agentleFS
princechouhan19princechouhan19/OpenCometAI/skills/fill-form/SKILL.md

Fill Form

Skill35 starsChanged 4 days agoMITView on GitHub

Safe form completion. Fill everything you can, submit nothing without permission. 1. Inventory every field from AVAILABLE INPUTS and INTERACTIVE ELEMENTS: inputs, textareas, selects, checkboxes, radios. Note label/placeholder/name. 2. Map each field to a value from (in order): explicit task text → USER PROFILE → sensible neutral placeholder. NEVER invent legal, payment, or identity data that was not provided. 3. type into each field. For selects use click then pick the option element. For checkbox consent: tick only what is…

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    If a validation error appears, fix THAT field using the error text — do not re-fill the whole form.

    line 36
  2. Distinctive:

    Never touch fields the task did not mention if they are optional and unclear.

    line 38

≈ “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

Fill Form

Safe form completion. Fill everything you can, submit nothing without permission.

Procedure

  1. Inventory every field from AVAILABLE INPUTS and INTERACTIVE ELEMENTS: inputs, textareas, selects, checkboxes, radios. Note label/placeholder/name.
  2. Map each field to a value from (in order): explicit task text → USER PROFILE → sensible neutral placeholder. NEVER invent legal, payment, or identity data that was not provided.
  3. type into each field. For selects use click then pick the option element. For checkbox consent: tick only what is required to proceed.
  4. Fill EVERYTHING first, then stop and report. submit ONLY if the task explicitly says to submit/send/apply.

Tool discipline

  • One field per type action; verify the value stuck from the page diff.
  • If a validation error appears, fix THAT field using the error text — do not re-fill the whole form.
  • Never touch fields the task did not mention if they are optional and unclear.

Answer format

List: field → value filled (mask sensitive values like passwords as •••). State clearly whether the form was submitted or left ready for review.

Verify before done

  • Required fields show no validation errors in the latest page state.
  • Submission happened only with explicit user instruction.

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.