Agent skill

AI Fomo

by vincelele in vincelele/ai-fomo-skills

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

MITAuto-check passedMedia & Creative

Install AI Fomo

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

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

GitHub CLI
$ gh skill install vincelele/ai-fomo-skills ai-fomo --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 .claude/skills/ai-fomo && 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
GitHub stars
248
Token cost
~1.2k tokens
SKILL.md length
568 words
Files
7 (incl. references, assets)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 3 steps: self-context/index.md if it exists → relevant self-context/preferences/*… → wiki/index.md when existing knowledge…
  • The user sends AI articles
  • SKILL.md covers Purpose, Use When, Do Not Use When and Required Context, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Fomo is an agent skill from vincelele/ai-fomo-skills. Judge, summarize, create podcast learning notes, and file AI-related information through the user's Personal Alignment Layer. Use when the user sends AI articles, changelogs, docs, X threads, GitHub repos, videos, podcasts, podcast transcripts, raw notes, asks whether AI content is worth reading or listening to, asks for a learning note that can replace listening to a podcast, asks what podcast segments are worth hearing, asks whether content should be kept or should go into wiki, should become a signal, or…

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files and assets (for example `agents/openai.yaml`, `assets/podcast-learning-note.template.md` and `references/alignment-rubric.md`).

It sits in Media & Creative, covering Podcasting, Changelog and release notes and Social media posts. It works with GitHub. 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 sends AI articles
  • Podcast transcripts
  • Asks whether AI content is worth reading
  • Asks for a learning note that can replace listening to a podcast

Example prompts

  • “/ai-fomo”

Workflow steps

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

  1. self-context/index.md if it exists
  2. relevant self-context/preferences/* files when needed
  3. wiki/index.md when existing knowledge may already cover the topic

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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

AI Fomo loads about 1.2k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 568 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~139
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
~4.9k

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 vincelele/ai-fomo-skills at commit 2401c6e, republished under its MIT licence (© vincelele). 568 words, ~1,167 tokens.

Download SKILL.mdSave it as .claude/skills/ai-fomo/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
ai-fomo
description
Judge, summarize, create podcast learning notes, and file AI-related information through the user's Personal Alignment Layer. Use when the user sends AI articles, changelogs, docs, X threads, GitHub repos, videos, podcasts, podcast transcripts, raw notes, asks whether AI content is worth reading or listening to, asks for a learning note that can replace listening to a podcast, asks what podcast segments are worth hearing, asks whether content should be kept or should go into wiki, should become a signal, or should update long-term preferences.

AI FOMO

Purpose

Turn AI information overload into personally aligned judgment. This skill should produce a decision, not just a summary.

Use When

Use this skill when the user:

  • sends AI-related content or a link
  • points to raw/inbox/
  • asks whether something is worth reading
  • asks whether a podcast or video is worth listening to
  • asks for a summary plus recommendation
  • asks for a podcast learning note that can replace listening to the full episode
  • asks whether something should go into wiki
  • asks for signals or a digest from retained material
  • gives feedback on filtering or summarization behavior

Do Not Use When

Do not use this skill for:

  • initializing a new workspace; use ai-fomo-init
  • connecting source APIs or feed collectors; use ai-fomo-sources
  • non-AI content with no relation to the user's alignment layer
  • generic summarization without value judgment

Required Context

Before judging material, read:

  1. self-context/index.md if it exists
  2. relevant self-context/preferences/* files when needed
  3. wiki/index.md when existing knowledge may already cover the topic

If the Personal Alignment Layer is missing or too vague, ask for minimal clarification or recommend running ai-fomo-init.

Core Workflow

  1. Read the source content directly or read the provided raw snapshot.
  2. Read the Personal Alignment Layer.
  3. Use references/alignment-rubric.md for value judgment.
  4. Reply in chat with a complete but concise summary.
  5. Make a three-tier recommendation:
    • write now: high quality, high relevance, durable judgment
    • ask first: useful but uncertain
    • skip: weak, generic, hype-heavy, or low relevance
  6. If writing files, use references/filing-rules.md.
  7. Always write or update wiki/sources before checking themes or dossiers.
  8. Prefer updating existing themes or dossiers over creating new pages.
  9. Only write signals or digests when the user asks or when the workflow explicitly calls for it.
  10. Record feedback as long-term preference only when the user indicates it should persist.
Show full SKILL.md (266 more words)Show less

Podcast Learning Note Mode

Use this mode when the source is a podcast episode, video transcript, or long-form interview and the user wants to learn without listening end to end.

Before writing the note, read references/podcast-learning-note.md. Use assets/podcast-learning-note.template.md as the scaffold when creating a Markdown file.

Default output target:

digests/podcasts/YYYY-MM-DD-short-slug.md

The note must answer three decisions:

  1. What is this episode about, and is it worth continuing?
  2. If continuing, what does the full episode cover in a readable learning structure?
  3. If listening to the original, which segments are worth hearing and which can be skipped?

Keep podcast learning notes separate from durable source summaries. Use digests/podcasts/ for human-readable learning notes and wiki/sources/ for retained long-term knowledge.

Default Chat Output

For each source, include:

  • what it is about
  • main structure or claims
  • durable mechanisms, constraints, or tradeoffs
  • why it matters or does not matter for this user
  • recommendation: write now, ask first, or skip
  • proposed filing target when relevant

Judgment Rules

  • Novelty is not importance.
  • Hype is not signal.
  • Long content is not automatically worth filing.
  • Long audio is not automatically worth listening to end to end.
  • Good filing candidates change product, system, market, evaluation, or workflow judgment.
  • If a source mainly reinforces an existing theme, update that theme rather than creating a new one.
  • Do not create a new theme for a one-off concept.
  • For podcasts, distinguish "worth reading the learning note", "worth selected listening", and "worth full listening".

References

  • Use references/alignment-rubric.md for judging value.
  • Use references/filing-rules.md before writing workspace files.
  • Use references/podcast-learning-note.md before writing podcast learning notes.
  • Use references/examples.md for calibration or testing.

© 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 6 other files (references, assets) in ai-fomo of vincelele/ai-fomo-skills.

  • SKILL.md
  • agents/openai.yaml
  • assets/podcast-learning-note.template.md
  • references/alignment-rubric.md
  • references/examples.md
  • references/filing-rules.md
  • references/podcast-learning-note.md

Open the folder on GitHubat commit 2401c6e

Compare with similar skills

AI Fomo 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Fomo this skillvincelele/ai-fomo-skills248—~1.2kAutomated safety check: PassMIT
Product Update LoggerVarnan-Tech/opendirectory674—~3.9kAutomated safety check: PassMIT
ContentclawLeoYeAI/openclaw-master-skills2.2k—~6.8kAutomated safety check: NotesMIT
Pull Request Explainer Videoheygen-com/hyperframes60k2 repos~8.4kAutomated safety check: NotesApache-2.0
PR To Videococo-research/coco513—~7.8kAutomated safety check: NotesCustom licence
ContentclawLeoYeAI/openclaw-master-skills2.2k—~5.4kAutomated safety check: NotesMIT

Similar skills

  • Product Update Logger

    Varnan-Tech/opendirectory

    Tell the skill what your product shipped. An agent skill from Varnan-Tech/opendirectory.

    674 GitHub stars~3.9k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Contentclaw

    LeoYeAI/openclaw-master-skills

    Automated content generation engine. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~6.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Pull Request Explainer Video

    heygen-com/hyperframes

    Turns a GitHub pull request into a code-change explainer video built from its diff, commits and files, rendered with HyperFrames.

    60k GitHub starsUsed in 2 repos~8.4k tokens
    Media & CreativeAuto-check: notes
  • PR To Video

    coco-research/coco

    A skill your agent uses when the user wants a GitHub PR (URL, owner/repoN, or 'this PR') made into a code-change explainer video from its diff and commits: changelog, feature reveal, fix, or refactor.

    513 GitHub stars~7.8k tokensUpdated yesterday
    Media & CreativeAuto-check: notes
  • Contentclaw

    LeoYeAI/openclaw-master-skills

    Turn papers, podcasts, and case studies into publish-ready social posts, infographics, and diagrams.

    2.2k GitHub stars~5.4k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • 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

More from vincelele/ai-fomo-skills

  • AI Fomo Sources

    vincelele/ai-fomo-skills

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

    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

What does AI Fomo do?

Judge, summarize, create podcast learning notes, and file AI-related information through the user's Personal Alignment Layer. AI Fomo is an agent skill from vincelele/ai-fomo-skills. Judge, summarize, create podcast learning notes, and file AI-related information through the user's Personal Alignment Layer.

When should I use AI Fomo?

AI Fomo fits situations like: the user sends AI articles; podcast transcripts; asks whether AI content is worth reading; asks for a learning note that can replace listening to a podcast.

How do I install AI Fomo in Claude Code?

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

How do I install AI Fomo in Codex?

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

Can I use AI Fomo 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 -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, .gemini/skills/ai-fomo, .github/skills/ai-fomo and .opencode/skills/ai-fomo in your project.

What does AI Fomo need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Fomo is instructions for the agent only.

Does AI Fomo access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Fomo 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 AI Fomo use?

AI Fomo 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 use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 3.8k tokens, read only when the agent opens those files.

What are the alternatives to AI Fomo?

Skills that share tags, products or a category with AI Fomo: Product Update Logger (Varnan-Tech/opendirectory, 674 stars), Contentclaw (LeoYeAI/openclaw-master-skills, 2.2k stars), Pull Request Explainer Video (heygen-com/hyperframes, 60k stars) and PR To Video (coco-research/coco, 513 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Fomo?

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.