AF skill-architect
Design and create new AI skills with the right internal structure — not just correct formatting. Works with any AI coding tool (Claude Code, Google Antigravity, Cursor, Windsurf, Cline, GitHub Copilot, etc.). Use this skill when someone wants to build a new skill and wants it to be well-structured from the ground up. Triggers on: "create a skill", "build a skill", "make a skill for X", "help me write a skill", "I want a skill that does X", "design a skill". Unlike a generic skill creator, skill-architect interviews you first to understand how the skill needs to work, then applies the right design pattern (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline, or combinations) before writing a single line — so the skill behaves correctly, not just looks correct.
As a process F 57/100 · Will not run — References files that are not bundled: references/style-guide.md, assets/[output]-template.md, references/review-checklist.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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/style-guide.md - warning
missing-refreference to a missing file: assets/[output]-template.md - warning
missing-refreference to a missing file: references/review-checklist.md - warning
missing-refreference to a missing file: references/conventions.md
Process rating: all ten parameters 57/100
- 0Tools and files. 4 referenced file(s) missing: references/style-guide.md, assets/[output]-template.md, references/review-checklist.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 6 branches
- 100Steps. 56 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3389 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 772: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 56 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.