agentleFS
14ag14ag/claude-skills/notepadpp-plugin-skill/SKILL.md

notepadpp-plugin-skill

Skill0 starsChanged 3 months agoMITView on GitHub

Use when the user asks to create, scaffold, debug, package, or publish a Notepad++ plugin (C++ or C#), including Plugin Admin compatibility, DLL install paths, x86/x64 issues, and nppPluginList submission prep. Do not use for generic Windows apps, VS Code extensions, or plain Notepad++ macros unless plugin architecture is explicitly required.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants a real Notepad++ plugin workflow end-to-end.

    line 8
  2. Distinctive:

    Use this skill for requests like:

    line 12
  3. Distinctive:

    Do not use this skill for:

    line 18
  4. Very specific:

    If the user asks for a very small automation and no binary plugin requirement, recommend PythonScript as a lighter path before building a …

    line 23
  5. Very specific:

    Read references/intake.md and capture:

    line 27
  6. Very specific:

    Read references/implementation-playbook.md and pick one track:

    line 29
  7. Very specific:

    If publishing is requested, follow Plugin Admin and nppPluginList prep in the playbook.

    line 35
  8. Distinctive:

    Ask only high-impact clarifications.

    line 48
  9. Distinctive:

    If architecture mismatch is possible, stop and verify x86 vs x64 before final install steps.

    line 52
  10. Distinctive:

    If user asks for unsafe or policy-violating behavior, refuse that part and continue with safe alternatives.

    line 54

≈ “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

Notepad++ Plugin Skill

Use this skill when the user wants a real Notepad++ plugin workflow end-to-end.

Trigger Boundaries

Use this skill for requests like:

  • "create a Notepad++ plugin"
  • "debug my Notepad++ plugin DLL"
  • "publish my plugin to Plugin Admin"
  • "set up a Notepad++ C# plugin project"

Do not use this skill for:

  • Generic C++/C# desktop development
  • VS Code extension development
  • Simple one-off automation that should be done with macros or PythonScript

If the user asks for a very small automation and no binary plugin requirement, recommend PythonScript as a lighter path before building a DLL plugin.

Workflow

  1. Read references/intake.md and capture:
    • plugin goal, target Notepad++ version, preferred language (C++ or C#), distribution intent, and user constraints.
  2. Read references/implementation-playbook.md and pick one track:
    • native C++ plugin
    • C# plugin pack
    • PythonScript fallback (when full plugin is overkill)
  3. Generate or edit project files in the workspace.
  4. Apply references/troubleshooting.md checks before concluding.
  5. If publishing is requested, follow Plugin Admin and nppPluginList prep in the playbook.

Output Contract

For primary triggers, respond with:

  • Plan: short implementation plan tied to user goal.
  • Changes: files created/edited and what each does.
  • Build + Install: exact build commands and plugin install path.
  • Verification: what was validated and remaining risks.
  • Next step: one recommended next action if work is incomplete.

Dialogue Policy

  • Ask only high-impact clarifications. Default assumptions:
    • Windows 10/11
    • modern Visual Studio toolchain
    • Notepad++ x64 unless user states otherwise
  • If architecture mismatch is possible, stop and verify x86 vs x64 before final install steps.
  • Work collaboratively with any other loaded skill; do not assume exclusive control of the workflow.
  • If user asks for unsafe or policy-violating behavior, refuse that part and continue with safe alternatives.

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.