AB skill-hub-united
Install skills from multiple skill hubs with one tool: clawhub.ai (default), skillhub.cn (SkillHub, China-optimized), skills.sh (npx skills, GitHub-based), the official anthropics/skills repo, and your own self-hosted "custom" hub. Routes to the right source based on how the user phrases the request, handles name collisions (rename/overwrite/abort), Anthropic source-available license gating, multi-skill repos, and path-traversal-safe extraction. Use when the user says "install skill X", "add skill X", "download skill X", "get X from clawhub", "get X from skillhub.cn", "use skills.sh to install X", "install the claude/anthropic X skill", or "install X from my hub". Also triggers in Chinese: "安装skill xxx"、"装一下xxx"、"下载skill xxx"、 "从 clawhub 装 xxx"、"从 skillhub.cn 装 xxx"、"用 skills.sh 装 xxx"、 "装 claude 的 xxx"、"从我的 hub 装 xxx"。
Install skills from multiple skill hubs with one tool: clawhub.ai (default), skillhub.cn (SkillHub, China-optimized), skills.sh (npx skills, GitHub-based)…
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-shell-rcREADME.md:69Writes to a shell startup file (security demo / example)echo 'export SKILL_HUB_CUSTOM_URL="https://my-hub.example.com/api/skill/download"' >> ~/.bashrc
demo -
low Dangerous commands
cmd-shell-rcSKILL.md:103Writes to a shell startup file (security demo / example)echo 'export SKILL_HUB_CUSTOM_URL="https://my-hub.example.com/api/skill/download"' >> ~/.bashrc
demo
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 100Steps. 55 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2192 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 831: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.