AC incident-postmortem
Generate structured, blame-free incident postmortem reports from logs, timeline data, and incident metadata. Produces root cause analysis, impact assessment, timeline reconstruction, lessons learned, and action items. Supports log parsing (syslog, JSON, Apache/Nginx, Python tracebacks), timeline JSON input, blame-free language checking, and multiple output formats (markdown, HTML, JSON). Use when asked to create a postmortem, write an incident report, document an outage, generate a post-incident review, analyze incident timeline, check postmortem language for blame, create RCA (root cause analysis), or produce an after-action report. Triggers on "postmortem", "incident report", "outage report", "post-incident", "root cause analysis", "RCA", "after-action", "blameless review", "incident review".
As a process C 55/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
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 55/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (incident-postmortem) differs from the folder (cm-incident-postmortem)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 15 steps
- 100Execution cost. Instruction body is 794 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 805: 120–800 characters recommended
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 15 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.