agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/personalize-ai-column/SKILL.md

personalize-ai-column

Skill2 starsChanged 2 months agoMITView on GitHub

Configure and preview the kit's generated first-touch callable using cited row evidence, a frozen experiment and an explicit credit ceiling.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the runtime contract, composition, functions/generate_first_touch/function.json and its prompt.

    line 8
  2. Very specific:

    Use the installed generate_first_touch callable as the default implementation.

    line 10
  3. Very specific:

    Use npm run example -- --function generate_first_touch only for synthetic fixture rows.

    line 12
  4. Distinctive:

    Check missing facts, unresolved merge tags, invented observations, stale titles and whether the output respects the assigned variant.

    line 14

≈ “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

Generate grounded copy per row

Read the runtime contract, composition, functions/generate_first_touch/function.json and its prompt.

Use the installed generate_first_touch callable as the default implementation. Map company_evidence, person_evidence, scoring_reasons, offer and the assigned copy/test metadata from the actual working table. A prompt filename does not automatically load external sources; evidence must be in the mapped inputs.

Use npm run example -- --function generate_first_touch only for synthetic fixture rows. Use npm run preview -- --function generate_first_touch to inspect rendering and estimated cost. For a real caller table, follow the exact binding example and preview that table's chosen row.

Check missing facts, unresolved merge tags, invented observations, stale titles and whether the output respects the assigned variant. Thin evidence should create an explicit hold or a clearly qualified draft; do not invent a personal detail.

A dry run renders and estimates; it does not demonstrate model output quality. Run a live sample only within the user's authorized row set and credit cap. Report actual run status and cost separately from estimates. Review the sample before scaling, then hand off to prepare_sequence. No fixed provider price or BYOK saving is assumed.

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.