Agent skill

AI Fomo Sources

by vincelele in vincelele/ai-fomo-skills

Configure AI information sources and collect traceable raw snapshots for an AI FOMO workspace.

MITAuto-check passedDevelopment

Install AI Fomo Sources

skills CLI
$ npx skills add vincelele/ai-fomo-skills --skill ai-fomo-sources -a claude-code

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

GitHub CLI
$ gh skill install vincelele/ai-fomo-skills ai-fomo-sources --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/vincelele/ai-fomo-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ai-fomo-sources .claude/skills/ai-fomo-sources && 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/

Facts

Skill name
ai-fomo-sources
GitHub stars
248
Token cost
~1.2k tokens
SKILL.md length
428 words
Files
9 (incl. scripts, references, assets)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Configure AI information sources and collect traceable raw snapshots for an AI FOMO workspace.

  • Works in 9 steps: Confirm the target AI FOMO workspace. → Identify the source type and required… → If the source is supported by… → …
  • The user wants to add feeds
  • SKILL.md covers Purpose, Use When, Do Not Use When and Core Workflow, plus 6 more sections
  • Runs Python scripts from its folder; calls python; reaches xiaoyuzhoufm.com; needs X_BEARER_TOKEN

What it does

AI Fomo Sources is an agent skill from vincelele/ai-fomo-skills. Configure AI information sources and collect traceable raw snapshots for an AI FOMO workspace. Use when the user wants to add feeds, docs, X accounts, GitHub repos, YouTube videos, podcasts, podcast comments, audio transcripts, changelogs, RSS sources, or other source connectors. This skill handles source intake only and should not judge or file knowledge.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/manual-raw-snapshot.template.md` and `assets/source-registry.example.yaml`).

It sits in Development, covering Podcasting and Changelog and release notes. It works with GitHub and YouTube. The repository describes itself as: Personal superalignment skills for turning AI information overload into reusable knowledge, signals, and digests. The licence is MIT.

When your agent uses it

  • The user wants to add feeds
  • Podcast comments
  • Audio transcripts
  • Other source connectors

Example prompts

  • “/ai-fomo-sources”

Requirements

  • Python 3
  • A credential in X_BEARER_TOKEN

Workflow steps

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

  1. Confirm the target AI FOMO workspace.
  2. Identify the source type and required access method.
  3. If the source is supported by scripts/import_source.py, directly import it.
  4. Use references/source-connectors.md when connector-specific guidance is needed.
  5. Prefer preview or dry-run before bulk writes.
  6. Store credentials outside committed files.
  7. Write source material only to raw/inbox/ by default.
  8. Preserve source metadata: URL, title, author, source type, published time, collected time, and dedupe key when known.
  9. Report what was collected and what still needs authentication or manual review.

What it can do on your machine

Read from SKILL.md and the folder at commit 2401c6e. 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

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • xiaoyuzhoufm.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • X_BEARER_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Fomo Sources loads about 1.2k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 428 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from vincelele/ai-fomo-skills at commit 2401c6e, republished under its MIT licence (© vincelele). 428 words, ~1,240 tokens.

Download SKILL.mdSave it as .claude/skills/ai-fomo-sources/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
ai-fomo-sources
description
Configure AI information sources and collect traceable raw snapshots for an AI FOMO workspace. Use when the user wants to add feeds, docs, X accounts, GitHub repos, YouTube videos, podcasts, podcast comments, audio transcripts, changelogs, RSS sources, or other source connectors. This skill handles source intake only and should not judge or file knowledge.

AI FOMO Sources

Purpose

Connect AI-related information sources and write traceable raw snapshots into raw/. This skill handles intake only. It must not decide long-term value.

Use When

Use this skill when the user asks to:

  • connect a source
  • configure source registry
  • collect new source material
  • create raw snapshots
  • add Feishu, Notion, GitHub, X, RSS, YouTube, podcast, podcast comments, transcript, changelog, or web sources

Do Not Use When

Do not use this skill to:

  • judge whether a source is high value
  • write wiki/sources
  • update themes or dossiers
  • generate signals or digests

Use ai-fomo for judgment after raw material exists.

Core Workflow

  1. Confirm the target AI FOMO workspace.
  2. Identify the source type and required access method.
  3. If the source is supported by scripts/import_source.py, directly import it.
  4. Use references/source-connectors.md when connector-specific guidance is needed.
  5. Prefer preview or dry-run before bulk writes.
  6. Store credentials outside committed files.
  7. Write source material only to raw/inbox/ by default.
  8. Preserve source metadata: URL, title, author, source type, published time, collected time, and dedupe key when known.
  9. Report what was collected and what still needs authentication or manual review.

Direct Import Runtime

Use scripts/import_source.py for supported sources:

bash
python scripts/import_source.py --workspace /path/to/workspace official-page --url https://example.com/changelog
python scripts/import_source.py --workspace /path/to/workspace rss --url https://example.com/feed.xml
python scripts/import_source.py --workspace /path/to/workspace github-repo --repo owner/name
python scripts/import_source.py --workspace /path/to/workspace github-trending --language python --since daily --limit 10
python scripts/import_source.py --workspace /path/to/workspace xiaoyuzhou-episode --url https://www.xiaoyuzhoufm.com/episode/episode_id
python scripts/import_source.py --workspace /path/to/workspace x-user --handle OpenAI

Use --dry-run first when importing a new source. x-user requires an X API bearer token in X_BEARER_TOKEN or a custom env var.

For Xiaoyuzhou bridge install/start, account login, subscribed inbox batch import, episode comments, and audio transcription, use scripts/xiaoyuzhou_account.py and read references/xiaoyuzhou-account.md.

bash
python scripts/xiaoyuzhou_account.py --workspace /path/to/workspace install-bridge --dry-run
python scripts/xiaoyuzhou_account.py --workspace /path/to/workspace install-bridge --start
python scripts/xiaoyuzhou_account.py --workspace /path/to/workspace bridge-status
python scripts/xiaoyuzhou_account.py --workspace /path/to/workspace import-inbox --limit 30 --max-pages 3 --dry-run
python scripts/xiaoyuzhou_account.py --workspace /path/to/workspace import-comments --episode-id episode_id --include-replies --dry-run
python scripts/xiaoyuzhou_account.py --workspace /path/to/workspace transcribe-raw --raw-file /path/to/raw.md --dry-run
python scripts/xiaoyuzhou_account.py --workspace /path/to/workspace import-inbox --limit 10 --with-comments --with-transcripts --transcript-limit 3 --dry-run
Show full SKILL.md (188 more words)Show less

Fallback Strategy

Direct import is the default. If a source is unsupported:

  1. create a manual raw snapshot from user-provided content, export, notes, or URL metadata
  2. add a registry entry only if the user explicitly wants to track the source long term
  3. hand off to ai-fomo for judgment

Do not turn fallback setup into a long onboarding survey.

Raw Snapshot Requirements

Each raw snapshot should be traceable and minimally structured:

  • source name and source id
  • source type
  • original URL or stable reference
  • title
  • author or publisher when known
  • published date when known
  • collected timestamp
  • content or excerpt permitted by the source boundary
  • metadata needed for later judgment

Credential Rules

  • Use environment variables or ignored local files for credentials.
  • Never commit tokens, cookies, or access keys.
  • Create .env.example with empty variable names only.
  • If a credential was committed, tell the user it must be rotated before public release.

Handoff

After collection, tell the user that ai-fomo should be used to judge whether the raw material deserves knowledge work.

References

  • Use references/source-connectors.md for source-type recipes.
  • Use references/xiaoyuzhou-account.md for Xiaoyuzhou bridge install, login, subscribed inbox import, comments, and transcription.

© vincelele, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references, assets) in ai-fomo-sources of vincelele/ai-fomo-skills.

  • SKILL.md
  • agents/openai.yaml
  • assets/env.example
  • assets/manual-raw-snapshot.template.md
  • assets/source-registry.example.yaml
  • references/source-connectors.md
  • references/xiaoyuzhou-account.md
  • scripts/import_source.py
  • scripts/xiaoyuzhou_account.py

Open the folder on GitHubat commit 2401c6e

Compare with similar skills

AI Fomo Sources 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.

AI Fomo Sources compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Fomo Sources this skillvincelele/ai-fomo-skills248—~1.2kAutomated safety check: PassMIT
Megaphone ReleaseKuberwastaken/megaphone170—~1.3kAutomated safety check: PassMIT
Add Release HighlightsArcReel/ArcReel5.4k—~194Automated safety check: PassAGPL-3.0
Cutting A ReleaseTriliumNext/Trilium38k—~3.2kAutomated safety check: PassAGPL-3.0
Rea Changelog Updatemorluto/rea80k—~1.9kAutomated safety check: PassMIT
Mole CLI Release Flowtw93/Mole70k—~2.6kAutomated safety check: PassGPL-3.0

Similar skills

  • Megaphone Release

    Kuberwastaken/megaphone

    Prepare, validate, publish, and verify Megaphone releases. An agent skill from Kuberwastaken/megaphone.

    170 GitHub stars~1.3k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Add Release Highlights

    ArcReel/ArcReel

    起草指定版本的版本亮点;确认后同步到 Changelog 与 GitHub Release,并推送 main. An agent skill from ArcReel/ArcReel.

    5.4k GitHub stars~194 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Cutting A Release

    TriliumNext/Trilium

    A skill your agent uses when cutting, preparing, or debugging a Trilium release — bumping the monorepo version, tagging, or diagnosing a failed "Release" workflow run.

    38k GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Prepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.

    80k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Runbook for assessing and executing a Mole CLI release: distribution channels, pre-flight checks, capital-V tags, build artifacts and the handoff to curated release notes.

    70k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Draft Release Notes

    jamiepine/voicebox

    Writes or refreshes the Unreleased section of CHANGELOG.md as a themed narrative built from the commits, PRs and diff since the last version tag.

    57k GitHub stars~941 tokensUpdated 4 days ago
    DevelopmentAuto-check passed

More from vincelele/ai-fomo-skills

  • AI Fomo

    vincelele/ai-fomo-skills

    Judge, summarize, create podcast learning notes, and file AI-related information through the user's Personal Alignment Layer.

    248 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • AI Fomo Init

    vincelele/ai-fomo-skills

    Initialize a personal AI FOMO workspace and Personal Alignment Layer.

    248 GitHub stars~946 tokensUpdated 4 mo ago
    Auto-check passed

Works with

Questions about AI Fomo Sources

What does AI Fomo Sources do?

Configure AI information sources and collect traceable raw snapshots for an AI FOMO workspace. AI Fomo Sources is an agent skill from vincelele/ai-fomo-skills. Configure AI information sources and collect traceable raw snapshots for an AI FOMO workspace.

When should I use AI Fomo Sources?

AI Fomo Sources fits situations like: the user wants to add feeds; podcast comments; audio transcripts; other source connectors.

How do I install AI Fomo Sources in Claude Code?

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

How do I install AI Fomo Sources in Codex?

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

Can I use AI Fomo Sources 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 vincelele/ai-fomo-skills --skill ai-fomo-sources -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-fomo-sources, .gemini/skills/ai-fomo-sources, .github/skills/ai-fomo-sources and .opencode/skills/ai-fomo-sources in your project.

What does AI Fomo Sources need to run?

Going by SKILL.md and its folder, AI Fomo Sources needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named X_BEARER_TOKEN. Our summary lists: Python 3; A credential in X_BEARER_TOKEN.

Does AI Fomo Sources access the network?

SKILL.md names 1 domain. In commands or code: xiaoyuzhoufm.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is AI Fomo Sources 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does AI Fomo Sources use?

AI Fomo Sources 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 AI Fomo Sources use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to AI Fomo Sources?

Skills that share tags, products or a category with AI Fomo Sources: Megaphone Release (Kuberwastaken/megaphone, 170 stars), Add Release Highlights (ArcReel/ArcReel, 5.4k stars), Cutting A Release (TriliumNext/Trilium, 38k stars) and Rea Changelog Update (morluto/rea, 80k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Fomo Sources?

vincelele (a GitHub user) maintains it in vincelele/ai-fomo-skills, which has 248 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on May 29, 2026.

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