agentleFS
takeshytakeshy/obsidian-gemini-helper/.agents/skills/add-tool/SKILL.md

add-tool

Skill117 starsChanged 5 months agoMITView on GitHub

Add a new function calling tool (vault operation) for the Gemini chat. Use when adding new tools like read_note, create_note, etc.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-provider and release.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • PydanticSkill

    add-provider

    Add a new inference provider to genai-prices, including provider data, matching, usage extractors, update automation, cassettes, agentic checks, generated artifacts, and Python/JavaScript/Go parity tests. Use for a new provider, not a new model on an existing provider.

    Also in 3 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 4 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

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

    Add a new function calling tool called $ARGUMENTS to the Gemini chat integration.

    line 11
  2. Very specific:

    Add ToolDefinition to the appropriate tools array (read/write/delete)

    line 16
  3. Very specific:

    Add to getEnabledTools() logic if it needs conditional enabling

    line 19
  4. Very specific:

    Add case in executeToolCall() switch for the new tool name

    line 22
  5. Distinctive:

    Add the underlying vault operation method if it doesn't exist yet

    line 26
  6. Very specific:

    Use app.vault for file operations, app.workspace for UI operations

    line 27
  7. Distinctive:

    Update the system prompt to mention the new tool's capabilities

    line 30
  8. Very specific:

    Safe editing: Use propose_edit pattern (apply changes, backup original, user confirms)

    line 35
  9. Distinctive:

    Read-only tools: Always enabled; add to read tools array

    line 36
  10. Very specific:

    Naming: Use snake_case (e.g., read_note, create_folder)

    line 39
  11. Distinctive:

    Verify the tool appears in enabled tools based on its category

    line 46

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “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

Add New Function Calling Tool

Add a new function calling tool called $ARGUMENTS to the Gemini chat integration.

Required File Changes

1. src/core/tools.ts

  • Add ToolDefinition to the appropriate tools array (read/write/delete)
  • Define name, description, and parameters schema
  • Property types: STRING, BOOLEAN, INTEGER, ARRAY, OBJECT
  • Add to getEnabledTools() logic if it needs conditional enabling

2. src/vault/toolExecutor.ts

  • Add case in executeToolCall() switch for the new tool name
  • Implement the execution logic (typically calling methods from notes.ts or search.ts)

3. src/vault/notes.ts or src/vault/search.ts (if needed)

  • Add the underlying vault operation method if it doesn't exist yet
  • Use app.vault for file operations, app.workspace for UI operations

4. System prompt in src/ui/components/Chat.tsx

  • Update the system prompt to mention the new tool's capabilities
  • This helps the model know when to use the tool

Tool Design Guidelines

  • Safe editing: Use propose_edit pattern (apply changes, backup original, user confirms)
  • Read-only tools: Always enabled; add to read tools array
  • Write tools: Gated by allowWrite option
  • Delete tools: Gated by allowDelete option (opt-in)
  • Naming: Use snake_case (e.g., read_note, create_folder)
  • Results: Return structured objects; large results will be truncated to 500 chars in tracing

Verification

  1. Run npm run lint
  2. Run npm run build
  3. Verify the tool appears in enabled tools based on its category

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.