BF claw-rpg
D&D-style RPG character system for AI lobster assistants. Automatically generates a character sheet from SOUL.md and MEMORY.md, assigns class (wizard/bard/rogue/paladin/druid/fighter) and 6 stats, tracks XP from token usage, levels up from 1 to 999 with a prestige system, and fires hidden easter egg flavor text during conversations. Use when: initializing a lobster's RPG character, syncing XP after conversations, checking level/stats, running prestige at Lv.999, or launching the character dashboard.
As a process F 13/100 · Will not run — References files that are not bundled: references/classes.md, references/abilities.md, references/prestige.md
How to improve
- 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: 2. 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 2, column 14: description: D&D-style RPG character system for AI lobster assistants. Automati… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
missing-refreference to a missing file: references/classes.md - warning
missing-refreference to a missing file: references/abilities.md - warning
missing-refreference to a missing file: references/prestige.md
Process rating: all ten parameters 13/100
- 0Tools and files. 3 referenced file(s) missing: references/classes.md, references/abilities.md, references/prestige.md
- 0Steps. Prose only: no discrete steps
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (claw-rpg) differs from the folder (ramboxie-claw-rpg)
- 100Execution cost. Instruction body is 692 tokens
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 504: enough signal without eating the budget
- +4Structure: 10 headings
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.