agentleFS
mauriciovieiramauriciovieira/groundwork/skills/how/SKILL.md

how

Skill0 starsChanged 4 months agoMITView on GitHub

Use when someone asks how something works - "how does X happen", "walk me through this flow", "where does this actually run". Explains behaviour from the feature map first, then traces the mechanism in the code. Read-only.

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

6 rules. 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 89 edited versions we read keep these.

  • 0

    Distinctive

    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
  1. Very specific:

    If this repository has a feature map, read the relevant entry under <docs_dir>/verify/features/ first.

    line 13
  2. Very specific:

    Read glossary.md too when the area has domain vocabulary, so your explanation uses the project's words rather than inventing parallel ones.

    line 19
  3. Very specific:

    If there is no feature map, say so once and trace from the code.

    line 22
  4. Very specific:

    Follow the actual path: entry point, what it calls, where state is read and written, where it ends.

    line 27
  5. Very specific:

    When the area is large, this is a good use of independent workers, one per path, so the tracing is not done one file at a time in a single …

    line 31
  6. Very specific:

    If the mechanism contradicts what the feature map says, that is a finding worth more than the explanation: report it, and offer verify …

    line 46

“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

groundwork:how

Explain how something actually works, from the outside in.

1. Start from behaviour, not code

If this repository has a feature map, read the relevant entry under <docs_dir>/verify/features/ first. It says what the feature does, how a person reaches it, and what proves it worked - all in behavioural terms, which is where an explanation should start. Reading it costs a page; reconstructing the same picture from source costs far more and is easier to get wrong.

Read glossary.md too when the area has domain vocabulary, so your explanation uses the project's words rather than inventing parallel ones.

If there is no feature map, say so once and trace from the code. verify --init is what creates one.

2. Trace the mechanism

Follow the actual path: entry point, what it calls, where state is read and written, where it ends. Prefer reading the code over guessing from names - a function called validate may not validate.

When the area is large, this is a good use of independent workers, one per path, so the tracing is not done one file at a time in a single context. See ../_runtime/RUNTIMES.md.

Note where behaviour is decided by configuration, an environment variable, or a feature flag rather than by the code path - that is the most common reason a correct-looking trace does not match what actually happens in production.

3. Explain

Lead with the shape - the two or three steps someone needs to hold in their head - then go into detail. Name concrete files and functions so the reader can go and look.

Say what you did not check. A trace that skipped an error path or a background job is still useful, but only if its edges are stated. Silence about a gap reads as coverage.

If the mechanism contradicts what the feature map says, that is a finding worth more than the explanation: report it, and offer verify --sync to correct the map.

For the reasoning behind a design rather than its mechanics, use why. The two compose: the mechanism plus the rationale is a complete explanation, and there is no separate skill for that combination because there does not need to be.

This skill writes nothing.

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.