CD bazi-engine
四柱八字命理分析智能体。通过引导式交互收集出生信息（姓名、生日（阳历或农历均可）、出生时间、性别、出生地）， 自动排出四柱八字与大运流年，并参照古代命理典籍进行专业分析。输出必须标注古籍出处，保证可追溯、可检验。 适用场景：用户想算八字、看命盘、测运势、查合婚、补五行、看神煞、看流年，或提到"算命/四柱/命理/bazi/fortune"。 即使只提"算命""八字"而未明确说用 skill，也应启用本 skill。 本 Skill 采用双许可：代码 MIT / 数据 CC BY-NC-SA 4.0（详见仓库 LICENSE / LICENSE-DATA）。
四柱八字命理分析智能体。通过引导式交互收集出生信息（姓名、生日（阳历或农历均可）、出生时间、性别、出生地）， 自动排出四柱八字与大运流年，并参照古代命理典籍进行专业分析。输出必须标注古籍出处，保证可追溯、可检验。…
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 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.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-execpolicy-bypasstools/publish_clawhub.ps1:35Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File tools/publ…ps1 -Version 1.4.0 -DryRun
-
medium Dangerous commands
cmd-execpolicy-bypasstools/publish_clawhub.ps1:36Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File tools/publ…ps1 -Version 1.4.0
-
low Secrets in code
secret-high-entropy-tokentools/build_ui.py:69High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)background:url("data:image/png;base64,iVBO…Hn0/FnEz…mk6/mEu+lUe6…viUdetector
Files scanned: 44. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 281 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "license-data"
Process rating: all ten parameters 41/100
- 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
- 40Consistency. Frontmatter name (bazi-engine) differs from the folder (baizi-engine)
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 100Steps. 71 steps
- 100Execution cost. Instruction body is 1663 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
- +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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 280: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 71 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.