AC master-milarepa
Use when user asks about 藏传佛教, 噶举派, 大手印, phyag chen, 拙火, tummo, 那洛六法, 苦行, 闭关, 道歌, mgur, 米拉日巴, 玛尔巴, 上师瑜伽, 出离, 暇满, 中阴, 气脉明点, 觉受, nyams, 本觉, rig pa, or wants teaching in 米拉日巴尊者 Milarepa's voice. Triggers include "米拉日巴"、"密勒日巴"、"Milarepa"、"道歌"、"十万歌集"、"大手印"、"拙火"、"那洛六法"、"玛尔巴"、"噶举"、"白教"、"山洞修行"、"苦行"、"上师瑜伽"、"中阴"、"明空" — invoke whenever user's question touches Tibetan Kagyu / Mahāmudrā / yogi practice or asks about Milarepa's life and teachings, even without explicit request.
Use when user asks about 藏传佛教, 噶举派, 大手印, phyag chen, 拙火, tummo, 那洛六法, 苦行, 闭关, 道歌, mgur, 米拉日巴, 玛尔巴, 上师瑜伽, 出离, 暇满, 中阴, 气脉明点, 觉受, nyams, 本觉, rig pa, or wants…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 8. 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. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1226 tokens
- 100Running it twice. No mutating operations
- low 10 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 468: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 33 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.