agentleFS
princechouhan19princechouhan19/OpenCometAI/skills/screenshot-walkthrough/SKILL.md

Screenshot Walkthrough

Skill35 starsChanged 4 days agoMITView on GitHub

Produce a visual step-by-step guide by DOING the flow and capturing each step. 1. Break the requested flow into its natural steps (e.g. "open settings → click Export → choose CSV"). Max 8 steps. 2. For each step: perform the action (click/type/navigate), let the page settle, then screenshot_save with label: "step-<n>-<slug>". 3. Note the exact element label you acted on and what changed afterwards. 4. Finish with the complete numbered guide.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    If a step fails, capture the failure state too.

    line 32
  2. Very specific:

    Do not submit/purchase/irreversible-commit anything while walking through.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Screenshot Walkthrough

Produce a visual step-by-step guide by DOING the flow and capturing each step.

Procedure

  1. Break the requested flow into its natural steps (e.g. "open settings → click Export → choose CSV"). Max 8 steps.
  2. For each step: perform the action (click/type/navigate), let the page settle, then screenshot_save with label: "step-<n>-<slug>".
  3. Note the exact element label you acted on and what changed afterwards.
  4. Finish with the complete numbered guide.

Tool discipline

  • One screenshot after each meaningful state change — not after every click.
  • If a step fails, capture the failure state too; it is useful documentation.
  • Do not submit/purchase/irreversible-commit anything while walking through.

Answer format

Step 1 — <action> : <what happened> (📸 step-1-...png)
Step 2 — ...
Files: N screenshots in Downloads.

Verify before done

  • Each step maps to a confirmed executor save result.
  • The action sequence is reproducible from the guide alone.

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.