AC mcp-to-skill
Converts any MCP server into a standalone skill package with zero runtime dependencies (no MCP process required). Trigger when user says: "convert this MCP to a skill", "I don't want to use MCP anymore", "wrap MCP X as a skill", "MCP is too heavy", "turn MCP capabilities into a skill". Does: connects to MCP server to extract tool schemas, analyzes source code to infer equivalent Bash commands, generates a ready-to-use skill package and registers it with the agent, optionally asks user to remove the original MCP. Does NOT: execute MCP tool calls to complete tasks (that's using MCP, not converting it); wrap existing Bash scripts as skills (use skill-creator); execute MCP business logic. Optional dependency: skill-creator (improves generated SKILL.md quality).
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1593 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 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
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 767: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.