CB skill-publish-guide
Guide for publishing and managing skills on ClawHub. Use when the user wants to publish, update, delete, or manage skills on ClawHub. 当用户需要发布、更新、删除或管理 ClawHub 上的技能时使用此技能。
Guide for publishing and managing skills on ClawHub.
As a process B 68/100 · Nearly there — weak spots: result and completion, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 3
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:190Downloads and executes remote code from an unrecognised host (pipe to shell)2. **Avoid curl|bash as primary install method** / 避免将 curl|bash 作为主要安装方式: Recommend Homebrew, Scoop, or source build first. If including a curl|bash script, add a security warning.
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:191Downloads and executes remote code from an unrecognised host (pipe to shell)优先推荐 Homebrew、Scoop 或源码构建。如包含 curl|bash 脚本，添加安全提示。
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:178Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)| Security scan flagged curl\|bash / 安全扫描标记 curl\|bash | Install script uses `curl \| bash` / 安装脚本使用 `curl \| bash` | Add security warning, recommend Homebrew/source build / 添加安全提示，推荐 Homebrew/源码构建 |
detector
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "env" - note
frontmatter-keyunknown frontmatter key "always"
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 16 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1869 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 170: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.