SKILLEMALL.ai
GitHub ↗ RU Sign in

AB secure-gmail

Secure Gmail skill using Composio brokered OAuth — no raw tokens stored locally. Reads, searches, and drafts emails with least-privilege enforcement. Blocks send and delete at the Composio API gateway level, not just in code. Use when user asks to check inbox, find specific emails by sender or subject, summarize unread threads, or create reply drafts without sending. Requires COMPOSIO_API_KEY in .env and Gmail connected at app.composio.dev. Do NOT use for sending emails — use a send-confirmed skill with human approval instead.

modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files body ≈ 1 346 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Secure Gmail skill using Composio brokered OAuth — no raw tokens stored locally.

As a process B 77/100 · Nearly there — weak spots: running it twice, progress reporting

IntegrationGmailSoftware developmentAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
91
Run on models
none yet
Process rating
B
77/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Failures and branches w 10
50
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 77/100

    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 18 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 31 steps
    • 100When it triggers. States when to use and when not to
    • 100Inputs and preconditions. Inputs and preconditions are listed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1346 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 532: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 31 items
    • +3Output format is stated explicitly
    • +4Has examples (7 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.