AD blooming-elf-v4
绿灵·Blooming Elf-v4 — This skill should be used when the user wants a reliable plant/flower watering reminder and care assistant (浇花/养花/植物养护). It fixes three recurring failures of the v3 markdown-based version — stale 'next watering' dates, format corruption in prose tables, and forgotten 'remember this' instructions — by storing mutable state in a structured plants.json (single source of truth), validating every write, and forcing persistence on 'remember'. It also incorporates an expert audit (15 corrections) covering pet-toxicity safety, watering-by-soil-moisture-first, formula simplification, cut-flower preservative, and acidifying best practices, and retains all of v3's onboarding, plant library, care rules, and SOPs.
绿灵·Blooming Elf-v4 — This skill should be used when the user wants a reliable plant/flower watering reminder and care assistant (浇花/养花/植物养护).
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 49/100
- 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
- 30Running it twice. 10 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 124 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3530 tokens
- low 19 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)
- +3Output format is not stated: the model decides each time
- -230 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 731: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 124 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.