AC igpt-email-search
Secure, per-user-isolated semantic email search via the iGPT API. Hybrid semantic + keyword retrieval across a user's full Gmail, Outlook, or IMAP inbox history — no shell access, no filesystem access, API-key scoped only. Returns relevant messages and threads ranked by meaning, not just keyword overlap. Use when the user needs to find specific emails, threads, or conversations by topic, participant, date range, or content. Retrieval only — for reasoning, summaries, or structured extraction, use the companion skill igpt-email-ask.
As a process C 62/100 · Has gaps — weak spots: result and completion, consistency, running it twice
The same skill appears in 1 more place: ClawHub
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (igpt-email-search) differs from the folder (igpt-email-intelligence)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 34 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 2007 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 536: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.