BC agent-failure-loop
An end-to-end self-improvement loop that automatically detects agent failures, classifies them, tracks recurrence, auto-generates rules, and promotes them to AGENTS.md/CLAUDE.md. If the same mistake repeats three times, a rule is automatically created.
As a process C 58/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, execution cost
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 8242 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 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. 8 mutating operations with no state check
- 40Execution cost. Instruction body is 8242 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 57 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 18 top-level sections: this looks like several domains in one skill
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)
- -236 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 252: enough signal without eating the budget
- +4Structure: 64 headings
- +3Step-by-step instructions: 57 items
- +3Output format is stated explicitly
- +4Has examples (37 code blocks)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.
External checks
ClawHub: suspicious
This skill is transparent about its purpose, but it can automatically turn local failure notes into persistent agent rules without a required human approval step.
LLM: suspicious (high) · VirusTotal: · 29 May 2026