one-line
Skill2 starsChanged 2 months agoMITView on GitHub
Explain it in exactly one sentence — nothing else.
In this repository10 other files it gives its agents.
- 3wSkill
- catchupSkill
- clear-viewSkill
- decisionSkill
- first-principleSkill
- impactSkill
- scopeSkill
- tldrSkill
- tradeoffSkill
- visSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Max 1 sentence. Hard limit: No second sentence, no bullets, no heading, no code block, no "let me know if you want more".
- Distinctive: line 24
No section headers and no closing verdict line — the sentence *is* the verdict.
- Distinctive: line 26
No analogies unless the analogy *is* the shortest true explanation.
- Distinctive: line 27
No hedging ("generally", "basically", "essentially", "kind of").
- Distinctive: line 57
Don't write "JWT is a JSON Web Token.
- Distinctive: line 60
Don't write "A signed token for auth — see the docs for details." Pointing elsewhere is not an explanation.
- Distinctive: line 63
If no request was supplied, ask: "One line on what?"
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
One Line
Goal: user reads one sentence and has the right mental model.
Rules
- Respond in the same language the user wrote in. If they write in Chinese, reply in Chinese. Technical terms (JWT, Redis, API…) stay in English.
- Max 1 sentence. Hard limit. No second sentence, no bullets, no heading, no code block, no "let me know if you want more".
- The sentence is bold — wrap the whole thing in
**, punctuation included. Nothing sits outside the bold. - Under 25 words. If it doesn't fit, you haven't found the core yet — cut the qualifiers, not the meaning.
- No section headers and no closing verdict line — the sentence is the verdict.
- Say what it does or is for, not what category it belongs to. "A tamper-proof token that proves who you are" beats "an open standard for representing claims".
- No analogies unless the analogy is the shortest true explanation.
- No hedging ("generally", "basically", "essentially", "kind of"). Commit.
- No emoji.
Output format
**[One sentence.]**That's the whole output.
Examples
/one-line JWT
**A signed token the client carries so the server can verify who they are without storing a session.**/one-line 為什麼要用 Redis
**把讀取頻繁但變動不多的資料放在記憶體裡,避免每次都打 database。**/one-line this function
**Retries the payment call with exponential backoff, giving up after three failures.**Anti-examples
Don't write "JWT is a JSON Web Token. It's used for auth." — that's two sentences and the first one says nothing.
Don't write "A signed token for auth — see the docs for details." Pointing elsewhere is not an explanation.
If no request was supplied, ask: "One line on what?"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

