CF litigation-hub
诉讼信息中枢系统。接收法院短信、送达链接、纸质文书照片，自动 OCR 识别、下载、归档、归类到标准案卷目录。基于 12 种期限规则库自动匹配，通过系统日历 + QQ 邮件（微信送达）+ 本机电脑提醒（系统通知 + 桌面 Markdown 文件）三条线提醒，支持 macOS / Windows / Linux 全平台。
诉讼信息中枢系统。接收法院短信、送达链接、纸质文书照片，自动 OCR 识别、下载、归档、归类到标准案卷目录。基于 12 种期限规则库自动匹配，通过系统日历 + QQ 邮件（微信送达）+ 本机电脑提醒（系统通知 + 桌面 Markdown 文件）三条线提醒，支持 macOS / Windows / Linux 全平台。
As a process F 33/100 · Will not run — References files that are not bundled: references/pending-items.json
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-persistencescripts/court_calendar.py:135Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)plist_path = os.path.expanduser(f"~/Library/LaunchAgents/{label}.plist")code literal -
medium Dangerous commands
cmd-persistencescripts/court_calendar.py:184Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)plist_path = os.path.expanduser(f"~/Library/LaunchAgents/{label}.plist")code literal -
medium Dangerous commands
cmd-persistencescripts/court_calendar.py:220Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)plist_path = os.path.expanduser(f"~/Library/LaunchAgents/{label}.plist")code literal -
medium Dangerous commands
cmd-persistenceSKILL.md:1014Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)| 日历事件重复 | 已内置去重（写入前自动删除同案号旧事件），如仍有重复请检查 launchd 是否有残留 plist：`ls ~/Library/LaunchAgents/com.mm.court-*` |
table -
low Dangerous commands
cmd-persistencescripts/court_deadline_reminder.py:209Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)plist_path = os.path.expanduser(f"~/Library/LaunchAgents/{label}.plist")detectorcode literal -
low Dangerous commands
cmd-persistencescripts/court_deadline_reminder.py:429Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)plist = os.path.expanduser(f"~/Library/LaunchAgents/{label}.plist")detectorcode literal
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7619 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/pending-items.json - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "original_author" - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName"
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: references/pending-items.json
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 70Execution cost. Instruction body is 7619 tokens
- 100Steps. 184 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -267 emoji in the instructions: noise for the model
- -32 of 6 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 159: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 184 items
- +4Has examples (41 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.