AC plugin-publisher
End-to-end plugin creation and publishing for Claude Code, Cowork, and OpenClaw. Handles the full lifecycle: design the plugin, scaffold it in the correct Anthropic marketplace format, generate an OpenClaw install script, create or connect to a GitHub repo, push it, and package a .plugin file for direct Cowork installation. Use this skill whenever the user says "create a plugin", "publish a plugin", "make a marketplace plugin", "push plugin to GitHub", "package a plugin", "turn this into a plugin", "make this installable", "publish to marketplace", or wants to convert existing skills/agents/workflows into a distributable plugin. Also trigger when the user asks to "update my plugin repo", "restructure my plugin", or "add a new plugin to my marketplace". Even if they just say "plugin" in the context of creating or distributing something, this skill is probably what they need.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-pipe-to-shellscripts/openclaw-generator-template.sh:40Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)err "OpenClaw not found. Install: curl -fsSL https://openclaw.ai/install.sh | bash"
code literalvendor-host
Files scanned: 5. 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 52/100
- 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
- 40Consistency. Frontmatter name (plugin-publisher) differs from the folder (autosolutions-plugin-publisher)
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 56 steps, 1 vague phrases
- 100Execution cost. Instruction body is 2601 tokens
- 100Running it twice. Mutating operations check current state
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 886: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.