agentleFS
n-n-coden-n-code/n-n-code-skills/.agents/skills/project-core-dev/SKILL.md

project-core-dev

Skill4 starsChanged 11 days agoMITView on GitHub

Project overlay for discovering and reporting repository-specific completion checks for routine repo-owned changes. Use when the validation path is unclear; prefer specialized project overlays for config, platform, release, or vendor concerns.

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:

    Use it with matching implementation guidance only when repository-specific checks or gaps remain unclear.

    line 9
  2. Distinctive:

    Read the applicable repository instructions, README, CI configuration, contributor docs, and presets.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Project Core Dev

This is a thin project overlay, not a standalone implementation workflow. Use it with matching implementation guidance only when repository-specific checks or gaps remain unclear. Omit it when another selected skill plus repo context already supplies exact commands and reporting obligations.

When to use

The task is a routine repo-owned change whose completion path is not yet concrete.

Not for

Use project-config-and-tests, project-platform-diagnose, project-release-maintainer, or project-vendor-boundary when that specialized concern leads. Do not use this skill to restate a generic validation checklist.

Completion Workflow

  1. Read the applicable repository instructions, README, CI configuration, contributor docs, and presets. Identify authoritative commands and mandatory gates; do not invent a second workflow.
  2. Map the touched surface to the narrowest honest repo-defined proof. Do not run broad checks merely because they exist.
  3. Execute within the task's authority. Prefer check modes for read-only work; do not install tools, start services, or mutate the environment just to close a checklist.
  4. Report exact commands, outcomes, gaps, and the narrowest next command that would close each material gap without implying it passed.

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.

Reviews can't be read right now.

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.