Not in the top 1,000 by GitHub stars
isas1/skills
Skills for explaining and summarising AI output: eli5-succinct, simple-summary, summary
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
skills/eli5-succinct/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
7554c7c816f1 → 7554c7c816f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 7554c7c816f1
No earlier version was observed for comparison.
skills/summary/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
7554c7c816f1 → 7554c7c816f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 7554c7c816f1
No earlier version was observed for comparison.
Heat
0.4- 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
30-day change not yet available: not enough history.
Individual skills in this repository
- eli5-succinct
skills/eli5-succinct - summary
skills/summary
How it works
eli5-succinct
When your agent uses it
Explain anything in plain language, briefly, in chat, with no file written. Code, a concept, an error message, a config, a decision, a diff, a dependency, why something broke. Use when the user says "eli5 succinct", "eli5", "eli15", "eli18", "elif18", "explain like I'm five", "explain this simply", "what does this actually do", "in plain english", "TL;DR", "STE", "technical english", "no dumbing down", "yes or no", or otherwise asks to understand something rather than to receive a document. Succinct by default, under 150 words. Chat only, this skill never writes a file. If the user wants something to look at, keep or send, that is a page, so use `summary`.
What it loads into context
Frontmatter
181 tokensAlways available to the agent
SKILL.md
1,104 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
- Routing
- How to explain
- The number is an audience dial
- Register: technical without dumbing down
- Yes/No questions
- Shape
- Write in the reader's own language
- Output
Files
SKILL.mdcore4,609 bytes
Read SKILL.md
# eli5 succinct
Someone asked what a thing is or how it works. Answer them, in chat, in words they already know, and keep it short.
## Routing
The deciding question is **what they want to end up holding**, not what words they used.
| They want | Skill |
|---|---|
| To understand something, briefly | this one |
| A page to look at, keep or send | `summary` |
| A page with a mode, a look or an audience attached | `summary` |
summary
When your agent uses it
A single-page HTML summary of a conversation, branch, work tree or set of user instructions. Visual and digestible, charts and diagrams over long explanations. Use whenever the user asks for a summary, recap, wrap-up or handover page, plain or with something attached. Bare asks like "summary", "simple summary", "quick summary", "just summarise this" build the plain page. Attached asks like "summary, make it ADHD friendly", "recap but make it look good", "summarise this for a client", "wrap up and animate it", "handover page" build the same page in the matching mode or audience variant (accessible for ADHD, autistic or dyslexia; artistic; animated). If they want an explanation in chat and no file at all, use `eli5-succinct`.
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
2,775 tokensWhen the skill is activated
Reference documents
2,229 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Routing
- Plain vs attached
- Target
- Step 1: gather
- Step 2: build the page
- Write in the reader's own language
- Modes
- Variants
- Step 3: write the file
- Step 4: reply
Files
SKILL.mdcore11,721 bytesSKILL.mdcore11,721 bytesmodes/accessible.mddoc2,996 bytesmodes/animated.mddoc2,469 bytesmodes/artistic.mddoc4,015 bytes
Read SKILL.md
# summary
The page skill. One self-contained HTML page, built to one house style. A bare ask builds the plain page; a mode, look or audience attached builds the same page dressed for it.
## Routing
This skill owns every summary that ends in a page. The only thing it does not own is an explanation the user wants in chat with no file.
| They say | Skill |
|---|---|
| "summary", "simple summary", "quick summary", bare "summarise this" | this one, plain (see **Plain vs attached**) |
| "summary" with a mode, look or audience attached | this one, that mode |
| "eli5 succinct on this function" (explain, no file) | `eli5-succinct` |
Skills included
- eli5-succinct
- summary
Repository facts
- License
- MIT
- Created
- Sep 19, 2026
- Last pushed
- Sep 26, 2026
- Forks
- 17
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated 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 1 note
skills/summary/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 1 network referencein 1 file: summary/modes/artistic.md:75
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show the signal with its line
skills/summary/modes/artistic.md
- Network accessline 75
If you can reach it, [Forever AI Components](https://github.com/isas1/forever-ai-components) is a catalogue of zero-dependency single-file components. Read the index, open two or three that fit, take the craft and rewrite it inline. Never a
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.
Signal confidence: 1 fact
- Network access in prose of documentationsummary/modes/artistic.md:75Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/eli5-succinct/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/eli5-succinct/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/eli5-succinct/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/eli5-succinct/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/eli5-succinct/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/eli5-succinct/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.
