SKILLEMALL.ai
GitHub ↗ RU Sign in

CD fireworks-ai-inference

Fast inference and fine-tuning platform with serverless and on-demand GPU deployments. OpenAI-compatible API for chat completions, embeddings, function calling, vision, and structured output. Supports SFT, DPO, and RL fine-tuning. SOC2 + HIPAA compliant.

synthetic-sciences/OpenScience Hermes author: synthetic-sciences Apache-2.0 1 file body ≈ 5 024 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Fast inference and fine-tuning platform with serverless and on-demand GPU deployments.

As a process D 37/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI 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%
94
Quality 40%
68
Run on models
none yet
Process rating
D
37/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:458
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -sSL https://cli.fireworks.ai/install.sh | bash
    vendor-host
  • low Exfiltration net-credential-use SKILL.md:62
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    os.environ["FIREWORKS_API_KEY"] = "fw_..."  # from https://fireworks.ai/api-keys
    vendor-host

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 254 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning body-long SKILL.md body ≈ 5024 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 37/100

  • 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
  • 30Running it twice. 22 mutating operations with no state check
  • 40Consistency. Frontmatter name (fireworks-ai-inference) differs from the folder (fireworks-ai)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5024 tokens
  • 100Steps. 20 steps
  • low 13 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)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 254: enough signal without eating the budget
  • +4Structure: 48 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (30 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.