AF skill-registry-manager
管理和安装 Claude Code skills 的工具。Use when: 列出可用skills、有哪些skills、安装skill、管理skills、添加订阅、列出订阅、查看订阅、删除订阅、取消订阅。NOT for: 与 skill 管理无关的任务。
As a process F 34/100 · Will not run — References files that are not bundled: repo-url
ProcedureSoftware developmentInfrastructureAI and agentstype and topics are labelled automatically from the skill text
How to improve
- The text references files that are not there: add them or drop the references.
For the model run — optional
- 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
- warning
missing-refreference to a missing file: repo-url
Process rating: all ten parameters 34/100
Will not run. References files that are not bundled: repo-url
- 0Tools and files. 1 referenced file(s) missing: repo-url
- 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
- 40Consistency. Frontmatter name (skill-registry-manager) differs from the folder (skills-registry-manager)
- 50When it triggers. No condition that starts the skill
- 100Steps. 44 steps
- 100Execution cost. Instruction body is 1004 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 127: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.
External checks
ClawHub: suspicious
This skill appears to be a skill installer/registry manager, but it gives agents broad installation and remote-fetch authority without enough safety gates or trust-boundary warnings.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026