BC openclaw-agent-cognitive-os
Use when activating top-level agent control: goal understanding, hierarchical planning, state tracking, multi-plugin orchestration, verification, recovery, reflection, and completion control.
Use when activating top-level agent control: goal understanding, hierarchical planning, state tracking, multi-plugin orchestration, verification, recovery…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 5. 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 6, column 12: changelog: ClawHub professional standard: Overview, When to Use, How to Use, Co… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog" - note
frontmatter-keyunknown frontmatter key "emoji"
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (openclaw-agent-cognitive-os) differs from the folder (agent-cognitive-os)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 85Steps. 75 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 3920 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 51 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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 191: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 75 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.