BF ssq-probability-analyzer
双色球算法选号防被骗 · 理性购彩科普助手 + 防割韭菜盾：随机性检验、选号思路科普与打假、胆拖结构优化、开奖数据核对，只讲真话、帮你买得明白不被大师割韭菜。当用户想了解双色球开奖的随机性、鉴别选号套路、核对开奖数据、或做理性购彩科普时使用。生成严谨的科普分析报告，内置对"预测可行性"的统计证伪（红球熵效率/任一组合恒等概率/样本外回测/no_edge 结论）、22 项自检护栏。核心立场：数学上任何选号思路都不优于随机，仅供娱乐参考，须量力而行、绝不可作为收益依据。
双色球算法选号防被骗 · 理性购彩科普助手 +…
As a process F 34/100 · Will not run — References files that are not bundled: references/faq.md, scripts/run_ssq.py, scripts/lib/REPORT_PATH.txt
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-agent-memory-dumpmemory.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensmemory.md
-
medium Dangerous commands
cmd-persistenceoperations.md:110Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- 任务名 `SSQ_…art`：`schtasks /create /tn SSQ_…art /tr "绝对路径\ssq_…bat" /sc weekly /d MON,WED,SAT /st 20:10 /ru SYSTEM /rl highest`
quoted
Files scanned: 61. 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
missing-refreference to a missing file: references/faq.md - warning
missing-refreference to a missing file: scripts/run_ssq.py - warning
missing-refreference to a missing file: scripts/lib/REPORT_PATH.txt - warning
missing-refreference to a missing file: references/scripts.md - warning
missing-refreference to a missing file: references/methodology.md - warning
missing-refreference to a missing file: references/operations.md - warning
missing-refreference to a missing file: references/changelog.md - warning
missing-refreference to a missing file: scripts/lib/ssq_error_log.txt - warning
missing-refreference to a missing file: scripts/lib/ - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 34/100
- 0Tools and files. 9 referenced file(s) missing: references/faq.md, scripts/run_ssq.py, scripts/lib/REPORT_PATH.txt
- 0Result and completion. Does not say what the result is
- 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
- 40Consistency. Frontmatter name (ssq-probability-analyzer) differs from the folder (ssq-skill)
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 4616 tokens
- 100Steps. 97 steps
- 100Running it twice. No mutating operations
- low 14 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 235: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 97 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.