AB incident-fupan
事故复盘 / Incident Fupan — structured root cause analysis for production failures, outages, bugs, and near-misses. Use when: (1) 事故复盘 or incident review is needed, (2) a production incident just happened and needs root cause analysis, (3) an agent made a costly mistake and you want to prevent recurrence, (4) building safety rules or kill switches from incident patterns. Triggers on: 复盘, fupan, postmortem, incident review, root cause analysis, 事故分析. Generates a full report with timeline, 5 Whys root cause, impact assessment, fix/prevention actions, and new defensive rules. NOT for: routine debugging, feature planning, or non-incident analysis.
As a process B 71/100 · 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: 4. 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 71/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 28 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 1135 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 647: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.