AB skill-publish
Publish AI agent skills to GitHub and multiple skill registries (skills.sh, clawhub.ai) in one workflow. Use this skill whenever the user wants to publish, upload, or push a skill to GitHub, skills.sh, clawhub.ai, or says things like "publish skill", "推送skill", "发布skill", "上传skill到平台", "publish to marketplace", "多平台发布". Also trigger when the user wants to update an already-published skill across platforms. This skill handles git push, registry publishing, and version management.
As a process B 65/100 · Nearly there — weak spots: result and completion, consistency
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 · 0
✓ No critical or high findings
Files scanned: 3. 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
- 40Consistency. Frontmatter name (skill-publish) differs from the folder (skill-publish-skill)
- 60Tools and files. Uses tools (bash, git) 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. 66 steps, 1 vague phrases
- 100Failures and branches. 15 branches, has a failure section
- 100Execution cost. Instruction body is 1836 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (15 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 483: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 66 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.