CC skill-construction
Methodology for building a properly structured Claude Code skill (SKILL.md + optional resources + evaluation rubric) from extracted components. Assesses complexity (Level 1 simple - SKILL.md only; Level 2 moderate - SKILL.md plus 1-3 resources; Level 3 complex - SKILL.md plus 4-8 resources), plans the resource grouping, drafts SKILL.md following Anthropic's authoring best practices (concise frontmatter with what + when triggers, body under 500 lines, progressive disclosure to resource files one level deep, workflow checklists), and constructs an evaluation rubric. Use when extracted components and a synthesis verdict are in hand and the next step is to materialize them as a skill. Trigger keywords - construct skill, build SKILL.md, skill construction, skill scaffolding, generate skill files.
Methodology for building a properly structured Claude Code skill (SKILL.md + optional resources + evaluation rubric) from extracted components. Assesses…
As a process C 52/100 · Has gaps — References files that are not bundled: ../component-extraction/SKILL.md, ../synthesis-application/SKILL.md, ../evaluation-rubrics/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../component-extraction/SKILL.md - warning
missing-refreference to a missing file: ../synthesis-application/SKILL.md - warning
missing-refreference to a missing file: ../evaluation-rubrics/SKILL.md
Process rating: all ten parameters 52/100
- 0Tools and files. 3 referenced file(s) missing: ../component-extraction/SKILL.md, ../synthesis-application/SKILL.md, ../evaluation-rubrics/SKILL.md
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 50 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2011 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
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 802: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.