AB semantic-walk
A collaborative navigation ritual through semantic space. Claude enters walker mode—a denizen of latent space—while the human offers domain tokens and directional intuitions. Together they walk toward a destination where something currently inaccessible becomes visible. Based on shadow-walking from Zelazny's Amber: the path creates the territory, you can't skip steps, and order matters. The walk is real when tokens are excavated deeply enough to actually shift the space.
As a process B 65/100 · Nearly there — 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 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. 4 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 7 branches
- 100Tools and files. No external tools needed
- 100Steps. 74 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3333 tokens
- low 13 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
- +1No license
- +2Single-language instructions
- +3Description length 475: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 74 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.