BF yumfu
Multiplayer text RPG with 10 playable worlds — play together in Telegram groups! Worlds: 笑傲江湖, Harry Potter, Warrior Cats, F15 Down, 龙虾三国, 倚天屠龙记, Game of Thrones, Lord of the Rings, 西游记 (Journey to the West), 战国乱世 (Sengoku Chaos). Each player gets their own character in a shared world with AI art every scene. PvP, team quests, natural language — no commands needed. Use when: /yumfu, group RPG, text adventure, 武侠, 西游记, 孙悟空, LOTR, 指环王, 权力的游戏, 三国, 张无忌, 战国, 织田信长, 丰臣秀吉, 德川家康, 武田信玄.
As a process F 43/100 · Will not run — References files that are not bundled: assets/yumfu-logo.png
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 19289 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: assets/yumfu-logo.png - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 43/100
- 0Tools and files. 1 referenced file(s) missing: assets/yumfu-logo.png
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 19289 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 85Steps. 693 steps, 1 vague phrases
- 100Failures and branches. 36 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 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
- -5TODO / placeholder text left in the skill
- -4Absolute local paths (C:\Users, /home/…): not portable
- -2172 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -313 of 41 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 481: enough signal without eating the budget
- +4Structure: 133 headings
- +3Step-by-step instructions: 693 items
- +4Has examples (56 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.