BC Statvs
Front door to STATVS (said status), the one append-only record of what happened across LifeOS and every app it runs: checks the record's health, says whether a system, app or site reports into it, writes rows, answers what happened, rebuilds and drills views, rewinds and replays past turns, and onboards a system through the five-step migration. USE WHEN statvs, status logging, status record, the record, is X logging to status, is my site reporting into status, full status logging, log this to status, write a status row, what happened, status tail, verify the record, status counters, drill, restore drill, rebuild a view, compare a view, rewind a turn, replay a miss, onboard X into status, migrate X to statvs, dual-write, register a stream. NOT FOR session status or why is this slow (the s shortcut), posting Vigil events or deciding what to text the principal (Vigil), complaints (Errata), memory recall (Cortex).
Promises to be the front door to STATVS logging: check record health, answer what happened in the system, write log rows, rebuild views, rewind past states, migrate new systems. Contains 8 files, 1627 tokens, no linter errors. Quality score 79, process score 56; no critical findings but coverage gaps remain.
No model runs, no sandbox tests. Description cuts off mid-word, suggesting incomplete work. For a logging system that's a problem: unclear which commands work and how they interact with LifeOS. Install if you already know STATVS internals; otherwise you'll patch the instructions yourself.
Front door to STATVS (said status), the one append-only record of what happened across LifeOS and every app it runs: checks the record's health, says whether…
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "evals"
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 11 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1627 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Description length 923: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 5 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.