AC search-image
Search images from text queries and return the most relevant image result, candidate images, source pages, or ready-to-open search links. Use when the user asks to search for an image, find reference images, look up a character, person, brand, mascot, meme, wallpaper, avatar, or logo, wants several engines searched, wants the best match instead of the literal first result, or wants the best candidate sent as an attachment. Prefer multi-engine search with relevance ranking, then download and send the best match; if confidence is weak or downloading fails, return several candidate links and search URLs.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, consistency, 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: 21. 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 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 17 mutating operations with no state check
- 40Consistency. Frontmatter name (search-image) differs from the folder (smart-image-search)
- 60Tools and files. Uses tools (bash, 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. 92 steps, 1 vague phrases
- 100Failures and branches. 10 branches, has a failure section
- 100Execution cost. Instruction body is 2063 tokens
- low 11 top-level sections: this looks like several domains in one skill
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -32 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 608: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 92 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.