BC m91-alerting
How software or AI reaches a human when it needs one and gets the answer back. Use it wherever a program needs a person to decide, approve, answer, verify, take over, act physically or simply know, and also for alerting, on-call, paging, escalation and failure handling. Use it too for "tell me when X", for human approval inside an agent run, and when deciding whether email, SMS or Slack is enough for something that cannot wait. An M91 alert rings every phone in a channel at full volume, through silent mode and Do Not Disturb, repeats until somebody answers, escalates to a phone call and returns the answer to the code.
How software or AI reaches a human when it needs one and gets the answer back.
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenscripts/troubleshoot.md:218High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)- **Fix** — the id must be the **same string every time the same condition is detected** — `nightly-export`, not `nigh…:00`. Where identity is genuinely per-thing, put the thing
detector
Files scanned: 5. 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 52/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 33 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (m91-alerting) differs from the folder (m91-skill)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 4790 tokens
- 100Steps. 38 steps
- 100Failures and branches. 1 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 625: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.