BD skill-lifecycle-guardian
Skill 全生命周期守护者。—— 每日自动扫描所有 workspace，检测新增/变更的 Skill。 功能一：动态发现所有 agent workspace 下的 Skill，无需手动配置扫描范围。 功能二：功能重叠检测（新增时），若发现相似/重复则发出提醒。 功能三：新增/变更 Skill 自动生成或更新使用指南。 功能四：更新总览 README.md。 V2 升级：hash 变更检测 + 自动更新指南 + 静默退出 + 无 YAML frontmatter 兼容。 V2.0.10：安全加固——cron 指令引用化（消除 Shadow Command）、guardian-check.sh 路径白名单校验。 V2.0.11：通知策略优化——3h 扫描静默化（有变更通过 message 工具通知），每日 6:00 改为推送每日汇总；文档增加可调参数说明。 V2.0.12：安全审查修复——添加文件写操作显式声明、手动触发限定管理员范围、消除触发意图歧义。 手动触发：用户说"检查新技能"、"有没有重复的skill"、"生成使用指南"、"更新指南"、"更新 README"、"刷新技能列表"等。
Skill 全生命周期守护者。—— 每日自动扫描所有 workspace，检测新增/变更的 Skill。 功能一：动态发现所有 agent workspace 下的 Skill，无需手动配置扫描范围。 功能二：功能重叠检测（新增时），若发现相似/重复则发出提醒。 功能三：新增/变更 Skill…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 3. 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")
Process rating: all ten parameters 46/100
- 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 48 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1689 tokens
- 100Running it twice. No mutating operations
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 501: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.