggingface/ai-deadlines	350	—	~1.3k	Automated safety check: Pass	MIT	15 days ago
Peft Fine TuningOrchestra-Research/AI-Research-SKILLs	13k	9 repos	~3.1k	Automated safety check: Pass	MIT	3 mo ago
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs	13k	9 repos	~3.3k	Automated safety check: Pass	MIT	3 mo ago
Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs	13k	8 repos	~2.3k	Automated safety check: Pass	MIT	3 mo ago
SageMaker Serving Image Selectionhuggingface/skills	11k	1 repos	~4.6k	Automated safety check: Pass	Apache-2.0	7 days ago
Hugging Face LLM Trainerhuggingface/skills	11k	3 repos	~7.2k	Automated safety check: Pass	Apache-2.0	7 days ago

Similar skills

Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
13k GitHub starsUsed in 9 repos~3.1k tokens
AI & LLM EngineeringAuto-check passed
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
13k GitHub starsUsed in 9 repos~3.3k tokens
AI & LLM EngineeringAuto-check passed
Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
13k GitHub starsUsed in 8 repos~2.3k tokens
AI & LLM EngineeringAuto-check passed
SageMaker Serving Image Selection
huggingface/skills
Official
Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.
11k GitHub starsUsed in 1 repo~4.6k tokens
AI & LLM EngineeringAuto-check passed
Hugging Face LLM Trainer
huggingface/skills
Official
Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.
11k GitHub starsUsed in 3 repos~7.2k tokens
AI & LLM EngineeringAuto-check passed
LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
13k GitHub starsUsed in 8 repos~3k tokens
AI & LLM EngineeringAuto-check passed

Works with

Hugging Face

Questions about Update Conferences

What does Update Conferences do?

Prioritize and run Modal conference-deadline agents on high-ROI conferences only. Update Conferences is an agent skill from huggingface/ai-deadlines, published by the product's own GitHub organization. Prioritize and run Modal conference-deadline agents on high-ROI conferences only.

When should I use Update Conferences?

Update Conferences fits situations like: updating conference YAML via agents/modalagent.py; choosing which conferences to refresh; running deadline agents; avoiding expensive all-conference Modal runs.

How do I install Update Conferences in Claude Code?

Run `npx skills add huggingface/ai-deadlines --skill update-conferences -a claude-code`. Or copy the skill folder (.agents/skills/update-conferences in huggingface/ai-deadlines) into .claude/skills/update-conferences in your project. Claude Code loads it when a task matches its description.

How do I install Update Conferences in Codex?

Run `npx skills add huggingface/ai-deadlines --skill update-conferences -a codex`. Or copy the skill folder (.agents/skills/update-conferences in huggingface/ai-deadlines) into .agents/skills/update-conferences in your project. Codex loads it when a task matches its description.

Can I use Update Conferences in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huggingface/ai-deadlines --skill update-conferences -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-conferences, .gemini/skills/update-conferences, .github/skills/update-conferences and .opencode/skills/update-conferences in your project.

What does Update Conferences need to run?

Going by SKILL.md and its folder, Update Conferences needs the command-line tools its instructions call (uv) and credentials named GH_TOKEN and HF_TOKEN. Our summary lists: Python 3.

Does Update Conferences access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Update Conferences safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Update Conferences use?

Update Conferences is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update Conferences use?

About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Update Conferences?

Skills that share tags, products or a category with Update Conferences: Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars) and SageMaker Serving Image Selection (huggingface/skills, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Conferences?

huggingface (a GitHub organization, an official publisher) maintains it in huggingface/ai-deadlines, which has 350 GitHub stars. The repository was last updated on September 23, 2026.

Source: huggingface/ai-deadlines on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Update Conferences

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Update Conferences

When to use

Selection rules (high ROI only)

How to build the list

Running the agent

Preflight

Monitor and report

Data conventions

Timeouts

Cost intuition

Troubleshooting

Local alternative

Files

Compare with similar skills

Similar skills

Peft Fine Tuning

Segment Anything Model Guide

Chroma Vector Database

SageMaker Serving Image Selection

Hugging Face LLM Trainer

LLM Benchmarking with lm-evaluation-harness

Related

Questions about Update Conferences