SKILLEMALL.ai
GitHub ↗ RU Sign in

CF blip-2-vision-language

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

synthetic-sciences/OpenScience Hermes author: synthetic-sciences Apache-2.0 3 files body ≈ 4 227 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Vision-language pre-training framework bridging frozen image encoders and LLMs.

As a process F 34/100 · No process to follow — References files that are not bundled: image, raw_image, query

ProcedureSalesforceAI and agentstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
C
84/100
safety, quality, tests
Safety 60%
92
Quality 40%
73
Run on models
none yet
Process rating
F
34/100
No process to follow
References files that are not bundled: image, raw_image, query
Tools and files w 18
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The text references files that are not there: add them or drop the references.
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 · 8

✓ No critical or high findings

Medium and low: 8
  • low Secrets in code secret-high-entropy-token references/advanced-usage.md:9
    High-entropy token-like string (may be an id, hash or a credential)
    from transformers import Blip…ion, Blip…sor
  • low Secrets in code secret-high-entropy-token references/advanced-usage.md:234
    High-entropy token-like string (may be an id, hash or a credential)
    from transformers import Blip…ion, Blip…sor
  • low Secrets in code secret-high-entropy-token references/advanced-usage.md:264
    High-entropy token-like string (may be an id, hash or a credential)
    from transformers import Blip…sor, Blip…ion
  • low Secrets in code secret-high-entropy-token references/advanced-usage.md:309
    High-entropy token-like string (may be an id, hash or a credential)
    from transformers import Blip…sor, Blip…ion
  • low Secrets in code secret-high-entropy-token references/advanced-usage.md:374
    High-entropy token-like string (may be an id, hash or a credential)
    from transformers import Blip…sor, Blip…ion
  • low Secrets in code secret-high-entropy-token references/troubleshooting.md:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    python -c "from transformers import Blip…ion; print('OK')"
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:66
    High-entropy token-like string (may be an id, hash or a credential)
    from transformers import Blip…sor, Blip…ion
  • low Secrets in code secret-high-entropy-token SKILL.md:307
    High-entropy token-like string (may be an id, hash or a credential)
    from transformers import Blip…sor, Blip…ion

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 228 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning missing-ref reference to a missing file: image
  • warning missing-ref reference to a missing file: raw_image
  • warning missing-ref reference to a missing file: query
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 34/100

Will not run. References files that are not bundled: image, raw_image, query
  • 0Tools and files. 3 referenced file(s) missing: image, raw_image, query
  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (blip-2-vision-language) differs from the folder (blip-2)
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 4227 tokens
  • 100Steps. 24 steps
  • low 10 top-level sections: this looks like several domains in one skill

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)
  • +2Single-language instructions
  • +3Description length 228: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 24 items
  • +3Output format is stated explicitly
  • +4Has examples (16 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.