Not in the top 1,000 by GitHub stars
superhero-tech/super-brain
Product Builder Second Brain - AI Product Heroes Edition 3
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
7-Skills/feynman/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bd1b84962017
No earlier version was observed for comparison.
7-Skills/ingest/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bd1b84962017
No earlier version was observed for comparison.
7-Skills/lint/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bd1b84962017
No earlier version was observed for comparison.
7-Skills/project-start/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bd1b84962017
No earlier version was observed for comparison.
7-Skills/project-update/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bd1b84962017
No earlier version was observed for comparison.
7-Skills/query/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bd1b84962017
No earlier version was observed for comparison.
7-Skills/second-brain-setup/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bd1b84962017
No earlier version was observed for comparison.
7-Skills/youtube/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → bd1b84962017
No earlier version was observed for comparison.
Verified commit bd1b84962017c0539bf3adc25b0e9eda7f050607
git clone --filter=blob:none --no-checkout https://github.com/superhero-tech/super-brain.git .hotskills/superhero-tech-super-brain && git -C .hotskills/superhero-tech-super-brain checkout --detach bd1b84962017c0539bf3adc25b0e9eda7f050607
# Copy each selected skill directory from .hotskills/superhero-tech-super-brain into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/superhero-tech/super-brain.git .hotskills/superhero-tech-super-brain && git -C .hotskills/superhero-tech-super-brain checkout --detach bd1b84962017c0539bf3adc25b0e9eda7f050607
# Copy each selected skill directory from .hotskills/superhero-tech-super-brain into .agents/skills/<skill-name>/Heat
7.5- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- feynman
7-Skills/feynman - ingest
7-Skills/ingest - lint
7-Skills/lint - project-start
7-Skills/project-start - project-update
7-Skills/project-update - query
7-Skills/query - second-brain-setup
7-Skills/second-brain-setup - youtube
7-Skills/youtube
How it works
feynman
When your agent uses it
Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin. Use when the human wants to actually understand a page in 4-Knowledge/, is about to teach or present it, or asks what the vault is hand-waving about.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
1,786 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to invoke
- How it works
- Self-check
- Hard constraints
Files
SKILL.mdcore7,193 bytesSKILL.mdcore7,193 bytesSKILL.mdcore7,193 bytesSKILL.mdcore7,193 bytesSKILL.mdcore7,193 bytes
Read SKILL.md
# Feynman
Take a concept out of `4-Knowledge/`, explain it in words a child owns, and mark every place the explanation went thin. Those places are the gaps.
Teach in the language the human is using.
**This skill reads the wiki and never edits it.** It saves the session to `9-Outputs/` and logs it, so there is a record of what got studied - but it creates no wiki page, changes no existing page, and touches nothing in `5-Raw/`. Learning is not ingesting.
## How to invoke
- "Explain X to me properly"
- "Feynman me on [topic]"
- "What am I fuzzy on?"
- `/feynman`View the complete source on GitHubingest
When your agent uses it
Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it. Use when the human drops something in the inbox, says to process it, or wants a backlog of clippings worked through.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
1,276 tokensWhen the skill is activated
Reference documents
490 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to invoke
- How it works
- Batch mode
- Daily notes
- Self-check
- Hard constraints
Files
SKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesSKILL.mdcore5,209 bytesreferences/page-templates.mddoc1,975 bytes
Read SKILL.md
# Ingest
Turn a source into wiki. Not one summary page per file - one page per concept, plus every existing page this source has something to say about.
Write wiki pages in the language the human writes in. One language per page.
## How to invoke
- "Process this", "run an ingest", "I dropped something in Inbox"
- "Process the whole inbox" for batch mode
- `/ingest`
Sources live in `2-Inbox/`. If the human clips with Obsidian Web Clipper on its default settings, check `Clippings/` too.
View the complete source on GitHublint
When your agent uses it
Health check over the compiled wiki in 4-Knowledge/, written up as a ranked report. Use when the human asks to check or lint the wiki, on the monthly maintenance pass, or before the vault gets trusted on a decision that matters.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,235 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to invoke
- What this catches, and what it does not
- How it works
- Self-check
- Hard constraints
Files
SKILL.mdcore4,933 bytesSKILL.mdcore4,933 bytesSKILL.mdcore4,933 bytesSKILL.mdcore4,933 bytesSKILL.mdcore4,933 bytesSKILL.mdcore4,933 bytes
Read SKILL.md
# Lint
Find what has rotted in the wiki, rank it, and hand the list to the human. Fixing is a separate decision.
Write the report in the language the wiki is written in.
## How to invoke
- "Check the wiki", "run a lint", "health check"
- The monthly maintenance pass
- Before the human leans on the vault for something expensive
## What this catches, and what it does not
View the complete source on GitHubproject-start
When your agent uses it
Sets up a new project folder and runs the interview that fills its brief. Use when the human starts a new project, or when work that has been living in chat needs a home with a brief, rules and a log.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
1,018 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to invoke
- How it works
- Self-check
- Hard constraints
Files
SKILL.mdcore4,210 bytesSKILL.mdcore4,210 bytes
Read SKILL.md
# Project Start
Copying three files takes a second. The value of this skill is the conversation that fills them, because a brief nobody pushed back on says "for all users" and "success is more engagement" and helps no one.
Run the interview in the language the human is using.
## How to invoke
- "New project", "let's start a project on X"
- Work that has been living in the chat needs a folder
- `/project-start`
## How it works
View the complete source on GitHubproject-update
When your agent uses it
Records what happened in a project as an artefact, a log entry and a refreshed index row. Use when the human reports progress, a decision, a prototype or a result, or when a project's scope has moved.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
953 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to invoke
- How it works
- Self-check
- Hard constraints
Files
SKILL.mdcore3,977 bytes
Read SKILL.md
# Project Update
Turn "here is what happened this week" into project state someone can pick up cold in three months.
Write every file in the language the human is using.
## How to invoke
- "I have an update", "here is what happened", "update the project"
- The human reports a decision, a prototype, a test result or a piece of research
- The scope of a project has moved
## How it works
View the complete source on GitHubquery
When your agent uses it
Answers from the compiled wiki in 4-Knowledge/, with citations and a saved output file. Use when the human asks something this vault should already know, wants a briefing or comparison built from ingested sources, or asks what the vault is missing on a topic.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
897 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to invoke
- How it works
- Self-check
- Hard constraints
Files
SKILL.mdcore3,634 bytes
Read SKILL.md
# Query
Answer from the wiki, not from memory, and keep the answer so the next question starts further along.
Write the answer and every file you produce in the language the human is using.
## How to invoke
- Any question the vault plausibly covers
- "What do we know about X?"
- "Compare X and Y from what I have"
- "Write me a briefing on X"
- `/query`
View the complete source on GitHubsecond-brain-setup
When your agent uses it
Use when creating or refreshing a product builder's personal profile in 8-System/about.md - supports both assessment-based (Gallup, DISC, MBTI) and interview-based onboarding
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,020 tokensWhen the skill is activated
Reference documents
3,184 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to use
- How it works
- STOP - red flags
- References
Files
SKILL.mdcore4,023 bytesevals/README.mddoc771 bytesevals/fixture-assessment-gallup.mddoc2,921 bytesevals/fixture-interview-solo.mddoc2,891 bytesevals/fixture-rerun-scope-change.mddoc3,545 bytesreferences/questions.mddoc2,449 bytes
Read SKILL.md
# Second Brain Setup
## Purpose
Runs a conversation with the product builder and writes the result to `8-System/about.md`. That file tells the agent who the human is, how they want to be treated and where they need to be pushed. It works as a pair with `8-System/brain.md`, which holds the universal operating rules.
## When to use
- Setting up a new vault for the first time
- Refreshing the profile after a role change, a new project or a shift in priorities
- When the AI feels "out of calibration"
## How it works
View the complete source on GitHubyoutube
When your agent uses it
Captures a YouTube video as a source note and a wiki page. Use when the human drops a video URL, wants a talk or tutorial turned into notes, or asks what a specific video said about a topic.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,015 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Requirements
- How to invoke
- How it works
- Self-check
- Cleanup
Files
SKILL.mdcore3,938 bytesSKILL.mdcore3,938 bytesSKILL.mdcore3,938 bytesSKILL.mdcore3,938 bytesSKILL.mdcore3,938 bytesSKILL.mdcore3,938 bytesSKILL.mdcore3,938 bytes
Read SKILL.md
# YouTube Video Summary
Turns a YouTube video into a structured note, then compiles that note into a wiki page in Knowledge.
## When to use
- You want a video turned into a clean note with metadata and key ideas
- For tutorials the output is a step-by-step guide, not a summary
## Requirements
This skill pulls metadata and subtitles with `yt-dlp`. Install it once:
```bashView the complete source on GitHubSkills included
- feynman
- ingest
- lint
- project-start
- project-update
- query
- second-brain-setup
- youtube
Repository facts
- License
- MIT
- Created
- Apr 24, 2026
- Last pushed
- Oct 26, 2026
- Forks
- 83
- Open issues
- 1
- Project activity
- Active
Rank over the last 12 weeks
Now #879 · best #854 · up 25 in 30 days
- #973 on Oct 19
- #976 on Oct 20
- #989 on Oct 21
- #946 on Oct 22
- #957 on Oct 23
- #879 since Oct 24
54 earlier periods
- #917 on Aug 11
- #915 on Aug 12
- #920 on Aug 13
- #897 on Aug 14
- #866 on Aug 15
- #889 on Aug 16
- #897 on Aug 17
- #915 on Aug 18
- #909 on Aug 19
- #854 on Aug 22
- #909 on Aug 23
- #929 on Aug 25
- #911 on Aug 26
- #919 on Aug 27
- #953 on Aug 28
- #925 on Aug 31
- #962 on Sep 1
- #928 on Sep 2
- #933 on Sep 3
- #895 on Sep 4
- #871 on Sep 5
- #910 on Sep 6
- #933 on Sep 7
- #945 on Sep 8
- #932 on Sep 9
- #930 on Sep 10
- #898 on Sep 11
- #932 on Sep 14
- #932 on Sep 16
- #929 on Sep 17
- #915 on Sep 18
- #909 on Sep 20
- #928 on Sep 21
- #947 on Sep 22
- #904 on Sep 24
- #854 on Sep 25
- #877 on Sep 26
- #898 on Sep 27
- #970 on Sep 29
- #891 on Oct 2
- #906 on Oct 4
- #913 on Oct 6
- #953 on Oct 7
- #990 on Oct 8
- #954 on Oct 9
- #928 on Oct 10
- #938 on Oct 11
- #963 on Oct 12
- #966 on Oct 13
- #985 on Oct 14
- #969 on Oct 15
- #974 on Oct 16
- #953 on Oct 17
- #935 on Oct 18
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 31 notes
7-Skills/feynman/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/feynman/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/feynman/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/feynman/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/ingest/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed7-Skills/lint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 1 dangerous shell commandin 1 file: youtube/SKILL.md:136
- 1 network referencein 1 file: youtube/SKILL.md:28
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 2 signals by file
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 2 facts
- Network access in prose of the SKILL.mdyoutube/SKILL.md:28Low confidence
- Dangerous shell operation in code of the SKILL.mdyoutube/SKILL.md:136High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path .claude/skills/feynman | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md 7-Skills/feynman/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md 7-Skills/feynman/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md 7-Skills/feynman/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md 7-Skills/feynman/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.