AC zai-coding
Configure OpenClaw to use Z.AI GLM Coding Plan models for all coding-related tasks. Set up optimal configuration for development workflows with steps: (1) Verify OpenClaw is running, (2) Choose region (international: zai-coding-global, China: zai-coding-cn), (3) Configure via onboard or manual edit of openclaw.json with ZAI_API_KEY env var, (4) Set optimal model (zai/glm-5, glm-4.7, glm-4.6), (5) Optionally enable tool_stream and adjust context tokens, (6) Restart gateway and validate, (7) Install Z.AI MCP Tools (web-search-prime, web-reader, zread). Use when configuring Z.AI Coding Plan, switching models, or optimizing coding workflows.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Configure OpenClaw to use Z.AI GLM Coding Plan models for all codi… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2832 tokens
- low 12 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 645: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (26 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.