DC skill-inventory
Office-agent skill inventory & health check. Scans any skills directory, measures size and context-token footprint, detects duplicates, and classifies skills into used / protected / closeable / manual-review buckets. Reverse-dependency scanning locks every skill referenced by automations, hooks or plugins. Read-only by default: two disclosed, consent-gated write targets — `--overrides --apply --yes` (programmatic close on platforms like WorkBuddy; dry-run without --yes) and `--set-lang` (saves the report language preference to ~/.workbuddy/skill-inventory.json) — plus one disclosed backup artifact: a timestamped ~/.workbuddy/settings.json.bak.<ts> safety copy created before the close write, path printed to the user. Report language: auto (default; the Agent decides per conversation language) / zh / en; one-off override via --lang; JSON output is always English-keyed. No network access, no subprocesses. English docs: SKILL.en.md. 办公型 Agent 通用的技能库盘点与效能体检。扫描任意技能目录，统计数量/体积/上下文 token 占用， 识别重复与近似技能，并按「有使用记录/受保护/可关闭候选/需人工确认」四档给出保守建议；反向依赖 扫描会锁定被自动化/Hook/插件引用的技能。默认只读，两处写路径目标均需显式授权：`--overrides --apply --yes`（仅 WorkBuddy 等可关平台，缺 --yes 只做预览）与 `--set-lang`（把报告 语言偏好写入 ~/.workbuddy/skill-inventory.json）；另有一份已披露的备份工件——关闭写入前在 settings.json 旁生成带时间戳的 settings.json.bak.<ts> 安全副本，路径会打印给用户。语言设置三选一： auto（默认，Agent 按对话语言 决定）/ zh / en；--lang 仅本次运行覆盖；--json 输出恒为英文键。无网络、无子进程。 英文文档见 SKILL.en.md。
Office-agent skill inventory & health check.
As a process C 51/100 · Has gaps — 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.
- Shorten the description to 1024 characters.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1390 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary"
Process rating: all ten parameters 51/100
- 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
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (skill-inventory) differs from the folder (agent-skill-inventory)
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 37 steps
- 100Execution cost. Instruction body is 1839 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 10 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)
- +3Description length 1390: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 37 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.