agentleFS
omnipresence-osomnipresence-os/claude-skills/fill-project-gap/SKILL.md

fill-project-gap

Skill0 starsChanged 6 months agoLicence not identifiedView on GitHub

Fills in a TBD placeholder file in the active project (style-guide.md, glossary.md, banned-phrases.md, editor-rules.md, project-config.md) by walking the user through a short, slot-specific interview, then writing the result over the placeholder content. Trigger when the user says any of "fill in my style guide", "fill in my glossary", "fill in my banned phrases", "fill in my editor rules", "set up my brand voice", "fix my brand voice", "update my style guide", "my voice is empty", "complete my project setup", "finish project setup". ALSO trigger as an INTERRUPT when a worker or agent detects a TBD placeholder mid-task and needs to pause + offer to fill it before continuing — the user complaint "that's not my brand voice" should fire detection and route here. Interrupts pause the calling task with a 2-option AskUserQuestion ("Fill now or skip?"), fill the gap if yes (~2-3 min interview), then resume the original task at the exact point it paused. Idempotent — re-running on an already-filled file refreshes it after asking the user to confirm overwrite. Pairs with new-project (scaffolds the placeholders) and load-worker (detects + flags them at session start).

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. About 0 are common, 11 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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.