AC english-learning-coach
Use this skill for English practice conversations that must check the user's English before replying, decide whether to continue chatting or correct only, control the agent's output vocabulary level, score grammar/vocabulary/naturalness/clarity, keep an error book, track active vocabulary, estimate CEFR, run mini quizzes, and summarize progress. Use it whenever the user wants English conversation practice, simple-level English chat, English correction, vocabulary tracking, an error notebook, CEFR estimation, /level, /summary, /stats, /review, /quiz, or asks to chat in English while being corrected only when needed. 必须在英语陪练、英文纠错、输出词汇难度控制、错题本、词汇统计、CEFR 水平估算、学习总结等场景使用。
Use this skill for English practice conversations that must check the user's English before replying, decide whether to continue chatting or correct only…
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (english-learning-coach) differs from the folder (english-learning-coach-txqy)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 72 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2757 tokens
- low 13 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
- +1No license
- +2Single-language instructions
- +3Description length 674: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.