CD sakyamuni-buddha-18lang
釋迦牟尼佛（Śākyamuni Buddha）18 語言 AI 人設與語錄庫 Skill。當用戶需要與「佛陀」對話、尋求佛法解答、人生智慧指引，或需要引用佛典語錄（法句經/慈經/吉祥經/心經/金剛經等）時使用。內建 18 種語言完整人設（中簡繁/英/日/韓/泰/緬/Pāli/梵/藏/越/僧伽羅/高棉/寮/印尼/印地/蒙古/法/俄）、19 語言經典語錄庫（40 則，含白話解釋+範例故事+應用提示）、54 則問答模板。適用場景：佛法問答、人生困惑指引、修行建議、佛典語錄引用、多語言佛教內容生成。Trigger keywords: 佛陀/釋迦牟尼/佛教/佛法/四聖諦/八正道/法句經/慈經/心經/金剛經/Buddha/Buddhism/Dharma/仏教/부처님/Phật pháp etc.
釋迦牟尼佛（Śākyamuni Buddha）18 語言 AI 人設與語錄庫 Skill。當用戶需要與「佛陀」對話、尋求佛法解答、人生智慧指引，或需要引用佛典語錄（法句經/慈經/吉祥經/心經/金剛經等）時使用。內建 18…
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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
-
high Obfuscation
uni-zero-widthpersona/sakyamuni-buddha-persona-18lang.md:118Zero-width / invisible characters (possible hidden text) (4 occurrences)- **නම**：බුදුරජාණන් වහන්සේ / ගෞතම බුදුරජාණන් වහන්සේ / භාග්␀යවතුන් වහන්සේ
-
high Obfuscation
uni-zero-widthqa-templates/sakyamuni-buddha-qa-templates-18lang.md:143Zero-width / invisible characters (possible hidden text) (5 occurrences)> බුදු යනු "පිබිදුණු තැනැත්තා" යි — දෙවියෙක් නොව, සම්පූර්ණයෙන් අවදි වූ මිනිසෙකි. මම ගෞතම බුදුරජාණන් වහන්සේය. පුරාණ ඉන්දියාවේ ඉපදී, ඉපදීම, දිරීම, ලෙඩවීම, මැරීම ය…
Files scanned: 7. 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 49/100
- 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 (sakyamuni-buddha-18lang) differs from the folder (deploy-skill)
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Execution cost. Instruction body is 659 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
- -213 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 346: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.