BC master-debate
Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争. Differs from /compare-masters (parallel single-round) by being adversarial multi-round via fresh-subagent orchestration. Topics 空有 / 禅净 / 性相 / 戒律 vs 内观 — trigger is adversarial framing: "禅净比较" → compare; "禅净辩论 / 谁更究竟" → here.
This skill launches a multi-round debate between Buddhist schools—triggered by phrasing like "who's right: Zen or Pure Land." It promises to unfold opposing positions through fresh sub-agents instead of a single-pass comparison.
The files hold 2729 tokens of instructions, three files, no scripts or test runs. Quality score 82 is solid for philosophical scenarios, but process score 53 signals gaps in orchestration logic. No critical findings. Platforms span Claude to DeepSeek.
The catch: it fires only on explicit "辩论" framing, not "比较." That distinction can blur in translation or context. For a scholar with precise phrasing—it works; for a casual user—it might not trigger at all.
Install if you need dialectic, not comparison, and you'll phrase requests carefully.
Differs from /compare-masters (parallel single-round) by being adversarial multi-round via fresh-subagent orchestration.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "kind" - note
frontmatter-keyunknown frontmatter key "verified_by" - note
frontmatter-keyunknown frontmatter key "verified_at"
Process rating: all ten parameters 53/100
- 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
- 100Tools and files. No external tools needed
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2729 tokens
- 100Running it twice. No mutating operations
- low 12 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 357: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.