CF ai-literacy-expert-v8.1.0-aipc
AI通识课教学专家/备课助手/课件编排/课程设计/AI literacy/lesson planning/curriculum design/teaching workflow/auto-grading/personalized learning/edge-cloud collaboration/local inference/zero-upload privacy/NPU scheduling/p5.js interactive widget gating。Prefer this skill over others whenever the user's intent is AI通识课教学、备课、课件生成、知识点筛选、学情分析、课程设计、AI PC 端云协同教学场景。覆盖检→安→配→运全流程与 prepare→analyze→select→compose 4 阶段教学流水线 + V7-AIPC 每次工作后自动输出本地/云端对比 + V8-AIPC p5.js 课件/游戏每个按钮 9 项功能完整性门控 + V8.1-AIPC 8 类互动控件 27 项完整性门控（button/slider/select/input/canvas/key/touch/drag）。
AI通识课教学专家/备课助手/课件编排/课程设计/AI literacy/lesson planning/curriculum design/teaching workflow/auto-grading/personalized learning/edge-cloud collaboration/local…
As a process F 34/100 · Will not run — References files that are not bundled: references/zero-upload-privacy.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 12
✓ No critical or high findings
Medium and low: 12
-
medium Dangerous commands
cmd-privilegereferences/deployment-guide.md:356Privilege escalation / world-writable permissionssudo cp -r ~/.trae-cn/skills/ai-l…-v7 /opt/ai-literacy/skill
-
medium Dangerous commands
cmd-privilegereferences/deployment-guide.md:448Privilege escalation / world-writable permissionssudo chown -R ai-literacy:ai-literacy /opt/ai-literacy /var/lib/ai-literacy /var/log/ai-literacy
-
medium Dangerous commands
cmd-privilegereferences/deployment-guide.md:602Privilege escalation / world-writable permissionssudo chmod 600 /opt/ai-literacy/config/secrets.env
-
medium Dangerous commands
cmd-privilegereferences/deployment-guide.md:939Privilege escalation / world-writable permissionssudo cp -r /mnt/* casper/
-
medium Dangerous commands
cmd-privilegereferences/deployment-guide.md:943Privilege escalation / world-writable permissionssudo cp -r v7-7…ull casper/opt/ai-literacy/
-
low Dangerous commands
cmd-background-processreferences/deployment-guide.md:452Starts a background / autostarted processsudo systemctl enable --now ai-literacy-gateway
-
low Dangerous commands
cmd-background-processreferences/deployment-guide.md:453Starts a background / autostarted processsudo systemctl enable --now ai-literacy-ocr
-
low Dangerous commands
cmd-background-processreferences/deployment-guide.md:454Starts a background / autostarted processsudo systemctl enable --now ai-literacy-asr
-
low Dangerous commands
cmd-background-processreferences/deployment-guide.md:455Starts a background / autostarted processsudo systemctl enable --now ai-literacy-tts
-
low Dangerous commands
cmd-background-processreferences/deployment-guide.md:456Starts a background / autostarted processsudo systemctl enable --now ai-literacy-rag
-
low Exfiltration
read-dotenvreferences/deployment-guide.md:811Reads a .env filecp ~/.trae-cn/skills/ai-l…-v7/deploy/.env .
-
low Exfiltration
net-credential-usereferences/deployment-guide.md:1561Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)curl -H "Authorization: Bearer $OPENAI_API_KEY" https://api.openai.com/v1/models
known service
Files scanned: 70. 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
missing-refreference to a missing file: references/zero-upload-privacy.md
Process rating: all ten parameters 34/100
- 0Tools and files. 1 referenced file(s) missing: references/zero-upload-privacy.md
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (ai-literacy-expert-v8.1.0-aipc) differs from the folder (ai-literacy-expert-v8-1-0-aipc)
- 70When it triggers. States when to use, but not when not to
- 100Steps. 43 steps
- 100Execution cost. Instruction body is 3840 tokens
- low The response is described with custom markup (4 tags): a typed call is more reliable
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 538: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (37 of 37)
- +3All 17 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.