AC skill-rules-designer
Analyzes an existing Claude Code skill and designs an optimal rules/ file structure. Covers three operations: (1) compressing SKILL.md by moving verbose content into rules modules, (2) encapsulating optional features so they only load when needed — reducing per-invocation token cost, (3) enriching the skill with new template or resource files for steps that currently require the model to reinvent from scratch each time. Also identifies vague instructions and rewrites them to be precise. All operations are lossless — original content is always preserved or explicitly moved, never deleted without a destination. Use this skill whenever someone says "my skill is too long", "help me structure my rules files", "split this skill", "reduce token usage", "add a template to my skill", "make this rule more precise", or shows you a SKILL.md and asks how to improve its structure or efficiency.
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: 6. 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 85Steps. 45 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2870 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 893: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 19 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.