AC WorkOS
Connect OpenClaw and other AI agents to WorkOS — a self-hosted workspace platform with documents, databases, tasks, meeting transcription, and sharing. Exposes 60+ tools through a remote MCP server with OAuth 2.1.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
IntegrationAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 30 mutating operations with no state check
- 40Consistency. Frontmatter name (WorkOS) differs from the folder (workosmcp)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 21 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1286 tokens
- 100Progress reporting. Reports progress
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 213: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.
External checks
ClawHub: clean
This is a coherent WorkOS MCP connection skill that clearly discloses OAuth access and workspace read/write capabilities, with no hidden execution or persistence in the artifacts.
LLM: benign (high) · VirusTotal: · 29 May 2026