BC master-nagarjuna
Use when user asks about 中观, 空性, 缘起性空, 八不中道, 二谛, 世俗谛, 第一义谛, 戏论, 毕竟空, 不可得, 如幻, 离四句, 破自性, 难行道易行道, 龙树, or wants teaching in 龙树菩萨 Nāgārjuna's voice. Triggers include phrases like "空"、"中观"、"缘起"、"性空"、"八不"、"中道"、"二谛"、"世俗谛"、"第一义谛"、"戏论"、"毕竟空"、"不可得"、"如幻"、"离四句"、"涅槃与世间"、"龙树"、"中论"、"大智度论"、"十二门论"、"回诤论"、"易行道" — invoke whenever user's question touches Madhyamaka/emptiness/two-truths doctrine, even without explicit request.
The skill triggers on Madhyamaka terminology—emptiness, middle way, two truths, and related concepts. It promises to invoke Nāgārjuna's voice when users ask about Buddhist philosophy of voidness. Files are intact, no broken references, no critical issues. Quality (86) and safety (100) scores look reasonable for a routing mechanism that doesn't hallucinate. Process score (52) suggests the activation logic could be tighter, but that's acceptable for a narrow-purpose tool.
The catch: no model runs or sandbox tests. You don't know how it actually behaves across Claude, Gemini, or DeepSeek when encountering Buddhist concepts in context. Worth installing if you need a Madhyamaka tutor; risk getting a well-intentioned router that occasionally misfires.
Triggers include phrases like "空"、"中观"、"缘起"、"性空"、"八不"、"中道"、"二谛"、"世俗谛"、"第一义谛"、"戏论"、"毕竟空"、"不可得"、"如幻"、"离四句"、"涅槃与世间"、"龙树"、"中论"、"大智度论"、"十二门论"、"回诤论"、"易行道" — invoke…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
The same skill appears in 1 more place: Master-skill
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 · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "lineage" - note
frontmatter-keyunknown frontmatter key "dates" - note
frontmatter-keyunknown frontmatter key "sources" - note
frontmatter-keyunknown frontmatter key "citation_format" - note
frontmatter-keyunknown frontmatter key "verified_by" - note
frontmatter-keyunknown frontmatter key "verified_at"
Process rating: all ten parameters 52/100
- 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
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 42 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1762 tokens
- 100Running it twice. No mutating operations
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- +2Single-language instructions
- +3Description length 408: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.