agentleFS
sreejithramansreejithraman/SreeStack/skills/why/SKILL.md

why

Skill1 starsChanged 16 days agoMITView on GitHub

Investigate code history to explain a design decision's rationale, when and why a regression was introduced, or whether an old constraint still applies. Use diagnosing-bugs for an active defect.

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

2 rules. 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use how for current execution and data flow.

    line 10
  2. Very specific:

    If the requested outcome is to diagnose or repair a current failure, use diagnosing-bugs for that work.

    line 12

“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

Why

Answer historical intent from records, not from a plausible reading of today's code. Keep observed behavior and motivation separate.

Use how for current execution and data flow.

If the requested outcome is to diagnose or repair a current failure, use diagnosing-bugs for that work. Use this skill for a separate question about the failure's history.

  1. Anchor the question. Identify the exact code, symbol, behavior, or decision in question. Read enough current code to understand what it does, then inspect its blame and history, following renames where relevant.
  2. Follow the decision trail. Read the introducing or changing commits and substantive PR discussion. Follow linked issues, design documents, incidents, or other available records when they could explain the decision. Search proportionally to the question; do not fan out across every connector by default. Record which promising sources were searched, empty, or unavailable. For a question about when a regression began, distinguish the commit that changed code from the first revision where the symptom occurred. Compare passing and failing revisions with an existing test, replay, bisect, or dated incident evidence when feasible; run revision checks in an isolated checkout. Without that evidence, call a commit a candidate and leave symptom onset unknown.
  3. Grade each explanation. Distinguish an explicit contemporary statement of rationale, several independent records that support an explanation, an inference from context, a plausible guess, and an unknown. Code shape alone proves behavior, not author intent. Surface conflicting accounts and whether a documented constraint still holds; do not select the tidier story without evidence.
  4. Answer and apply. Cite the record beside each historical claim. State what the code does now, why the record says it was shaped that way, what remains uncertain, and any current constraint a proposed change should preserve or revisit. If no rationale survives the search, say so and name the search coverage.

This is a read-only investigation unless the user also asks for a code or documentation change. Keep private records within the audience authorized to see them.

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.