AC terminal-screenshot
Render a terminal CLI program's colored output to a PNG so Claude can actually SEE the real visual result — color contrast, alignment, background blocks, highlighting — instead of only reading plain text and raw ANSI escape codes. Use this whenever verifying or debugging how a CLI tool looks in the terminal: delta git diff colors, bat syntax highlighting, starship prompt, eza/ls colors, git diff, ripgrep matches, or any ANSI-colored output. ALWAYS use it right after changing any CLI color config (delta / bat / themes / lazygit pager) to visually confirm the result rather than guessing from hex values — reading a hex code is not the same as seeing the rendered contrast on the real terminal background. Trigger phrases: 看终端效果, 终端截图, 验证配色, 配色对比, 终端真实效果, terminal screenshot, render terminal output, ANSI to image, "does this color look right", "is the contrast enough", delta/bat color verification.
Render a terminal CLI program's colored output to a PNG so Claude can actually SEE the real visual result — color contrast, alignment, background blocks…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 58/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 7 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1523 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 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)
- +3Description length 905: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (4 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.