agentleFS
therealtinhtutetherealtinhtute/mono-harness/skills/reason/how/SKILL.md

how

Skill5 starsChanged 3 days agoMITView on GitHub

Explain how a subsystem works or where code belongs: trace the flow, map the files, cite file:line. Use for \"how does X work\", walkthroughs before a change, layering questions. Read-only.

98 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-pstack, ketchup-video 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.
  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 25 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 13 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 28 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 14 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 19 projects that use this

  • drafaelSkill

    in-your-own-words

    Restate the user's goals and the problem they are trying to solve to check understanding. Manual invocation only; use when the user explicitly invokes in-your-own-words or requests this understanding check. Do not solve the task or rewrite the assistant's last answer.

    Also in 26 projects that use this

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 97 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:

    Explain: Write the sections below, dropping any that do not apply.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 97 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

How: Explain a Subsystem

Outcome Contract

  • Outcome: an explanation a senior engineer new to the area can start working from: what it is, how a call flows through it, where things live, what trips people up.
  • Done when: every section that applies is written, each claim about the code cites file:line, and what was not traced is listed rather than guessed.
  • Writes: nothing. No file, plan or commit.

Process

  1. Size it. An ambiguous scope → state your reading and continue; the user can redirect. One module, a small utility or a narrow question → simple: trace it yourself and go to step 4. A subsystem across several files or services, a cross-cutting feature or a full overview → complex. When in doubt, simple.
  2. Explore (complex only). Split the question into 2–4 angles, each a distinct slice. Spawn one scout per angle in one message, each briefed from references/explorer-brief.md, per work work-swarm.md.
  3. Reconcile (complex only). Merge overlapping findings. Settle a contradiction by reading the code yourself, never by majority. A slice a scout could not trace: read it yourself, or list it under Open Questions.
  4. Explain. Write the sections below, dropping any that do not apply. A placement question ("where should this live", "which layer owns this") is answered from the boundaries you found: name the owner and cite the code that shows it.

Output

  • Overview — 1–2 paragraphs: what it is, what it does, why it exists. A reader can stop here and decide whether to go on.
  • Key Concepts — the types, services or abstractions the rest depends on, one line each.
  • How It Works — the longest section: what triggers it, each step, where the data goes, the decision points. Prose with function names and file:line, not code dumps. Add a diagram (mermaid, or ASCII for a simple relation) only when components call each other or data changes shape across stages.
  • Where Things Live — the few files to open first.
  • Gotchas — surprising behavior, history, pitfalls.
  • Open Questions — what you could not trace.

Name things concretely: "install calls registry::update", not "the service delegates to the registry". Explain why a part is complex; do not pad a simple one.

Defer to: hunt (a symptom to diagnose), think (a decision, or why it was built this way), librarian (code in another GitHub repo), learn (a domain rather than this codebase).

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.