agentleFS
Sign inStart free
nb-99nb-99/skillektion/skills/how/SKILL.md

how

Skill1 starsChanged 3 months agoMITView on GitHub

Explain how code, a feature flow, or a subsystem works and where its responsibilities belong. Use for code walkthroughs, architecture onboarding, runtime traces, ownership questions, and architecture critique.

90 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

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 89 edited versions we read keep these.

  • 3

    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:

    Use independent workers when available.

    line 21
  2. Distinctive:

    When the user asks for architectural problems or improvements, explain the system first.

    line 41
  3. Distinctive:

    Verify proposed issues against the code and classify them as:

    line 48

“Common” is measured: kept by at least 6 in 10 of the 89 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

Build a working mental model, not an annotated source listing.

Scope

Interpret the target from the request and current context. State a best-guess scope when ambiguous so the user can redirect without blocking exploration.

  • For one function or module, trace and explain it directly.
  • For a cross-cutting subsystem, divide exploration into two to four distinct read-only slices, such as entry points and flow, state and data model, integration boundaries, and configuration or operations.

Use independent workers when available; otherwise inspect the slices sequentially. Each slice must report components, execution flow, files read, boundaries, surprises, and open questions. Read actual code and follow calls, types, and data from trigger to effect.

Explain

Synthesize the evidence into only the sections the question needs:

  • Overview: what it is, what it does, and why the reader cares.
  • Key concepts: the types, services, and abstractions needed for the model.
  • How it works: trigger, ordered flow, data movement, and decision points.
  • Where it lives: a small map of relevant files and ownership boundaries.
  • Gotchas: surprising behavior, sharp edges, and unresolved questions.

Cite specific files and symbols. Use a diagram only when it reduces explanation cost. Mark inferred behavior and evidence gaps.

Critique

When the user asks for architectural problems or improvements, explain the system first. Then use independent read-only critique passes when available. Give each pass the same explanation, paths, and question. Ask each pass to find incorrect boundaries, hidden coupling, confused ownership, fragile data flow, and unnecessary complexity. Require a reachable impact, code evidence, and the smallest useful improvement for every proposed issue.

Verify proposed issues against the code and classify them as:

  • Act on: concrete problems worth fixing now.
  • Consider: real concern with uncertain cost or priority.
  • Noted: valid but low-priority observation.
  • Dismissed: incorrect, missing context, or preference without impact.

Present the standalone explanation before the critique. The task is complete when the requested flow can be traced without hand-waving and every critique finding is verified or dismissed with a reason.

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.

Check your setup, free