AD deepseek-ocr
OCR text recognition using DeepSeek-OCR model. Use when user asks for OCR, text recognition, image text extraction, screenshot recognition, or converting images to text/markdown.
As a process D 40/100 · Unfinished process — weak spots: steps, result and completion, when it triggers
How to improve
For the model run — optional
- 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 40/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (deepseek-ocr) differs from the folder (ucloud-deepseek-ocr)
- 43Steps. 2 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 290 tokens
- 100Running it twice. No mutating operations
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 178: enough signal without eating the budget
- +4Structure: 6 headings
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.
External checks
ClawHub: clean
This is a straightforward cloud OCR helper that uploads a user-selected image to a configured API, with privacy caveats but no evidence of hidden, destructive, or deceptive behavior.
LLM: benign (high) · VirusTotal: suspicious · 28 May 2026