AC daily-mood
Daily Mood delivers a warm, deeply thoughtful life message to every registered user each morning and evening — tuned to their emotional state. Unlike static quote cards, Daily Mood is mood-aware: users report how they're feeling (happy, anxious, tired, lost, grateful…) and instantly receive a message crafted for that exact headspace. Every morning at 08:00 a fresh message goes out; every evening at 21:00 a gentle night-time reflection closes the day. Multi-user support means the cron job walks every registered user and sends each one a personalised push in their preferred language (Chinese or English). No external API needed — all message generation is handled by the Agent's own language ability, grounded by a curated mood-to-tone mapping. Trigger words: 心情寄语, 今日寄语, 人生寄语, 寄语, 今天心情, 我今天很累, 我很焦虑, 我很开心, 我迷茫了, 给我一句话, 鼓励我, 陪伴, 治愈, 晚安寄语, 早安寄语, daily mood, mood message, life message, morning message, evening message, send me a message, encourage me, daily wisdom, 每日寄语, 开启寄语推送.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "keywords"
Process rating: all ten parameters 51/100
- 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
- 30Running it twice. 3 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 712 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)
- +3Description length 985: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (4 code blocks)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.