BD veezvg-auto-evolution
Build and maintain a self-evolving skill system that silently captures feedback, graduates repeated feedback into formal rules, improves low-performing skills, and proposes new skills when repeated patterns are not covered. Use when users mention auto evolution, feedback capture, rule graduation, skill optimization, evolution proposals, "that's not right", "you forgot again", "not like this", 自动进化, 反馈沉淀, 规则毕业, Skill 优化, or 新 Skill 提议.
As a process D 38/100 · Unfinished process — weak spots: steps, result and completion, when it triggers
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Bash Grep Glob
Files scanned: 10. 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 38/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 633 tokens
- 100Running it twice. No mutating operations
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)
- +4Structure: 0 headings, hard to scan
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 438: enough signal without eating the budget
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.