answer-as-type
Skill13 starsChanged 51 days agoMITView on GitHub
Answer as a return value, not as prose.
In this repository5 other files it gives its agents.
- add-didactic-commentsSkill
- back-your-claimsSkill
- fill-the-gapsSkill
- just-do-itSkill
- no-bs-answerSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 5 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
No preamble, no restatement of the question, no reasoning, no caveat, no unit, no trailing sentence, no word about the check.
- Distinctive: line 17
IF the answer needs work first (read files, run a command, count something), THEN do the work with tools, and return only the value.
- Very specific: line 18
IF $type is one of the types in the table below, THEN type is $type, and the rest of the request is the question.
- Very specific: line 19
IF $type is not one of those types, THEN type is not set, and the whole request is the question.
- Very specific: line 20
IF type is set, THEN it is the return annotation of the function, and it is final.
- Very specific: line 21
IF type is not set, THEN infer it from the question, using the table below.
- Very specific: line 22
IF the value cannot be computed, THEN return None and nothing else.
- Distinctive: line 40
NEVER wrap the value in a code fence unless the value is itself code.
- Distinctive: line 44
ALWAYS run the check, even when the value looks obvious.
- Very specific: line 46
Run check-value.py from this skill's folder.
- Distinctive: line 95
IF the user then asks why, or how, THEN explain in one or two sentences.
≈ “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
Func
The user called a function. Return its value. Nothing else.
No preamble, no restatement of the question, no reasoning, no caveat, no unit, no trailing sentence, no word about the check.
The first word of the request is $type.
- IF the answer needs work first (read files, run a command, count something), THEN do the work with tools, and return only the value.
- IF
$typeis one of the types in the table below, THENtypeis$type, and the rest of the request is the question. The word is the type, not a verb:listmeans a numbered list,seta bullet list. - IF
$typeis not one of those types, THENtypeis not set, and the whole request is the question. - IF
typeis set, THEN it is the return annotation of the function, and it is final. NEVER swap it for the type you would infer, even when the question reads like another type. Convert the answer into it, using the table below. - IF
typeis not set, THEN infer it from the question, using the table below. - IF the value cannot be computed, THEN return
Noneand nothing else.
Return types
| Type | Format | Infer it when the question asks for | Convert into it, when the question asks for something else |
bool | true or false | yes/no, is/are, does/do, can/should | whether any such thing exists |
int | bare digits: 5 | how many, count, index, line number | how many things answer the question |
float | bare decimal: 0.42 | ratio, percentage, average, duration | the number that answers it, as a decimal |
str | the bare string, no quotes | a name, a path, a command, a single value | the answer on one line |
list | numbered markdown list | steps, an ordered procedure, a ranking | the items, numbered, even when their order carries no meaning |
set | bullet markdown list | items where order carries no meaning | the items, bulleted, even when they have an order |
boolistrue/false, neverYes/No.intandfloatcarry no unit, no thousands separator, no words.5, not5 sub-agents.floatkeeps the precision the question implies. Do not pad zeros.listandsetitems are values too: each one is short and bare, with no explanation attached.- Order matters in a
listand never in aset. IFtypeis not set and you are unsure which, THEN return aset. - NEVER wrap the value in a code fence unless the value is itself code.
The check
ALWAYS run the check, even when the value looks obvious. Your last tool call before you reply is the check, on the exact reply you are about to send.
Run check-value.py from this skill's folder. Give it the value on stdin, and the whole
request of the user, type word included, as --question. The script reads the type from the
request: the named type when there is one, the inferred type otherwise.
printf '%s' "$VALUE" | python3 <skill-folder>/check-value.py --question "$ARGUMENTS"Exit 0 means the format holds. Exit 1 prints one finding per line. IF the script exits 1, THEN rewrite the value and run it again. Deliver only a value that exits 0, and say nothing about the check.
The script reads the format, not the truth. It cannot tell you that the value is correct.
Examples
Q: did you edit any file outside src/?
falseQ: /func int how many sub-agents did you spawn during the session?
5Q: which kind of return values does this skill implement?
- bool
- int
- float
- str
- list
- setQ: how do I release a new version?
1. Bump the version in `pyproject.toml`.
2. Run `uv build`.
3. Tag the commit.
4. Push the tag.The follow-up
IF the user then asks why, or how, THEN explain in one or two sentences. Give the fact that produced the value. Do not repeat the value.
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.

