agentleFS
ArcticFox2029ArcticFox2029/chamnan/skills/why/SKILL.md

why

Skill10 starsChanged 7 days agoMITView on GitHub

Work out whether a failure is your machine or your code before debugging either, using the environment this repository has declared and the dependency map. Use when a test, build or command fails and the cause is not obvious from the error.

112 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 106 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Distinctive:

    If you just edited the file the failure names, this adds nothing — you have the diff and the error, which is more than either command above …

    line 47

“Common” is measured: kept by at least 6 in 10 of the 106 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Your machine, or your code — decide that first

The expensive mistake is not picking the wrong fix. It is spending two hours in the code when the problem was a version, or two hours on the environment when the problem was a line somebody changed. One decision comes before any debugging, and this repository holds evidence for both sides of it.

1 · The machine

chamnan-env

What this repository has declared about the environments it runs in — the constraints nobody writes down and everybody re-learns. A shell alias that hangs without a terminal, a binary that is not on this platform, a Python whose certificate bundle is broken. If the failure matches one of these, stop: there is nothing wrong with the code.

An error that mentions a command not found, a version mismatch, a certificate, a path separator or a permission is a machine failure until something rules that out.

2 · The code

chamnan-impact <the file the failure points at>

Who imports it, which tests cover it, and what this repository has recorded about it. If the failing test is in that list, the change and the failure are connected. If it is not, the error's file and the failure's cause are probably different files.

3 · What this cannot tell you, and do not pretend otherwise

chamnan does not know when the test last passed. A Bash tool response carries no exit code — only stdout, stderr and whether it was interrupted — and the stderr field was measured to be a constant rather than a signal, so there is no record of outcomes to consult. git log on the files chamnan-impact names is the substitute, and it is a weaker one: it shows what changed, not what broke.

Say that plainly rather than inventing a history.

When the agent already knows

If you just edited the file the failure names, this adds nothing — you have the diff and the error, which is more than either command above can give you. Use it when the failure is one you did not cause: a test that was already red when the session opened, a failure in code you did not touch, or one that appeared after pulling somebody else's work.

What not to say

Do not report both halves. The output of this skill is a decision — machine or code — and then the evidence for that one. Listing everything from both commands is the raw material, not the answer.

Do not treat a quiet chamnan-env as proof the machine is fine. It lists what somebody declared, and an undeclared constraint is the most likely kind to be biting you. A silent environment file means nobody has written this down yet, which is worth saying — and worth fixing with chamnan-env set once you find it.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.