SKILLEMALL.ai

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.

ClawHub Hermes author: voronindenis5 v0.1.1 MIT-0 7 files body ≈ 2 502 tokens Open the sourceclawhub.ai analyzed 3 d ago

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

GeneratorData and analyticsAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
99
Quality 40%
90
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
  • 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-security references/failure-taxonomy.md:76
    Offensive-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-hermes description 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.

External checks

ClawHub: suspicious
The skill is a coherent failure-analysis tool, but it can persist sensitive session-log details without redaction guidance or clear storage limits.
LLM: suspicious (high) · VirusTotal: · 11 Aug 2026