briefly
Skill82 starsChanged 42 days agoMITView on GitHub
Make this reply brief — the answer only, sized to the question. Use when the user writes /briefly anywhere in a prompt, or explicitly asks to keep it brief or for a TL;DR.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-reviewSkill
- commit-batchingSkill
- commit-batchSkill
- create-alertSkill
- disclose-projectSkill
- discloseSkill
- evolve-claude-mdSkill
- figure-reviewSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- lit-reviewSkill
- overbakedSkill
- pathfinderSkill
- pickupSkill
- recover-sessionsSkill
- repo-initSkill
- retroSkill
- reviewer-2Skill
- slack-messageSkill
- spot-aiSkill
- tab-setupSkill
- unstaleSkill
- worklogSkill
- write-new-skillSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 37
Length is capped, rigor isn't: verify what the answer depends on.
- Distinctive: line 39
If something material was cut, end with one line naming it (e.g.
≈ “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
Answer briefly, for this reply only.
The question is everything the user wrote, minus /briefly itself — don't trust command arguments to hold it (stacked with another skill, /briefly can receive that skill's arguments). An explicit length ("1 line", "50 words", "3 bullets") overrides the defaults below.
With another skill: wherever /briefly appears — before, after, or inside another command's arguments — it caps only your reply's prose. Run the other skill's steps in full, and never shorten content that skill writes (log entries, files, commits); a literal /briefly in such content stays verbatim.
Default budget (pick by question type)
| Question | Budget |
| Fact, yes/no, lookup | 1–2 sentences. Yes/no leads with the word. |
| "How do I…" / explain | ≤ 5 bullets or ~80 words |
| Choice / design / compare | Recommendation + ≤ 3 reasons. No option survey. |
| Code | Minimal snippet, ≤ 1 line of prose around it |
| Review / debug finding | Top 1–3 issues, most severe first |
The budget is a ceiling, not a target. When unsure, take the smaller one.
Cut
- Preamble, restating the question, closing recaps, offers of further help.
- Headers and sections — plain sentences or a short list instead (this overrides house-style section headers).
- Secondary caveats; background the user already has.
- Exploration beyond what the answer needs — fewer tool calls, not just fewer words.
Keep
- At most one caveat — the one that would change the answer or its interpretation (a baseline, a sign convention, a NaN/masking trap). One clause, not a paragraph. A second caveat goes in the closing "Skipped:" line, not the body.
- Uncertainty when present: "unsure; likely X".
- Length is capped, rigor isn't: verify what the answer depends on.
If something material was cut, end with one line naming it (e.g. "Skipped: the 2-D case.").
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.