BF poetry-resonance
Connect Tang and Song poetry with everyday life — daily poem card, a line for a real moment, plain-language study notes, spaced-repetition review, weekly reading summary. 把唐诗宋词和真实生活连起来：今日日签 / 找一句诗 / 说人话拆解 / 背诗复习 / 读诗周记。五种模式（有感而发 / 学习沉淀 / 今日日签 / 复习验收 / 学习周报）+ 李白全集 + 杜甫苏轼精选诗库。Language scope: Chinese-only by design — the subject is Tang/Song classical Chinese poetry, and no multilingual variant exists or is planned. 中文触发词（须与诗词语境同现才激活）：诗词日签、每日诗词、今日一句、唐诗宋词、古诗配诗、找一句唐诗、诗词拆解、诗词深读、背诗复习、背诗抽查、读诗周记、诗人日签（李白/杜甫/苏轼）。单独出现的"复习""周报""拆解"属通用词，不触发本 skill。Not for academic criticism, metrical composition, or non-Chinese poetry. 零依赖纯本地；联网可选且可关（只发诗名/作者/诗句/城市名，见「数据边界」）。
Connect Tang and Song poetry with everyday life — daily poem card, a line for a real moment, plain-language study notes, spaced-repetition review, weekly…
As a process F 42/100 · Will not run — References files that are not bundled: references/seal_qr.svg, references/*.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 3, column 14: description: Connect Tang and Song poetry with everyday life — daily poem card,… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/seal_qr.svg - warning
missing-refreference to a missing file: references/*.md
Process rating: all ten parameters 42/100
- 0Tools and files. 2 referenced file(s) missing: references/seal_qr.svg, references/*.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 100Steps. 96 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2810 tokens
- low 17 top-level sections: this looks like several domains in one skill
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 652: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 96 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.