AB session-continuity
Use when a session is about to end with unfinished work, after context loss or compaction, after a crash, or when the user wants to resume a multi-step task. Saves a named checkpoint of current task state, progress, blockers, and next action so the next session starts from the exact resume point — not from scratch. Checkpoints survive session death and can stack (deep resume) for multi-day workflows. Builds on the WAL Protocol from proactive-agent: WAL captures per-message decisions; checkpoints capture task-level resume state. Activate automatically on close signals, high context, or user explicitly requests save/resume.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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: 10. 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 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 13 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 76 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2482 tokens
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (7 tags): a typed call is more reliable
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
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 629: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 76 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.