AC buddy_mode
A living digital companion that grows with the user. Each buddy is a non-human creature born from the user's real habits — debugging spawns ember-pool creatures, coffee breaks hatch warm sprouts, hiking plans attract trail driftlings. Buddies remember shared experiences, grow stats over time, and form collections unique to each person. Activates on /buddy or when the user asks for a companion. Supports bilingual zh/en, rarity luck rolls, dynamic pool generation, context-aware reactions, and stat growth through use.
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, consistency, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 8617 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 19 mutating operations with no state check
- 40Consistency. Frontmatter name (buddy_mode) differs from the folder (driftling-buddy)
- 40Execution cost. Instruction body is 8617 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 18 branches
- 100Steps. 295 steps
- 100When it triggers. States when to use and when not to
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 24 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 520: enough signal without eating the budget
- +4Structure: 45 headings
- +3Step-by-step instructions: 295 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.