AB memory-lifecycle
Structured memory management to resolve cliff-edge forgetting, false persistence, context blowup, contradictions, hallucinated recall, and stale accumulation. Use when the user states anything durable to carry across sessions — preferences, corrections, decisions, team/environment facts, or standing instructions ('from now on...', 'always X before Y', 'never...') even without saying 'remember'; for first-time setup, compaction flush, deep research or project work, recalling a past session missing from context, when MEMORY.md exceeds its size threshold, or on 'init memory' / 'promote memory' / 'compact memory' / 'workspace init'.
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions
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: 6. 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
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 5 branches
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2261 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 636: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.