AB skill-retrieval-gate
Decide whether to run `memory_search` before following another skill or workflow, so the agent can reduce token usage without forcing retrieval on every task. Use when a task may depend on local knowledge, project history, prior decisions, user preferences, or existing notes, and you need a lightweight rule for when to retrieve, how to query, how much context to load, and when to fall back. Typical triggers include requests like: continue previous work, use project memory first, check what we already documented, base this on existing notes, or decide whether retrieval is worth it before following the skill.
As a process B 68/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, progress reporting
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: 7. 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 68/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 31 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 605 tokens
- 100Running it twice. No mutating operations
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)
- +1No license
- +2Single-language instructions
- +3Description length 614: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.