AC multi-channel-skill-publisher
Publish ONE skill to ALL agent-skill channels from a single source of truth: the ClawHub skill registry, a ClawHub bundle-plugin package, and a Claude Code plugin marketplace (plain GitHub repo). Use when the user wants to publish, release, rename, or version-bump a skill/plugin across registries, or asks how to package a skill as a Claude Code plugin or OpenClaw bundle plugin. Covers the SSOT/sync model against redundancy, exact manifests (plugin.json, marketplace.json, openclaw.plugin.json), known CLI bugs and their web-UI workarounds (rename, --name, display-name fallback), versioning pitfalls (permanent versions, highest-version-wins display name, web-UI version drift), and publish gotchas (version must exceed live on BOTH namespaces, push before source-linked package publish, name-driven search).
Publish ONE skill to ALL agent-skill channels from a single source of truth: the ClawHub skill registry, a ClawHub bundle-plugin package, and a Claude Code…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
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: 2. 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 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, git, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2253 tokens
- 100Running it twice. Mutating operations check current state
- high The skill tells the model to perform an irreversible action with no human approval
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 812: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 8 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.