Gmail Draft Initialize

Atomic node skill to initialize a Gmail draft with recipients.

Security Scan

The skill's instructions and requirements are narrowly focused on creating a Gmail draft via a 'gog' CLI and are internally consistent, but it depends on an external binary of unknown provenance so verify that binary before use.

Purpose & Capability

The name/description (initialize a Gmail draft with recipients) matches the single required binary ('gog') and the single command the SKILL.md instructs the agent to run. Asking for the gog CLI is proportionate to the described task.

Instruction Scope

SKILL.md is narrowly scoped: it tells the agent to run a single CLI command, check the JSON response for a draftId, and retry up to 3 times on failure. It does not instruct reading unrelated files, scanning environment variables, or transmitting data to unknown endpoints.

Install Mechanism

There is no install spec and no code files — this is instruction-only. That is the lowest-risk install model. The skill assumes the 'gog' binary is already present on PATH.

Credentials

The skill declares no env vars or credentials, which is reasonable if the 'gog' CLI is already authenticated in the environment. However, because it relies on an external binary, that binary (and its configuration/storage of credentials) is the implicit credential surface — the skill itself does not request unrelated secrets.

Persistence & Privilege

always is false, the skill is user-invocable, and it does not request system-wide persistence or modify other skills' configs. Autonomous model invocation is allowed by default but not excessive here given the narrow scope.

Assessment

This skill is narrowly focused and appears coherent, but it depends entirely on an external 'gog' CLI of unknown origin. Before installing or enabling it: 1) Verify what 'gog' is (project homepage, publisher) and install it from a trusted source; 2) Confirm the 'gog' binary is already authenticated to the correct Gmail account and review what credentials/config it stores; 3) Test the skill in a safe/sandboxed environment to confirm it only creates drafts and returns draftId; 4) If you do not want an agent to invoke this autonomously, keep it user-invocable only or disable autonomous invocation. If you need additional assurance, request the skill author/source or a checksum/official install instructions for 'gog.'

Lean Philosophy (Principles)

• Kaizen (改善): This skill is an atomic node, strictly limited to initializing a draft with recipients, preventing complex multi-field string constructions.
• Standardized Work (Hyojun Sagyo): This node represents the most efficient, standardized path for this specific task before automation.
• Jidoka (自働化): This node includes autonomous defect detection. It relies on the CLI's self-healing loop and will report errors if the initialization fails.

This skill allows the agent to create a new, empty email draft in Gmail with specified recipients. It does NOT set the subject or body (use the dedicated update skills for those).

Cognitive Directives

WHEN [A new email needs to be drafted] THEN [Execute the native terminal command gog gmail drafts create --to "..." --json]

Schema Example

{
  "command": "gog gmail drafts create --to \"[e-mail]\" --json"
}

Jidoka Validation Loop

1. Try: Execute the command.
2. Evaluate: Check the JSON response to confirm the draft ID is returned.
3. Correct/Fail: If it failed or hallucinated parameters, retry up to 3 times (max_retries=3) with the exact error.
4. Proceed: Return the final draft ID for subsequent update steps.

Expected Output

A JSON object confirming the draft was created and returning the draftId.