AC failure-forensics
Use when an agent task fails or produces unexpected results. Performs structured post-mortem root cause analysis: categorizes the failure, traces the exact failure point through tool-call logs, reconstructs the decision chain, generates a post-mortem report, and saves lessons to prevent recurrence.
Performs structured post-mortem root cause analysis: categorizes the failure, traces the exact failure point through tool-call logs, reconstructs the decision…
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 Risky intent
intent-offensive-securityreferences/failure-taxonomy.md:76Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- sudo / privilege escalation required but not available
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 299 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 60 steps
- 100Execution cost. Instruction body is 2502 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 299: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.