AB reimagine-it
Claude Code / Codex / Factory Droid plugin and Cursor / Copilot / Gemini CLI Agent Skill. Install with npx skills add Kayforkind/reimagine-it, /plugin marketplace add Kayforkind/reimagine-it, or codex plugin marketplace add Kayforkind/reimagine-it. Redesign any file from its own content: webpage, HTML, landing page, README, PDF, document, slides, PowerPoint, infographic, SVG, dashboard, CLI, or protocol. Use when the user says /reimagine-it, reimagine it, reinvent this, redesign this page, make an infographic, content-aware redesign, or wants a visual leap instead of a mood board. Tokens: artistic, cinematic, photography, neon, glassmorphism, bento, infographic, svg, 3js, simulation, plus leftover words as an open brief. Not /better.
Claude Code / Codex / Factory Droid plugin and Cursor / Copilot / Gemini CLI Agent Skill.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, execution cost, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 36. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9689 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 13 mutating operations with no state check
- 40Execution cost. Instruction body is 9689 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 99 steps, 3 vague phrases
- 100Failures and branches. 12 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (23 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +3Description length 743: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 99 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.