CD openclaw-skill-manager
OpenClaw skill inventory tool: scans installed skills via the OpenClaw CLI, auto-classifies (10 categories/48 subcategories, user overlay), detects duplicates, exports Markdown/JSON/HTML interactive reports (static sortable HTML, no server), opt-in push of Markdown to Feishu/Notion (env-var credentials, privacy notice), usage stats, missing-dependency graphs, snapshot-diff incremental updates, batch enable/disable with auto-backup, and report-only update checks. CLI output and category labels are Chinese by design. OpenClaw 技能清单工具：经 CLI 扫描已装技能，自动分类（10 大类 48 子类，支持覆盖层）与重复检测，导出 Markdown/JSON/HTML 交互式报告（静态可排序网页，无需服务器），可选推送 Markdown 到飞书/Notion（凭据走环境变量，含隐私提示），使用统计、缺失依赖图、快照增量更新、批量启停（自动备份）、更新检查（只报告）。输出与分类标签为中文。
OpenClaw skill inventory tool: scans installed skills via the OpenClaw CLI, auto-classifies (10 categories/48 subcategories, user overlay), detects…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
Files scanned: 27. 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
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (openclaw-skill-manager) differs from the folder (skill-classifier)
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 41 steps
- 100Execution cost. Instruction body is 1517 tokens
- low 11 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
- -239 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 712: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (9 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.